4128 lines
315 KiB
Plaintext
4128 lines
315 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "403799f7",
|
||
"metadata": {
|
||
"origin_pos": 0
|
||
},
|
||
"source": [
|
||
"# 锚框\n",
|
||
":label:`sec_anchor`\n",
|
||
"\n",
|
||
"目标检测算法通常会在输入图像中采样大量的区域，然后判断这些区域中是否包含我们感兴趣的目标，并调整区域边界从而更准确地预测目标的*真实边界框*（ground-truth bounding box）。\n",
|
||
"不同的模型使用的区域采样方法可能不同。\n",
|
||
"这里我们介绍其中的一种方法：以每个像素为中心，生成多个缩放比和宽高比（aspect ratio）不同的边界框。\n",
|
||
"这些边界框被称为*锚框*（anchor box）我们将在 :numref:`sec_ssd`中设计一个基于锚框的目标检测模型。\n",
|
||
"\n",
|
||
"首先，让我们修改输出精度，以获得更简洁的输出。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "e079962e",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:42.677769Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:42.676695Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.106116Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.104773Z"
|
||
},
|
||
"origin_pos": 2,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"%matplotlib inline\n",
|
||
"import torch\n",
|
||
"from d2l import torch as d2l\n",
|
||
"\n",
|
||
"torch.set_printoptions(2) # 精简输出精度"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "dc5b92b8",
|
||
"metadata": {
|
||
"origin_pos": 4
|
||
},
|
||
"source": [
|
||
"## 生成多个锚框\n",
|
||
"\n",
|
||
"假设输入图像的高度为$h$，宽度为$w$。\n",
|
||
"我们以图像的每个像素为中心生成不同形状的锚框：*缩放比*为$s\\in (0, 1]$，*宽高比*为$r > 0$。\n",
|
||
"那么[**锚框的宽度和高度分别是$hs\\sqrt{r}$和$hs/\\sqrt{r}$。**]\n",
|
||
"请注意，当中心位置给定时，已知宽和高的锚框是确定的。\n",
|
||
"\n",
|
||
"要生成多个不同形状的锚框，让我们设置许多缩放比（scale）取值$s_1,\\ldots, s_n$和许多宽高比（aspect ratio）取值$r_1,\\ldots, r_m$。\n",
|
||
"当使用这些比例和长宽比的所有组合以每个像素为中心时，输入图像将总共有$whnm$个锚框。\n",
|
||
"尽管这些锚框可能会覆盖所有真实边界框，但计算复杂性很容易过高。\n",
|
||
"在实践中，(**我们只考虑**)包含$s_1$或$r_1$的(**组合：**)\n",
|
||
"\n",
|
||
"(**\n",
|
||
"$$(s_1, r_1), (s_1, r_2), \\ldots, (s_1, r_m), (s_2, r_1), (s_3, r_1), \\ldots, (s_n, r_1).$$\n",
|
||
"**)\n",
|
||
"\n",
|
||
"也就是说，以同一像素为中心的锚框的数量是$n+m-1$。\n",
|
||
"对于整个输入图像，将共生成$wh(n+m-1)$个锚框。\n",
|
||
"\n",
|
||
"上述生成锚框的方法在下面的`multibox_prior`函数中实现。\n",
|
||
"我们指定输入图像、尺寸列表和宽高比列表，然后此函数将返回所有的锚框。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "4c5fb635",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.112186Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.111657Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.126939Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.125859Z"
|
||
},
|
||
"origin_pos": 6,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def multibox_prior(data, sizes, ratios):\n",
|
||
" \"\"\"生成以每个像素为中心具有不同形状的锚框\"\"\"\n",
|
||
" in_height, in_width = data.shape[-2:]\n",
|
||
" device, num_sizes, num_ratios = data.device, len(sizes), len(ratios)\n",
|
||
" boxes_per_pixel = (num_sizes + num_ratios - 1)\n",
|
||
" size_tensor = torch.tensor(sizes, device=device)\n",
|
||
" ratio_tensor = torch.tensor(ratios, device=device)\n",
|
||
"\n",
|
||
" # 为了将锚点移动到像素的中心，需要设置偏移量。\n",
|
||
" # 因为一个像素的高为1且宽为1，我们选择偏移我们的中心0.5\n",
|
||
" offset_h, offset_w = 0.5, 0.5\n",
|
||
" steps_h = 1.0 / in_height # 在y轴上缩放步长\n",
|
||
" steps_w = 1.0 / in_width # 在x轴上缩放步长\n",
|
||
"\n",
|
||
" # 生成锚框的所有中心点\n",
|
||
" center_h = (torch.arange(in_height, device=device) + offset_h) * steps_h\n",
|
||
" center_w = (torch.arange(in_width, device=device) + offset_w) * steps_w\n",
|
||
" shift_y, shift_x = torch.meshgrid(center_h, center_w, indexing='ij')\n",
|
||
" shift_y, shift_x = shift_y.reshape(-1), shift_x.reshape(-1)\n",
|
||
"\n",
|
||
" # 生成“boxes_per_pixel”个高和宽，\n",
|
||
" # 之后用于创建锚框的四角坐标(xmin,xmax,ymin,ymax)\n",
|
||
" w = torch.cat((size_tensor * torch.sqrt(ratio_tensor[0]),\n",
|
||
" sizes[0] * torch.sqrt(ratio_tensor[1:])))\\\n",
|
||
" * in_height / in_width # 处理矩形输入\n",
|
||
" h = torch.cat((size_tensor / torch.sqrt(ratio_tensor[0]),\n",
|
||
" sizes[0] / torch.sqrt(ratio_tensor[1:])))\n",
|
||
" # 除以2来获得半高和半宽\n",
|
||
" anchor_manipulations = torch.stack((-w, -h, w, h)).T.repeat(\n",
|
||
" in_height * in_width, 1) / 2\n",
|
||
"\n",
|
||
" # 每个中心点都将有“boxes_per_pixel”个锚框，\n",
|
||
" # 所以生成含所有锚框中心的网格，重复了“boxes_per_pixel”次\n",
|
||
" out_grid = torch.stack([shift_x, shift_y, shift_x, shift_y],\n",
|
||
" dim=1).repeat_interleave(boxes_per_pixel, dim=0)\n",
|
||
" output = out_grid + anchor_manipulations\n",
|
||
" return output.unsqueeze(0)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "8f03ef54",
|
||
"metadata": {
|
||
"origin_pos": 8
|
||
},
|
||
"source": [
|
||
"可以看到[**返回的锚框变量`Y`的形状**]是（批量大小，锚框的数量，4）。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "f411d4af",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.131714Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.131003Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.238891Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.237843Z"
|
||
},
|
||
"origin_pos": 10,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"561 728\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"torch.Size([1, 2042040, 4])"
|
||
]
|
||
},
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"img = d2l.plt.imread('../img/catdog.jpg')\n",
|
||
"h, w = img.shape[:2]\n",
|
||
"\n",
|
||
"print(h, w)\n",
|
||
"X = torch.rand(size=(1, 3, h, w))\n",
|
||
"Y = multibox_prior(X, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5])\n",
|
||
"Y.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a368b5c5",
|
||
"metadata": {
|
||
"origin_pos": 12
|
||
},
|
||
"source": [
|
||
"将锚框变量`Y`的形状更改为(图像高度,图像宽度,以同一像素为中心的锚框的数量,4)后，我们可以获得以指定像素的位置为中心的所有锚框。\n",
|
||
"在接下来的内容中，我们[**访问以（250,250）为中心的第一个锚框**]。\n",
|
||
"它有四个元素：锚框左上角的$(x, y)$轴坐标和右下角的$(x, y)$轴坐标。\n",
|
||
"输出中两个轴的坐标各分别除以了图像的宽度和高度。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "a7b7cfa3",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.244522Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.243982Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.252916Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.251985Z"
|
||
},
|
||
"origin_pos": 13,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"tensor([0.06, 0.07, 0.63, 0.82])"
|
||
]
|
||
},
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"boxes = Y.reshape(h, w, 5, 4)\n",
|
||
"boxes[250, 250, 0, :]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "eb941166",
|
||
"metadata": {
|
||
"origin_pos": 15
|
||
},
|
||
"source": [
|
||
"为了[**显示以图像中以某个像素为中心的所有锚框**]，定义下面的`show_bboxes`函数来在图像上绘制多个边界框。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "b2dc5400",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.257994Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.257297Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.267572Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.266638Z"
|
||
},
|
||
"origin_pos": 16,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def show_bboxes(axes, bboxes, labels=None, colors=None):\n",
|
||
" \"\"\"显示所有边界框\"\"\"\n",
|
||
" def _make_list(obj, default_values=None):\n",
|
||
" if obj is None:\n",
|
||
" obj = default_values\n",
|
||
" elif not isinstance(obj, (list, tuple)):\n",
|
||
" obj = [obj]\n",
|
||
" return obj\n",
|
||
"\n",
|
||
" labels = _make_list(labels)\n",
|
||
" colors = _make_list(colors, ['b', 'g', 'r', 'm', 'c'])\n",
|
||
" for i, bbox in enumerate(bboxes):\n",
|
||
" color = colors[i % len(colors)]\n",
|
||
" rect = d2l.bbox_to_rect(bbox.detach().numpy(), color)\n",
|
||
" axes.add_patch(rect)\n",
|
||
" if labels and len(labels) > i:\n",
|
||
" text_color = 'k' if color == 'w' else 'w'\n",
|
||
" axes.text(rect.xy[0], rect.xy[1], labels[i],\n",
|
||
" va='center', ha='center', fontsize=9, color=text_color,\n",
|
||
" bbox=dict(facecolor=color, lw=0))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0aefc961",
|
||
"metadata": {
|
||
"origin_pos": 17
|
||
},
|
||
"source": [
|
||
"正如从上面代码中所看到的，变量`boxes`中$x$轴和$y$轴的坐标值已分别除以图像的宽度和高度。\n",
|
||
"绘制锚框时，我们需要恢复它们原始的坐标值。\n",
|
||
"因此，在下面定义了变量`bbox_scale`。\n",
|
||
"现在可以绘制出图像中所有以(250,250)为中心的锚框了。\n",
|
||
"如下所示，缩放比为0.75且宽高比为1的蓝色锚框很好地围绕着图像中的狗。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "c199e557",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.272415Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.271753Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.634073Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.632866Z"
|
||
},
|
||
"origin_pos": 18,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/svg+xml": [
|
||
"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n",
|
||
"<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
|
||
" \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
|
||
"<svg xmlns:xlink=\"http://www.w3.org/1999/xlink\" width=\"229.502021pt\" height=\"182.601395pt\" viewBox=\"0 0 229.502021 182.601395\" xmlns=\"http://www.w3.org/2000/svg\" version=\"1.1\">\n",
|
||
" <metadata>\n",
|
||
" <rdf:RDF xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n",
|
||
" <cc:Work>\n",
|
||
" <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n",
|
||
" <dc:date>2023-08-18T07:00:45.532795</dc:date>\n",
|
||
" <dc:format>image/svg+xml</dc:format>\n",
|
||
" <dc:creator>\n",
|
||
" <cc:Agent>\n",
|
||
" <dc:title>Matplotlib v3.5.1, https://matplotlib.org/</dc:title>\n",
|
||
" </cc:Agent>\n",
|
||
" </dc:creator>\n",
|
||
" </cc:Work>\n",
|
||
" </rdf:RDF>\n",
|
||
" </metadata>\n",
|
||
" <defs>\n",
|
||
" <style type=\"text/css\">*{stroke-linejoin: round; stroke-linecap: butt}</style>\n",
|
||
" </defs>\n",
|
||
" <g id=\"figure_1\">\n",
|
||
" <g id=\"patch_1\">\n",
|
||
" <path d=\"M 0 182.601395 \n",
|
||
"L 229.502021 182.601395 \n",
|
||
"L 229.502021 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 182.601395 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 45.946941 158.72327 \n",
|
||
"L 222.302021 158.72327 \n",
|
||
"L 222.302021 22.82327 \n",
|
||
"L 45.946941 22.82327 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g clip-path=\"url(#pfd4dce92da)\">\n",
|
||
" <image xlink:href=\"data:image/png;base64,\n",
|
||
"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\" id=\"image4ee7073173\" transform=\"scale(1 -1)translate(0 -136)\" x=\"45.946941\" y=\"-22.72327\" width=\"177\" height=\"136\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 55.788187 32.664511 \n",
|
||
"L 157.713184 32.664511 \n",
|
||
"L 157.713184 134.589506 \n",
|
||
"L 55.788187 134.589506 \n",
|
||
"L 55.788187 32.664511 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfd4dce92da)\" style=\"fill: none; stroke: #0000ff; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 72.775686 49.652011 \n",
|
||
"L 140.725677 49.652011 \n",
|
||
"L 140.725677 117.602006 \n",
|
||
"L 72.775686 117.602006 \n",
|
||
"L 72.775686 49.652011 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfd4dce92da)\" style=\"fill: none; stroke: #008000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 89.763184 66.639513 \n",
|
||
"L 123.738184 66.639513 \n",
|
||
"L 123.738184 100.614506 \n",
|
||
"L 89.763184 100.614506 \n",
|
||
"L 89.763184 66.639513 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfd4dce92da)\" style=\"fill: none; stroke: #ff0000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_6\">\n",
|
||
" <path d=\"M 34.678828 47.591083 \n",
|
||
"L 178.822562 47.591083 \n",
|
||
"L 178.822562 119.662945 \n",
|
||
"L 34.678828 119.662945 \n",
|
||
"L 34.678828 47.591083 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfd4dce92da)\" style=\"fill: none; stroke: #bf00bf; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 70.714756 11.555156 \n",
|
||
"L 142.786608 11.555156 \n",
|
||
"L 142.786608 155.698862 \n",
|
||
"L 70.714756 155.698862 \n",
|
||
"L 70.714756 11.555156 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfd4dce92da)\" style=\"fill: none; stroke: #00bfbf; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m55255c8e12\" d=\"M 0 0 \n",
|
||
"L 0 3.5 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m55255c8e12\" x=\"46.068064\" y=\"158.72327\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(42.886814 173.321707)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-30\" d=\"M 2034 4250 \n",
|
||
"Q 1547 4250 1301 3770 \n",
|
||
"Q 1056 3291 1056 2328 \n",
|
||
"Q 1056 1369 1301 889 \n",
|
||
"Q 1547 409 2034 409 \n",
|
||
"Q 2525 409 2770 889 \n",
|
||
"Q 3016 1369 3016 2328 \n",
|
||
"Q 3016 3291 2770 3770 \n",
|
||
"Q 2525 4250 2034 4250 \n",
|
||
"z\n",
|
||
"M 2034 4750 \n",
|
||
"Q 2819 4750 3233 4129 \n",
|
||
"Q 3647 3509 3647 2328 \n",
|
||
"Q 3647 1150 3233 529 \n",
|
||
"Q 2819 -91 2034 -91 \n",
|
||
"Q 1250 -91 836 529 \n",
|
||
"Q 422 1150 422 2328 \n",
|
||
"Q 422 3509 836 4129 \n",
|
||
"Q 1250 4750 2034 4750 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m55255c8e12\" x=\"94.517262\" y=\"158.72327\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(84.973512 173.321707)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-32\" d=\"M 1228 531 \n",
|
||
"L 3431 531 \n",
|
||
"L 3431 0 \n",
|
||
"L 469 0 \n",
|
||
"L 469 531 \n",
|
||
"Q 828 903 1448 1529 \n",
|
||
"Q 2069 2156 2228 2338 \n",
|
||
"Q 2531 2678 2651 2914 \n",
|
||
"Q 2772 3150 2772 3378 \n",
|
||
"Q 2772 3750 2511 3984 \n",
|
||
"Q 2250 4219 1831 4219 \n",
|
||
"Q 1534 4219 1204 4116 \n",
|
||
"Q 875 4013 500 3803 \n",
|
||
"L 500 4441 \n",
|
||
"Q 881 4594 1212 4672 \n",
|
||
"Q 1544 4750 1819 4750 \n",
|
||
"Q 2544 4750 2975 4387 \n",
|
||
"Q 3406 4025 3406 3419 \n",
|
||
"Q 3406 3131 3298 2873 \n",
|
||
"Q 3191 2616 2906 2266 \n",
|
||
"Q 2828 2175 2409 1742 \n",
|
||
"Q 1991 1309 1228 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m55255c8e12\" x=\"142.96646\" y=\"158.72327\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(133.42271 173.321707)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-34\" d=\"M 2419 4116 \n",
|
||
"L 825 1625 \n",
|
||
"L 2419 1625 \n",
|
||
"L 2419 4116 \n",
|
||
"z\n",
|
||
"M 2253 4666 \n",
|
||
"L 3047 4666 \n",
|
||
"L 3047 1625 \n",
|
||
"L 3713 1625 \n",
|
||
"L 3713 1100 \n",
|
||
"L 3047 1100 \n",
|
||
"L 3047 0 \n",
|
||
"L 2419 0 \n",
|
||
"L 2419 1100 \n",
|
||
"L 313 1100 \n",
|
||
"L 313 1709 \n",
|
||
"L 2253 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m55255c8e12\" x=\"191.415657\" y=\"158.72327\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 600 -->\n",
|
||
" <g transform=\"translate(181.871907 173.321707)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-36\" d=\"M 2113 2584 \n",
|
||
"Q 1688 2584 1439 2293 \n",
|
||
"Q 1191 2003 1191 1497 \n",
|
||
"Q 1191 994 1439 701 \n",
|
||
"Q 1688 409 2113 409 \n",
|
||
"Q 2538 409 2786 701 \n",
|
||
"Q 3034 994 3034 1497 \n",
|
||
"Q 3034 2003 2786 2293 \n",
|
||
"Q 2538 2584 2113 2584 \n",
|
||
"z\n",
|
||
"M 3366 4563 \n",
|
||
"L 3366 3988 \n",
|
||
"Q 3128 4100 2886 4159 \n",
|
||
"Q 2644 4219 2406 4219 \n",
|
||
"Q 1781 4219 1451 3797 \n",
|
||
"Q 1122 3375 1075 2522 \n",
|
||
"Q 1259 2794 1537 2939 \n",
|
||
"Q 1816 3084 2150 3084 \n",
|
||
"Q 2853 3084 3261 2657 \n",
|
||
"Q 3669 2231 3669 1497 \n",
|
||
"Q 3669 778 3244 343 \n",
|
||
"Q 2819 -91 2113 -91 \n",
|
||
"Q 1303 -91 875 529 \n",
|
||
"Q 447 1150 447 2328 \n",
|
||
"Q 447 3434 972 4092 \n",
|
||
"Q 1497 4750 2381 4750 \n",
|
||
"Q 2619 4750 2861 4703 \n",
|
||
"Q 3103 4656 3366 4563 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-36\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"me0e7b9b398\" d=\"M 0 0 \n",
|
||
"L -3.5 0 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me0e7b9b398\" x=\"45.946941\" y=\"22.944393\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(32.584441 26.743612)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me0e7b9b398\" x=\"45.946941\" y=\"47.168992\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- 100 -->\n",
|
||
" <g transform=\"translate(19.859441 50.968211)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-31\" d=\"M 794 531 \n",
|
||
"L 1825 531 \n",
|
||
"L 1825 4091 \n",
|
||
"L 703 3866 \n",
|
||
"L 703 4441 \n",
|
||
"L 1819 4666 \n",
|
||
"L 2450 4666 \n",
|
||
"L 2450 531 \n",
|
||
"L 3481 531 \n",
|
||
"L 3481 0 \n",
|
||
"L 794 0 \n",
|
||
"L 794 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me0e7b9b398\" x=\"45.946941\" y=\"71.393591\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(19.859441 75.192809)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me0e7b9b398\" x=\"45.946941\" y=\"95.61819\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 300 -->\n",
|
||
" <g transform=\"translate(19.859441 99.417408)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-33\" d=\"M 2597 2516 \n",
|
||
"Q 3050 2419 3304 2112 \n",
|
||
"Q 3559 1806 3559 1356 \n",
|
||
"Q 3559 666 3084 287 \n",
|
||
"Q 2609 -91 1734 -91 \n",
|
||
"Q 1441 -91 1130 -33 \n",
|
||
"Q 819 25 488 141 \n",
|
||
"L 488 750 \n",
|
||
"Q 750 597 1062 519 \n",
|
||
"Q 1375 441 1716 441 \n",
|
||
"Q 2309 441 2620 675 \n",
|
||
"Q 2931 909 2931 1356 \n",
|
||
"Q 2931 1769 2642 2001 \n",
|
||
"Q 2353 2234 1838 2234 \n",
|
||
"L 1294 2234 \n",
|
||
"L 1294 2753 \n",
|
||
"L 1863 2753 \n",
|
||
"Q 2328 2753 2575 2939 \n",
|
||
"Q 2822 3125 2822 3475 \n",
|
||
"Q 2822 3834 2567 4026 \n",
|
||
"Q 2313 4219 1838 4219 \n",
|
||
"Q 1578 4219 1281 4162 \n",
|
||
"Q 984 4106 628 3988 \n",
|
||
"L 628 4550 \n",
|
||
"Q 988 4650 1302 4700 \n",
|
||
"Q 1616 4750 1894 4750 \n",
|
||
"Q 2613 4750 3031 4423 \n",
|
||
"Q 3450 4097 3450 3541 \n",
|
||
"Q 3450 3153 3228 2886 \n",
|
||
"Q 3006 2619 2597 2516 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-33\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me0e7b9b398\" x=\"45.946941\" y=\"119.842789\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(19.859441 123.642007)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_6\">\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me0e7b9b398\" x=\"45.946941\" y=\"144.067388\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 500 -->\n",
|
||
" <g transform=\"translate(19.859441 147.866606)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-35\" d=\"M 691 4666 \n",
|
||
"L 3169 4666 \n",
|
||
"L 3169 4134 \n",
|
||
"L 1269 4134 \n",
|
||
"L 1269 2991 \n",
|
||
"Q 1406 3038 1543 3061 \n",
|
||
"Q 1681 3084 1819 3084 \n",
|
||
"Q 2600 3084 3056 2656 \n",
|
||
"Q 3513 2228 3513 1497 \n",
|
||
"Q 3513 744 3044 326 \n",
|
||
"Q 2575 -91 1722 -91 \n",
|
||
"Q 1428 -91 1123 -41 \n",
|
||
"Q 819 9 494 109 \n",
|
||
"L 494 744 \n",
|
||
"Q 775 591 1075 516 \n",
|
||
"Q 1375 441 1709 441 \n",
|
||
"Q 2250 441 2565 725 \n",
|
||
"Q 2881 1009 2881 1497 \n",
|
||
"Q 2881 1984 2565 2268 \n",
|
||
"Q 2250 2553 1709 2553 \n",
|
||
"Q 1456 2553 1204 2497 \n",
|
||
"Q 953 2441 691 2322 \n",
|
||
"L 691 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_8\">\n",
|
||
" <path d=\"M 45.946941 158.72327 \n",
|
||
"L 45.946941 22.82327 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_9\">\n",
|
||
" <path d=\"M 222.302021 158.72327 \n",
|
||
"L 222.302021 22.82327 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_10\">\n",
|
||
" <path d=\"M 45.946941 158.72327 \n",
|
||
"L 222.302021 158.72327 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_11\">\n",
|
||
" <path d=\"M 45.946941 22.82327 \n",
|
||
"L 222.302021 22.82327 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <g id=\"patch_12\">\n",
|
||
" <path d=\"M 24.349359 40.979668 \n",
|
||
"L 87.227015 40.979668 \n",
|
||
"L 87.227015 24.349355 \n",
|
||
"L 24.349359 24.349355 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #0000ff\"/>\n",
|
||
" </g>\n",
|
||
" <!-- s=0.75, r=1 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(28.309359 35.147949)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-73\" d=\"M 2834 3397 \n",
|
||
"L 2834 2853 \n",
|
||
"Q 2591 2978 2328 3040 \n",
|
||
"Q 2066 3103 1784 3103 \n",
|
||
"Q 1356 3103 1142 2972 \n",
|
||
"Q 928 2841 928 2578 \n",
|
||
"Q 928 2378 1081 2264 \n",
|
||
"Q 1234 2150 1697 2047 \n",
|
||
"L 1894 2003 \n",
|
||
"Q 2506 1872 2764 1633 \n",
|
||
"Q 3022 1394 3022 966 \n",
|
||
"Q 3022 478 2636 193 \n",
|
||
"Q 2250 -91 1575 -91 \n",
|
||
"Q 1294 -91 989 -36 \n",
|
||
"Q 684 19 347 128 \n",
|
||
"L 347 722 \n",
|
||
"Q 666 556 975 473 \n",
|
||
"Q 1284 391 1588 391 \n",
|
||
"Q 1994 391 2212 530 \n",
|
||
"Q 2431 669 2431 922 \n",
|
||
"Q 2431 1156 2273 1281 \n",
|
||
"Q 2116 1406 1581 1522 \n",
|
||
"L 1381 1569 \n",
|
||
"Q 847 1681 609 1914 \n",
|
||
"Q 372 2147 372 2553 \n",
|
||
"Q 372 3047 722 3315 \n",
|
||
"Q 1072 3584 1716 3584 \n",
|
||
"Q 2034 3584 2315 3537 \n",
|
||
"Q 2597 3491 2834 3397 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-3d\" d=\"M 678 2906 \n",
|
||
"L 4684 2906 \n",
|
||
"L 4684 2381 \n",
|
||
"L 678 2381 \n",
|
||
"L 678 2906 \n",
|
||
"z\n",
|
||
"M 678 1631 \n",
|
||
"L 4684 1631 \n",
|
||
"L 4684 1100 \n",
|
||
"L 678 1100 \n",
|
||
"L 678 1631 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-2e\" d=\"M 684 794 \n",
|
||
"L 1344 794 \n",
|
||
"L 1344 0 \n",
|
||
"L 684 0 \n",
|
||
"L 684 794 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-37\" d=\"M 525 4666 \n",
|
||
"L 3525 4666 \n",
|
||
"L 3525 4397 \n",
|
||
"L 1831 0 \n",
|
||
"L 1172 0 \n",
|
||
"L 2766 4134 \n",
|
||
"L 525 4134 \n",
|
||
"L 525 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-2c\" d=\"M 750 794 \n",
|
||
"L 1409 794 \n",
|
||
"L 1409 256 \n",
|
||
"L 897 -744 \n",
|
||
"L 494 -744 \n",
|
||
"L 750 256 \n",
|
||
"L 750 794 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-72\" d=\"M 2631 2963 \n",
|
||
"Q 2534 3019 2420 3045 \n",
|
||
"Q 2306 3072 2169 3072 \n",
|
||
"Q 1681 3072 1420 2755 \n",
|
||
"Q 1159 2438 1159 1844 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1341 3275 1631 3429 \n",
|
||
"Q 1922 3584 2338 3584 \n",
|
||
"Q 2397 3584 2469 3576 \n",
|
||
"Q 2541 3569 2628 3553 \n",
|
||
"L 2631 2963 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"52.099609\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"135.888672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"199.511719\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-37\" x=\"231.298828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\" x=\"294.921875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2c\" x=\"358.544922\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"390.332031\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"422.119141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"463.232422\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\" x=\"547.021484\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <g id=\"patch_13\">\n",
|
||
" <path d=\"M 44.199983 57.967168 \n",
|
||
"L 101.351389 57.967168 \n",
|
||
"L 101.351389 41.336855 \n",
|
||
"L 44.199983 41.336855 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #008000\"/>\n",
|
||
" </g>\n",
|
||
" <!-- s=0.5, r=1 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(48.159983 52.135449)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"52.099609\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"135.888672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"199.511719\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\" x=\"231.298828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2c\" x=\"294.921875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"326.708984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"358.496094\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"399.609375\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\" x=\"483.398438\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_13\">\n",
|
||
" <g id=\"patch_14\">\n",
|
||
" <path d=\"M 58.324356 74.954669 \n",
|
||
"L 121.202012 74.954669 \n",
|
||
"L 121.202012 58.324357 \n",
|
||
"L 58.324356 58.324357 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ff0000\"/>\n",
|
||
" </g>\n",
|
||
" <!-- s=0.25, r=1 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(62.284356 69.122951)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"52.099609\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"135.888672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"199.511719\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\" x=\"231.298828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\" x=\"294.921875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2c\" x=\"358.544922\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"390.332031\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"422.119141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"463.232422\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\" x=\"547.021484\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_14\">\n",
|
||
" <g id=\"patch_15\">\n",
|
||
" <path d=\"M 3.24 55.90624 \n",
|
||
"L 66.117656 55.90624 \n",
|
||
"L 66.117656 39.275927 \n",
|
||
"L 3.24 39.275927 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #bf00bf\"/>\n",
|
||
" </g>\n",
|
||
" <!-- s=0.75, r=2 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(7.2 50.074521)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"52.099609\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"135.888672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"199.511719\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-37\" x=\"231.298828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\" x=\"294.921875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2c\" x=\"358.544922\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"390.332031\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"422.119141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"463.232422\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\" x=\"547.021484\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_15\">\n",
|
||
" <g id=\"patch_16\">\n",
|
||
" <path d=\"M 34.982647 19.870312 \n",
|
||
"L 106.446866 19.870312 \n",
|
||
"L 106.446866 3.24 \n",
|
||
"L 34.982647 3.24 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #00bfbf\"/>\n",
|
||
" </g>\n",
|
||
" <!-- s=0.75, r=0.5 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(38.942647 14.038594)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"52.099609\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"135.888672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"199.511719\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-37\" x=\"231.298828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\" x=\"294.921875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2c\" x=\"358.544922\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"390.332031\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"422.119141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"463.232422\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"547.021484\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"610.644531\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\" x=\"642.431641\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"pfd4dce92da\">\n",
|
||
" <rect x=\"45.946941\" y=\"22.82327\" width=\"176.35508\" height=\"135.9\"/>\n",
|
||
" </clipPath>\n",
|
||
" </defs>\n",
|
||
"</svg>\n"
|
||
],
|
||
"text/plain": [
|
||
"<Figure size 252x180 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"d2l.set_figsize()\n",
|
||
"bbox_scale = torch.tensor((w, h, w, h))\n",
|
||
"fig = d2l.plt.imshow(img)\n",
|
||
"show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,\n",
|
||
" ['s=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2',\n",
|
||
" 's=0.75, r=0.5'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "da87f940",
|
||
"metadata": {
|
||
"origin_pos": 19
|
||
},
|
||
"source": [
|
||
"## [**交并比（IoU）**]\n",
|
||
"\n",
|
||
"我们刚刚提到某个锚框“较好地”覆盖了图像中的狗。\n",
|
||
"如果已知目标的真实边界框，那么这里的“好”该如何如何量化呢？\n",
|
||
"直观地说，可以衡量锚框和真实边界框之间的相似性。\n",
|
||
"*杰卡德系数*（Jaccard）可以衡量两组之间的相似性。\n",
|
||
"给定集合$\\mathcal{A}$和$\\mathcal{B}$，他们的杰卡德系数是他们交集的大小除以他们并集的大小：\n",
|
||
"\n",
|
||
"$$J(\\mathcal{A},\\mathcal{B}) = \\frac{\\left|\\mathcal{A} \\cap \\mathcal{B}\\right|}{\\left| \\mathcal{A} \\cup \\mathcal{B}\\right|}.$$\n",
|
||
"\n",
|
||
"事实上，我们可以将任何边界框的像素区域视为一组像素。通\n",
|
||
"过这种方式，我们可以通过其像素集的杰卡德系数来测量两个边界框的相似性。\n",
|
||
"对于两个边界框，它们的杰卡德系数通常称为*交并比*（intersection over union，IoU），即两个边界框相交面积与相并面积之比，如 :numref:`fig_iou`所示。\n",
|
||
"交并比的取值范围在0和1之间：0表示两个边界框无重合像素，1表示两个边界框完全重合。\n",
|
||
"\n",
|
||
"\n",
|
||
":label:`fig_iou`\n",
|
||
"\n",
|
||
"接下来部分将使用交并比来衡量锚框和真实边界框之间、以及不同锚框之间的相似度。\n",
|
||
"给定两个锚框或边界框的列表，以下`box_iou`函数将在这两个列表中计算它们成对的交并比。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "feab924c",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.639984Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.639243Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.649165Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.648025Z"
|
||
},
|
||
"origin_pos": 21,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def box_iou(boxes1, boxes2):\n",
|
||
" \"\"\"计算两个锚框或边界框列表中成对的交并比\"\"\"\n",
|
||
" box_area = lambda boxes: ((boxes[:, 2] - boxes[:, 0]) *\n",
|
||
" (boxes[:, 3] - boxes[:, 1]))\n",
|
||
" # boxes1,boxes2,areas1,areas2的形状:\n",
|
||
" # boxes1：(boxes1的数量,4),\n",
|
||
" # boxes2：(boxes2的数量,4),\n",
|
||
" # areas1：(boxes1的数量,),\n",
|
||
" # areas2：(boxes2的数量,)\n",
|
||
" areas1 = box_area(boxes1)\n",
|
||
" areas2 = box_area(boxes2)\n",
|
||
" # inter_upperlefts,inter_lowerrights,inters的形状:\n",
|
||
" # (boxes1的数量,boxes2的数量,2)\n",
|
||
" inter_upperlefts = torch.max(boxes1[:, None, :2], boxes2[:, :2])\n",
|
||
" inter_lowerrights = torch.min(boxes1[:, None, 2:], boxes2[:, 2:])\n",
|
||
" inters = (inter_lowerrights - inter_upperlefts).clamp(min=0)\n",
|
||
" # inter_areasandunion_areas的形状:(boxes1的数量,boxes2的数量)\n",
|
||
" inter_areas = inters[:, :, 0] * inters[:, :, 1]\n",
|
||
" union_areas = areas1[:, None] + areas2 - inter_areas\n",
|
||
" return inter_areas / union_areas"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "aa0f6d1e",
|
||
"metadata": {
|
||
"origin_pos": 23
|
||
},
|
||
"source": [
|
||
"## 在训练数据中标注锚框\n",
|
||
":label:`subsec_labeling-anchor-boxes`\n",
|
||
"\n",
|
||
"在训练集中，我们将每个锚框视为一个训练样本。\n",
|
||
"为了训练目标检测模型，我们需要每个锚框的*类别*（class）和*偏移量*（offset）标签，其中前者是与锚框相关的对象的类别，后者是真实边界框相对于锚框的偏移量。\n",
|
||
"在预测时，我们为每个图像生成多个锚框，预测所有锚框的类别和偏移量，根据预测的偏移量调整它们的位置以获得预测的边界框，最后只输出符合特定条件的预测边界框。\n",
|
||
"\n",
|
||
"目标检测训练集带有*真实边界框*的位置及其包围物体类别的标签。\n",
|
||
"要标记任何生成的锚框，我们可以参考分配到的最接近此锚框的真实边界框的位置和类别标签。\n",
|
||
"下文将介绍一个算法，它能够把最接近的真实边界框分配给锚框。\n",
|
||
"\n",
|
||
"### [**将真实边界框分配给锚框**]\n",
|
||
"\n",
|
||
"给定图像，假设锚框是$A_1, A_2, \\ldots, A_{n_a}$，真实边界框是$B_1, B_2, \\ldots, B_{n_b}$，其中$n_a \\geq n_b$。\n",
|
||
"让我们定义一个矩阵$\\mathbf{X} \\in \\mathbb{R}^{n_a \\times n_b}$，其中第$i$行、第$j$列的元素$x_{ij}$是锚框$A_i$和真实边界框$B_j$的IoU。\n",
|
||
"该算法包含以下步骤。\n",
|
||
"\n",
|
||
"1. 在矩阵$\\mathbf{X}$中找到最大的元素，并将它的行索引和列索引分别表示为$i_1$和$j_1$。然后将真实边界框$B_{j_1}$分配给锚框$A_{i_1}$。这很直观，因为$A_{i_1}$和$B_{j_1}$是所有锚框和真实边界框配对中最相近的。在第一个分配完成后，丢弃矩阵中${i_1}^\\mathrm{th}$行和${j_1}^\\mathrm{th}$列中的所有元素。\n",
|
||
"1. 在矩阵$\\mathbf{X}$中找到剩余元素中最大的元素，并将它的行索引和列索引分别表示为$i_2$和$j_2$。我们将真实边界框$B_{j_2}$分配给锚框$A_{i_2}$，并丢弃矩阵中${i_2}^\\mathrm{th}$行和${j_2}^\\mathrm{th}$列中的所有元素。\n",
|
||
"1. 此时，矩阵$\\mathbf{X}$中两行和两列中的元素已被丢弃。我们继续，直到丢弃掉矩阵$\\mathbf{X}$中$n_b$列中的所有元素。此时已经为这$n_b$个锚框各自分配了一个真实边界框。\n",
|
||
"1. 只遍历剩下的$n_a - n_b$个锚框。例如，给定任何锚框$A_i$，在矩阵$\\mathbf{X}$的第$i^\\mathrm{th}$行中找到与$A_i$的IoU最大的真实边界框$B_j$，只有当此IoU大于预定义的阈值时，才将$B_j$分配给$A_i$。\n",
|
||
"\n",
|
||
"下面用一个具体的例子来说明上述算法。\n",
|
||
"如 :numref:`fig_anchor_label`（左）所示，假设矩阵$\\mathbf{X}$中的最大值为$x_{23}$，我们将真实边界框$B_3$分配给锚框$A_2$。\n",
|
||
"然后，我们丢弃矩阵第2行和第3列中的所有元素，在剩余元素（阴影区域）中找到最大的$x_{71}$，然后将真实边界框$B_1$分配给锚框$A_7$。\n",
|
||
"接下来，如 :numref:`fig_anchor_label`（中）所示，丢弃矩阵第7行和第1列中的所有元素，在剩余元素（阴影区域）中找到最大的$x_{54}$，然后将真实边界框$B_4$分配给锚框$A_5$。\n",
|
||
"最后，如 :numref:`fig_anchor_label`（右）所示，丢弃矩阵第5行和第4列中的所有元素，在剩余元素（阴影区域）中找到最大的$x_{92}$，然后将真实边界框$B_2$分配给锚框$A_9$。\n",
|
||
"之后，我们只需要遍历剩余的锚框$A_1, A_3, A_4, A_6, A_8$，然后根据阈值确定是否为它们分配真实边界框。\n",
|
||
"\n",
|
||
"\n",
|
||
":label:`fig_anchor_label`\n",
|
||
"\n",
|
||
"此算法在下面的`assign_anchor_to_bbox`函数中实现。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "8ac4113a",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.654100Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.653303Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.664045Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.663020Z"
|
||
},
|
||
"origin_pos": 25,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def assign_anchor_to_bbox(ground_truth, anchors, device, iou_threshold=0.5):\n",
|
||
" \"\"\"将最接近的真实边界框分配给锚框\"\"\"\n",
|
||
" num_anchors, num_gt_boxes = anchors.shape[0], ground_truth.shape[0]\n",
|
||
" # 位于第i行和第j列的元素x_ij是锚框i和真实边界框j的IoU\n",
|
||
" jaccard = box_iou(anchors, ground_truth)\n",
|
||
" # 对于每个锚框，分配的真实边界框的张量\n",
|
||
" anchors_bbox_map = torch.full((num_anchors,), -1, dtype=torch.long,\n",
|
||
" device=device)\n",
|
||
" # 根据阈值，决定是否分配真实边界框\n",
|
||
" max_ious, indices = torch.max(jaccard, dim=1)\n",
|
||
" anc_i = torch.nonzero(max_ious >= iou_threshold).reshape(-1)\n",
|
||
" box_j = indices[max_ious >= iou_threshold]\n",
|
||
" anchors_bbox_map[anc_i] = box_j\n",
|
||
" col_discard = torch.full((num_anchors,), -1)\n",
|
||
" row_discard = torch.full((num_gt_boxes,), -1)\n",
|
||
" for _ in range(num_gt_boxes):\n",
|
||
" max_idx = torch.argmax(jaccard)\n",
|
||
" box_idx = (max_idx % num_gt_boxes).long()\n",
|
||
" anc_idx = (max_idx / num_gt_boxes).long()\n",
|
||
" anchors_bbox_map[anc_idx] = box_idx\n",
|
||
" jaccard[:, box_idx] = col_discard\n",
|
||
" jaccard[anc_idx, :] = row_discard\n",
|
||
" return anchors_bbox_map"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "f57512db",
|
||
"metadata": {
|
||
"origin_pos": 27
|
||
},
|
||
"source": [
|
||
"### 标记类别和偏移量\n",
|
||
"\n",
|
||
"现在我们可以为每个锚框标记类别和偏移量了。\n",
|
||
"假设一个锚框$A$被分配了一个真实边界框$B$。\n",
|
||
"一方面，锚框$A$的类别将被标记为与$B$相同。\n",
|
||
"另一方面，锚框$A$的偏移量将根据$B$和$A$中心坐标的相对位置以及这两个框的相对大小进行标记。\n",
|
||
"鉴于数据集内不同的框的位置和大小不同，我们可以对那些相对位置和大小应用变换，使其获得分布更均匀且易于拟合的偏移量。\n",
|
||
"这里介绍一种常见的变换。\n",
|
||
"[**给定框$A$和$B$，中心坐标分别为$(x_a, y_a)$和$(x_b, y_b)$，宽度分别为$w_a$和$w_b$，高度分别为$h_a$和$h_b$，可以将$A$的偏移量标记为：\n",
|
||
"\n",
|
||
"$$\\left( \\frac{ \\frac{x_b - x_a}{w_a} - \\mu_x }{\\sigma_x},\n",
|
||
"\\frac{ \\frac{y_b - y_a}{h_a} - \\mu_y }{\\sigma_y},\n",
|
||
"\\frac{ \\log \\frac{w_b}{w_a} - \\mu_w }{\\sigma_w},\n",
|
||
"\\frac{ \\log \\frac{h_b}{h_a} - \\mu_h }{\\sigma_h}\\right),$$\n",
|
||
"**]\n",
|
||
"其中常量的默认值为 $\\mu_x = \\mu_y = \\mu_w = \\mu_h = 0, \\sigma_x=\\sigma_y=0.1$ ， $\\sigma_w=\\sigma_h=0.2$。\n",
|
||
"这种转换在下面的 `offset_boxes` 函数中实现。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "a5b6bbdc",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.668909Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.668107Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.675569Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.674509Z"
|
||
},
|
||
"origin_pos": 28,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def offset_boxes(anchors, assigned_bb, eps=1e-6):\n",
|
||
" \"\"\"对锚框偏移量的转换\"\"\"\n",
|
||
" c_anc = d2l.box_corner_to_center(anchors)\n",
|
||
" c_assigned_bb = d2l.box_corner_to_center(assigned_bb)\n",
|
||
" offset_xy = 10 * (c_assigned_bb[:, :2] - c_anc[:, :2]) / c_anc[:, 2:]\n",
|
||
" offset_wh = 5 * torch.log(eps + c_assigned_bb[:, 2:] / c_anc[:, 2:])\n",
|
||
" offset = torch.cat([offset_xy, offset_wh], axis=1)\n",
|
||
" return offset"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1e309f7d",
|
||
"metadata": {
|
||
"origin_pos": 29
|
||
},
|
||
"source": [
|
||
"如果一个锚框没有被分配真实边界框，我们只需将锚框的类别标记为*背景*（background）。\n",
|
||
"背景类别的锚框通常被称为*负类*锚框，其余的被称为*正类*锚框。\n",
|
||
"我们使用真实边界框（`labels`参数）实现以下`multibox_target`函数，来[**标记锚框的类别和偏移量**]（`anchors`参数）。\n",
|
||
"此函数将背景类别的索引设置为零，然后将新类别的整数索引递增一。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "291738a2",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.680339Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.679651Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:45.692690Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:45.691647Z"
|
||
},
|
||
"origin_pos": 31,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def multibox_target(anchors, labels):\n",
|
||
" \"\"\"使用真实边界框标记锚框\"\"\"\n",
|
||
" batch_size, anchors = labels.shape[0], anchors.squeeze(0)\n",
|
||
" batch_offset, batch_mask, batch_class_labels = [], [], []\n",
|
||
" device, num_anchors = anchors.device, anchors.shape[0]\n",
|
||
" for i in range(batch_size):\n",
|
||
" label = labels[i, :, :]\n",
|
||
" anchors_bbox_map = assign_anchor_to_bbox(\n",
|
||
" label[:, 1:], anchors, device)\n",
|
||
" bbox_mask = ((anchors_bbox_map >= 0).float().unsqueeze(-1)).repeat(\n",
|
||
" 1, 4)\n",
|
||
" # 将类标签和分配的边界框坐标初始化为零\n",
|
||
" class_labels = torch.zeros(num_anchors, dtype=torch.long,\n",
|
||
" device=device)\n",
|
||
" assigned_bb = torch.zeros((num_anchors, 4), dtype=torch.float32,\n",
|
||
" device=device)\n",
|
||
" # 使用真实边界框来标记锚框的类别。\n",
|
||
" # 如果一个锚框没有被分配，标记其为背景（值为零）\n",
|
||
" indices_true = torch.nonzero(anchors_bbox_map >= 0)\n",
|
||
" bb_idx = anchors_bbox_map[indices_true]\n",
|
||
" class_labels[indices_true] = label[bb_idx, 0].long() + 1\n",
|
||
" assigned_bb[indices_true] = label[bb_idx, 1:]\n",
|
||
" # 偏移量转换\n",
|
||
" offset = offset_boxes(anchors, assigned_bb) * bbox_mask\n",
|
||
" batch_offset.append(offset.reshape(-1))\n",
|
||
" batch_mask.append(bbox_mask.reshape(-1))\n",
|
||
" batch_class_labels.append(class_labels)\n",
|
||
" bbox_offset = torch.stack(batch_offset)\n",
|
||
" bbox_mask = torch.stack(batch_mask)\n",
|
||
" class_labels = torch.stack(batch_class_labels)\n",
|
||
" return (bbox_offset, bbox_mask, class_labels)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a78ead98",
|
||
"metadata": {
|
||
"origin_pos": 33
|
||
},
|
||
"source": [
|
||
"### 一个例子\n",
|
||
"\n",
|
||
"下面通过一个具体的例子来说明锚框标签。\n",
|
||
"我们已经为加载图像中的狗和猫定义了真实边界框，其中第一个元素是类别（0代表狗，1代表猫），其余四个元素是左上角和右下角的$(x, y)$轴坐标（范围介于0和1之间）。\n",
|
||
"我们还构建了五个锚框，用左上角和右下角的坐标进行标记：$A_0, \\ldots, A_4$（索引从0开始）。\n",
|
||
"然后我们[**在图像中绘制这些真实边界框和锚框**]。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "e22f46a6",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:45.697286Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:45.696846Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.054321Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.053210Z"
|
||
},
|
||
"origin_pos": 34,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/svg+xml": [
|
||
"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n",
|
||
"<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
|
||
" \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
|
||
"<svg xmlns:xlink=\"http://www.w3.org/1999/xlink\" width=\"216.84258pt\" height=\"170.656221pt\" viewBox=\"0 0 216.84258 170.656221\" xmlns=\"http://www.w3.org/2000/svg\" version=\"1.1\">\n",
|
||
" <metadata>\n",
|
||
" <rdf:RDF xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n",
|
||
" <cc:Work>\n",
|
||
" <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n",
|
||
" <dc:date>2023-08-18T07:00:45.953248</dc:date>\n",
|
||
" <dc:format>image/svg+xml</dc:format>\n",
|
||
" <dc:creator>\n",
|
||
" <cc:Agent>\n",
|
||
" <dc:title>Matplotlib v3.5.1, https://matplotlib.org/</dc:title>\n",
|
||
" </cc:Agent>\n",
|
||
" </dc:creator>\n",
|
||
" </cc:Work>\n",
|
||
" </rdf:RDF>\n",
|
||
" </metadata>\n",
|
||
" <defs>\n",
|
||
" <style type=\"text/css\">*{stroke-linejoin: round; stroke-linecap: butt}</style>\n",
|
||
" </defs>\n",
|
||
" <g id=\"figure_1\">\n",
|
||
" <g id=\"patch_1\">\n",
|
||
" <path d=\"M 0 170.656221 \n",
|
||
"L 216.84258 170.656221 \n",
|
||
"L 216.84258 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 170.656221 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 209.64258 146.778096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"L 33.2875 10.878096 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g clip-path=\"url(#pfdc233e7f8)\">\n",
|
||
" <image xlink:href=\"data:image/png;base64,\n",
|
||
"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\" id=\"imaged1729ac5fb\" transform=\"scale(1 -1)translate(0 -136)\" x=\"33.2875\" y=\"-10.778096\" width=\"177\" height=\"136\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 51.044132 21.871218 \n",
|
||
"L 125.113264 21.871218 \n",
|
||
"L 125.113264 136.027218 \n",
|
||
"L 51.044132 136.027218 \n",
|
||
"L 51.044132 21.871218 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #000000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 130.403916 38.17922 \n",
|
||
"L 192.128198 38.17922 \n",
|
||
"L 192.128198 130.591217 \n",
|
||
"L 130.403916 130.591217 \n",
|
||
"L 130.403916 38.17922 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #000000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 33.408623 24.589219 \n",
|
||
"L 68.679641 24.589219 \n",
|
||
"L 68.679641 51.769219 \n",
|
||
"L 33.408623 51.769219 \n",
|
||
"L 33.408623 24.589219 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #0000ff; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_6\">\n",
|
||
" <path d=\"M 59.861886 38.17922 \n",
|
||
"L 103.950658 38.17922 \n",
|
||
"L 103.950658 65.359221 \n",
|
||
"L 59.861886 65.359221 \n",
|
||
"L 59.861886 38.17922 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #008000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 144.51232 17.794219 \n",
|
||
"L 188.601097 17.794219 \n",
|
||
"L 188.601097 144.181226 \n",
|
||
"L 144.51232 144.181226 \n",
|
||
"L 144.51232 17.794219 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #ff0000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_8\">\n",
|
||
" <path d=\"M 149.802979 72.154218 \n",
|
||
"L 174.492693 72.154218 \n",
|
||
"L 174.492693 119.719223 \n",
|
||
"L 149.802979 119.719223 \n",
|
||
"L 149.802979 72.154218 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #bf00bf; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_9\">\n",
|
||
" <path d=\"M 133.931017 51.769219 \n",
|
||
"L 195.655299 51.769219 \n",
|
||
"L 195.655299 133.30921 \n",
|
||
"L 133.931017 133.30921 \n",
|
||
"L 133.931017 51.769219 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pfdc233e7f8)\" style=\"fill: none; stroke: #00bfbf; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"me324064f0e\" d=\"M 0 0 \n",
|
||
"L 0 3.5 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me324064f0e\" x=\"33.408623\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(30.227373 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-30\" d=\"M 2034 4250 \n",
|
||
"Q 1547 4250 1301 3770 \n",
|
||
"Q 1056 3291 1056 2328 \n",
|
||
"Q 1056 1369 1301 889 \n",
|
||
"Q 1547 409 2034 409 \n",
|
||
"Q 2525 409 2770 889 \n",
|
||
"Q 3016 1369 3016 2328 \n",
|
||
"Q 3016 3291 2770 3770 \n",
|
||
"Q 2525 4250 2034 4250 \n",
|
||
"z\n",
|
||
"M 2034 4750 \n",
|
||
"Q 2819 4750 3233 4129 \n",
|
||
"Q 3647 3509 3647 2328 \n",
|
||
"Q 3647 1150 3233 529 \n",
|
||
"Q 2819 -91 2034 -91 \n",
|
||
"Q 1250 -91 836 529 \n",
|
||
"Q 422 1150 422 2328 \n",
|
||
"Q 422 3509 836 4129 \n",
|
||
"Q 1250 4750 2034 4750 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me324064f0e\" x=\"81.857821\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(72.314071 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-32\" d=\"M 1228 531 \n",
|
||
"L 3431 531 \n",
|
||
"L 3431 0 \n",
|
||
"L 469 0 \n",
|
||
"L 469 531 \n",
|
||
"Q 828 903 1448 1529 \n",
|
||
"Q 2069 2156 2228 2338 \n",
|
||
"Q 2531 2678 2651 2914 \n",
|
||
"Q 2772 3150 2772 3378 \n",
|
||
"Q 2772 3750 2511 3984 \n",
|
||
"Q 2250 4219 1831 4219 \n",
|
||
"Q 1534 4219 1204 4116 \n",
|
||
"Q 875 4013 500 3803 \n",
|
||
"L 500 4441 \n",
|
||
"Q 881 4594 1212 4672 \n",
|
||
"Q 1544 4750 1819 4750 \n",
|
||
"Q 2544 4750 2975 4387 \n",
|
||
"Q 3406 4025 3406 3419 \n",
|
||
"Q 3406 3131 3298 2873 \n",
|
||
"Q 3191 2616 2906 2266 \n",
|
||
"Q 2828 2175 2409 1742 \n",
|
||
"Q 1991 1309 1228 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me324064f0e\" x=\"130.307019\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(120.763269 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-34\" d=\"M 2419 4116 \n",
|
||
"L 825 1625 \n",
|
||
"L 2419 1625 \n",
|
||
"L 2419 4116 \n",
|
||
"z\n",
|
||
"M 2253 4666 \n",
|
||
"L 3047 4666 \n",
|
||
"L 3047 1625 \n",
|
||
"L 3713 1625 \n",
|
||
"L 3713 1100 \n",
|
||
"L 3047 1100 \n",
|
||
"L 3047 0 \n",
|
||
"L 2419 0 \n",
|
||
"L 2419 1100 \n",
|
||
"L 313 1100 \n",
|
||
"L 313 1709 \n",
|
||
"L 2253 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#me324064f0e\" x=\"178.756217\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 600 -->\n",
|
||
" <g transform=\"translate(169.212467 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-36\" d=\"M 2113 2584 \n",
|
||
"Q 1688 2584 1439 2293 \n",
|
||
"Q 1191 2003 1191 1497 \n",
|
||
"Q 1191 994 1439 701 \n",
|
||
"Q 1688 409 2113 409 \n",
|
||
"Q 2538 409 2786 701 \n",
|
||
"Q 3034 994 3034 1497 \n",
|
||
"Q 3034 2003 2786 2293 \n",
|
||
"Q 2538 2584 2113 2584 \n",
|
||
"z\n",
|
||
"M 3366 4563 \n",
|
||
"L 3366 3988 \n",
|
||
"Q 3128 4100 2886 4159 \n",
|
||
"Q 2644 4219 2406 4219 \n",
|
||
"Q 1781 4219 1451 3797 \n",
|
||
"Q 1122 3375 1075 2522 \n",
|
||
"Q 1259 2794 1537 2939 \n",
|
||
"Q 1816 3084 2150 3084 \n",
|
||
"Q 2853 3084 3261 2657 \n",
|
||
"Q 3669 2231 3669 1497 \n",
|
||
"Q 3669 778 3244 343 \n",
|
||
"Q 2819 -91 2113 -91 \n",
|
||
"Q 1303 -91 875 529 \n",
|
||
"Q 447 1150 447 2328 \n",
|
||
"Q 447 3434 972 4092 \n",
|
||
"Q 1497 4750 2381 4750 \n",
|
||
"Q 2619 4750 2861 4703 \n",
|
||
"Q 3103 4656 3366 4563 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-36\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m42a919a6a1\" d=\"M 0 0 \n",
|
||
"L -3.5 0 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m42a919a6a1\" x=\"33.2875\" y=\"10.999219\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(19.925 14.798437)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m42a919a6a1\" x=\"33.2875\" y=\"35.223818\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- 100 -->\n",
|
||
" <g transform=\"translate(7.2 39.023036)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-31\" d=\"M 794 531 \n",
|
||
"L 1825 531 \n",
|
||
"L 1825 4091 \n",
|
||
"L 703 3866 \n",
|
||
"L 703 4441 \n",
|
||
"L 1819 4666 \n",
|
||
"L 2450 4666 \n",
|
||
"L 2450 531 \n",
|
||
"L 3481 531 \n",
|
||
"L 3481 0 \n",
|
||
"L 794 0 \n",
|
||
"L 794 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m42a919a6a1\" x=\"33.2875\" y=\"59.448417\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(7.2 63.247635)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m42a919a6a1\" x=\"33.2875\" y=\"83.673016\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 300 -->\n",
|
||
" <g transform=\"translate(7.2 87.472234)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-33\" d=\"M 2597 2516 \n",
|
||
"Q 3050 2419 3304 2112 \n",
|
||
"Q 3559 1806 3559 1356 \n",
|
||
"Q 3559 666 3084 287 \n",
|
||
"Q 2609 -91 1734 -91 \n",
|
||
"Q 1441 -91 1130 -33 \n",
|
||
"Q 819 25 488 141 \n",
|
||
"L 488 750 \n",
|
||
"Q 750 597 1062 519 \n",
|
||
"Q 1375 441 1716 441 \n",
|
||
"Q 2309 441 2620 675 \n",
|
||
"Q 2931 909 2931 1356 \n",
|
||
"Q 2931 1769 2642 2001 \n",
|
||
"Q 2353 2234 1838 2234 \n",
|
||
"L 1294 2234 \n",
|
||
"L 1294 2753 \n",
|
||
"L 1863 2753 \n",
|
||
"Q 2328 2753 2575 2939 \n",
|
||
"Q 2822 3125 2822 3475 \n",
|
||
"Q 2822 3834 2567 4026 \n",
|
||
"Q 2313 4219 1838 4219 \n",
|
||
"Q 1578 4219 1281 4162 \n",
|
||
"Q 984 4106 628 3988 \n",
|
||
"L 628 4550 \n",
|
||
"Q 988 4650 1302 4700 \n",
|
||
"Q 1616 4750 1894 4750 \n",
|
||
"Q 2613 4750 3031 4423 \n",
|
||
"Q 3450 4097 3450 3541 \n",
|
||
"Q 3450 3153 3228 2886 \n",
|
||
"Q 3006 2619 2597 2516 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-33\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m42a919a6a1\" x=\"33.2875\" y=\"107.897614\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(7.2 111.696833)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_6\">\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m42a919a6a1\" x=\"33.2875\" y=\"132.122213\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 500 -->\n",
|
||
" <g transform=\"translate(7.2 135.921432)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-35\" d=\"M 691 4666 \n",
|
||
"L 3169 4666 \n",
|
||
"L 3169 4134 \n",
|
||
"L 1269 4134 \n",
|
||
"L 1269 2991 \n",
|
||
"Q 1406 3038 1543 3061 \n",
|
||
"Q 1681 3084 1819 3084 \n",
|
||
"Q 2600 3084 3056 2656 \n",
|
||
"Q 3513 2228 3513 1497 \n",
|
||
"Q 3513 744 3044 326 \n",
|
||
"Q 2575 -91 1722 -91 \n",
|
||
"Q 1428 -91 1123 -41 \n",
|
||
"Q 819 9 494 109 \n",
|
||
"L 494 744 \n",
|
||
"Q 775 591 1075 516 \n",
|
||
"Q 1375 441 1709 441 \n",
|
||
"Q 2250 441 2565 725 \n",
|
||
"Q 2881 1009 2881 1497 \n",
|
||
"Q 2881 1984 2565 2268 \n",
|
||
"Q 2250 2553 1709 2553 \n",
|
||
"Q 1456 2553 1204 2497 \n",
|
||
"Q 953 2441 691 2322 \n",
|
||
"L 691 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_10\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 33.2875 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_11\">\n",
|
||
" <path d=\"M 209.64258 146.778096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_12\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 209.64258 146.778096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_13\">\n",
|
||
" <path d=\"M 33.2875 10.878096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <g id=\"patch_14\">\n",
|
||
" <path d=\"M 38.617101 30.186374 \n",
|
||
"L 63.471163 30.186374 \n",
|
||
"L 63.471163 13.556062 \n",
|
||
"L 38.617101 13.556062 \n",
|
||
"z\n",
|
||
"\"/>\n",
|
||
" </g>\n",
|
||
" <!-- dog -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(42.577101 24.354656)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-64\" d=\"M 2906 2969 \n",
|
||
"L 2906 4863 \n",
|
||
"L 3481 4863 \n",
|
||
"L 3481 0 \n",
|
||
"L 2906 0 \n",
|
||
"L 2906 525 \n",
|
||
"Q 2725 213 2448 61 \n",
|
||
"Q 2172 -91 1784 -91 \n",
|
||
"Q 1150 -91 751 415 \n",
|
||
"Q 353 922 353 1747 \n",
|
||
"Q 353 2572 751 3078 \n",
|
||
"Q 1150 3584 1784 3584 \n",
|
||
"Q 2172 3584 2448 3432 \n",
|
||
"Q 2725 3281 2906 2969 \n",
|
||
"z\n",
|
||
"M 947 1747 \n",
|
||
"Q 947 1113 1208 752 \n",
|
||
"Q 1469 391 1925 391 \n",
|
||
"Q 2381 391 2643 752 \n",
|
||
"Q 2906 1113 2906 1747 \n",
|
||
"Q 2906 2381 2643 2742 \n",
|
||
"Q 2381 3103 1925 3103 \n",
|
||
"Q 1469 3103 1208 2742 \n",
|
||
"Q 947 2381 947 1747 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6f\" d=\"M 1959 3097 \n",
|
||
"Q 1497 3097 1228 2736 \n",
|
||
"Q 959 2375 959 1747 \n",
|
||
"Q 959 1119 1226 758 \n",
|
||
"Q 1494 397 1959 397 \n",
|
||
"Q 2419 397 2687 759 \n",
|
||
"Q 2956 1122 2956 1747 \n",
|
||
"Q 2956 2369 2687 2733 \n",
|
||
"Q 2419 3097 1959 3097 \n",
|
||
"z\n",
|
||
"M 1959 3584 \n",
|
||
"Q 2709 3584 3137 3096 \n",
|
||
"Q 3566 2609 3566 1747 \n",
|
||
"Q 3566 888 3137 398 \n",
|
||
"Q 2709 -91 1959 -91 \n",
|
||
"Q 1206 -91 779 398 \n",
|
||
"Q 353 888 353 1747 \n",
|
||
"Q 353 2609 779 3096 \n",
|
||
"Q 1206 3584 1959 3584 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-67\" d=\"M 2906 1791 \n",
|
||
"Q 2906 2416 2648 2759 \n",
|
||
"Q 2391 3103 1925 3103 \n",
|
||
"Q 1463 3103 1205 2759 \n",
|
||
"Q 947 2416 947 1791 \n",
|
||
"Q 947 1169 1205 825 \n",
|
||
"Q 1463 481 1925 481 \n",
|
||
"Q 2391 481 2648 825 \n",
|
||
"Q 2906 1169 2906 1791 \n",
|
||
"z\n",
|
||
"M 3481 434 \n",
|
||
"Q 3481 -459 3084 -895 \n",
|
||
"Q 2688 -1331 1869 -1331 \n",
|
||
"Q 1566 -1331 1297 -1286 \n",
|
||
"Q 1028 -1241 775 -1147 \n",
|
||
"L 775 -588 \n",
|
||
"Q 1028 -725 1275 -790 \n",
|
||
"Q 1522 -856 1778 -856 \n",
|
||
"Q 2344 -856 2625 -561 \n",
|
||
"Q 2906 -266 2906 331 \n",
|
||
"L 2906 616 \n",
|
||
"Q 2728 306 2450 153 \n",
|
||
"Q 2172 0 1784 0 \n",
|
||
"Q 1141 0 747 490 \n",
|
||
"Q 353 981 353 1791 \n",
|
||
"Q 353 2603 747 3093 \n",
|
||
"Q 1141 3584 1784 3584 \n",
|
||
"Q 2172 3584 2450 3431 \n",
|
||
"Q 2728 3278 2906 2969 \n",
|
||
"L 2906 3500 \n",
|
||
"L 3481 3500 \n",
|
||
"L 3481 434 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-64\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"63.476562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-67\" x=\"124.658203\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <g id=\"patch_15\">\n",
|
||
" <path d=\"M 119.447822 46.494376 \n",
|
||
"L 141.360009 46.494376 \n",
|
||
"L 141.360009 29.864064 \n",
|
||
"L 119.447822 29.864064 \n",
|
||
"z\n",
|
||
"\"/>\n",
|
||
" </g>\n",
|
||
" <!-- cat -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(123.407822 40.662657)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-63\" d=\"M 3122 3366 \n",
|
||
"L 3122 2828 \n",
|
||
"Q 2878 2963 2633 3030 \n",
|
||
"Q 2388 3097 2138 3097 \n",
|
||
"Q 1578 3097 1268 2742 \n",
|
||
"Q 959 2388 959 1747 \n",
|
||
"Q 959 1106 1268 751 \n",
|
||
"Q 1578 397 2138 397 \n",
|
||
"Q 2388 397 2633 464 \n",
|
||
"Q 2878 531 3122 666 \n",
|
||
"L 3122 134 \n",
|
||
"Q 2881 22 2623 -34 \n",
|
||
"Q 2366 -91 2075 -91 \n",
|
||
"Q 1284 -91 818 406 \n",
|
||
"Q 353 903 353 1747 \n",
|
||
"Q 353 2603 823 3093 \n",
|
||
"Q 1294 3584 2113 3584 \n",
|
||
"Q 2378 3584 2631 3529 \n",
|
||
"Q 2884 3475 3122 3366 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-61\" d=\"M 2194 1759 \n",
|
||
"Q 1497 1759 1228 1600 \n",
|
||
"Q 959 1441 959 1056 \n",
|
||
"Q 959 750 1161 570 \n",
|
||
"Q 1363 391 1709 391 \n",
|
||
"Q 2188 391 2477 730 \n",
|
||
"Q 2766 1069 2766 1631 \n",
|
||
"L 2766 1759 \n",
|
||
"L 2194 1759 \n",
|
||
"z\n",
|
||
"M 3341 1997 \n",
|
||
"L 3341 0 \n",
|
||
"L 2766 0 \n",
|
||
"L 2766 531 \n",
|
||
"Q 2569 213 2275 61 \n",
|
||
"Q 1981 -91 1556 -91 \n",
|
||
"Q 1019 -91 701 211 \n",
|
||
"Q 384 513 384 1019 \n",
|
||
"Q 384 1609 779 1909 \n",
|
||
"Q 1175 2209 1959 2209 \n",
|
||
"L 2766 2209 \n",
|
||
"L 2766 2266 \n",
|
||
"Q 2766 2663 2505 2880 \n",
|
||
"Q 2244 3097 1772 3097 \n",
|
||
"Q 1472 3097 1187 3025 \n",
|
||
"Q 903 2953 641 2809 \n",
|
||
"L 641 3341 \n",
|
||
"Q 956 3463 1253 3523 \n",
|
||
"Q 1550 3584 1831 3584 \n",
|
||
"Q 2591 3584 2966 3190 \n",
|
||
"Q 3341 2797 3341 1997 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-74\" d=\"M 1172 4494 \n",
|
||
"L 1172 3500 \n",
|
||
"L 2356 3500 \n",
|
||
"L 2356 3053 \n",
|
||
"L 1172 3053 \n",
|
||
"L 1172 1153 \n",
|
||
"Q 1172 725 1289 603 \n",
|
||
"Q 1406 481 1766 481 \n",
|
||
"L 2356 481 \n",
|
||
"L 2356 0 \n",
|
||
"L 1766 0 \n",
|
||
"Q 1100 0 847 248 \n",
|
||
"Q 594 497 594 1153 \n",
|
||
"L 594 3053 \n",
|
||
"L 172 3053 \n",
|
||
"L 172 3500 \n",
|
||
"L 594 3500 \n",
|
||
"L 594 4494 \n",
|
||
"L 1172 4494 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"54.980469\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\" x=\"116.259766\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_13\">\n",
|
||
" <g id=\"patch_16\">\n",
|
||
" <path d=\"M 26.585498 32.904376 \n",
|
||
"L 40.231748 32.904376 \n",
|
||
"L 40.231748 16.274063 \n",
|
||
"L 26.585498 16.274063 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #0000ff\"/>\n",
|
||
" </g>\n",
|
||
" <!-- 0 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(30.545498 27.072657)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_14\">\n",
|
||
" <g id=\"patch_17\">\n",
|
||
" <path d=\"M 53.038761 46.494376 \n",
|
||
"L 66.685011 46.494376 \n",
|
||
"L 66.685011 29.864064 \n",
|
||
"L 53.038761 29.864064 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #008000\"/>\n",
|
||
" </g>\n",
|
||
" <!-- 1 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(56.998761 40.662657)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_15\">\n",
|
||
" <g id=\"patch_18\">\n",
|
||
" <path d=\"M 137.689195 26.109375 \n",
|
||
"L 151.335445 26.109375 \n",
|
||
"L 151.335445 9.479063 \n",
|
||
"L 137.689195 9.479063 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ff0000\"/>\n",
|
||
" </g>\n",
|
||
" <!-- 2 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(141.649195 20.277657)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_16\">\n",
|
||
" <g id=\"patch_19\">\n",
|
||
" <path d=\"M 142.979854 80.469374 \n",
|
||
"L 156.626104 80.469374 \n",
|
||
"L 156.626104 63.839062 \n",
|
||
"L 142.979854 63.839062 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #bf00bf\"/>\n",
|
||
" </g>\n",
|
||
" <!-- 3 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(146.939854 74.637656)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-33\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_17\">\n",
|
||
" <g id=\"patch_20\">\n",
|
||
" <path d=\"M 127.107892 60.084376 \n",
|
||
"L 140.754142 60.084376 \n",
|
||
"L 140.754142 43.454063 \n",
|
||
"L 127.107892 43.454063 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #00bfbf\"/>\n",
|
||
" </g>\n",
|
||
" <!-- 4 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(131.067892 54.252657)scale(0.09 -0.09)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"pfdc233e7f8\">\n",
|
||
" <rect x=\"33.2875\" y=\"10.878096\" width=\"176.35508\" height=\"135.9\"/>\n",
|
||
" </clipPath>\n",
|
||
" </defs>\n",
|
||
"</svg>\n"
|
||
],
|
||
"text/plain": [
|
||
"<Figure size 252x180 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"ground_truth = torch.tensor([[0, 0.1, 0.08, 0.52, 0.92],\n",
|
||
" [1, 0.55, 0.2, 0.9, 0.88]])\n",
|
||
"anchors = torch.tensor([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],\n",
|
||
" [0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],\n",
|
||
" [0.57, 0.3, 0.92, 0.9]])\n",
|
||
"\n",
|
||
"fig = d2l.plt.imshow(img)\n",
|
||
"show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')\n",
|
||
"show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4']);"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "414c8154",
|
||
"metadata": {
|
||
"origin_pos": 35
|
||
},
|
||
"source": [
|
||
"使用上面定义的`multibox_target`函数，我们可以[**根据狗和猫的真实边界框，标注这些锚框的分类和偏移量**]。\n",
|
||
"在这个例子中，背景、狗和猫的类索引分别为0、1和2。\n",
|
||
"下面我们为锚框和真实边界框样本添加一个维度。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"id": "511fc2cf",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.059898Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.059146Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.067556Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.066157Z"
|
||
},
|
||
"origin_pos": 37,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"labels = multibox_target(anchors.unsqueeze(dim=0),\n",
|
||
" ground_truth.unsqueeze(dim=0))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5c2b454d",
|
||
"metadata": {
|
||
"origin_pos": 39
|
||
},
|
||
"source": [
|
||
"返回的结果中有三个元素，都是张量格式。第三个元素包含标记的输入锚框的类别。\n",
|
||
"\n",
|
||
"让我们根据图像中的锚框和真实边界框的位置来分析下面返回的类别标签。\n",
|
||
"首先，在所有的锚框和真实边界框配对中，锚框$A_4$与猫的真实边界框的IoU是最大的。\n",
|
||
"因此，$A_4$的类别被标记为猫。\n",
|
||
"去除包含$A_4$或猫的真实边界框的配对，在剩下的配对中，锚框$A_1$和狗的真实边界框有最大的IoU。\n",
|
||
"因此，$A_1$的类别被标记为狗。\n",
|
||
"接下来，我们需要遍历剩下的三个未标记的锚框：$A_0$、$A_2$和$A_3$。\n",
|
||
"对于$A_0$，与其拥有最大IoU的真实边界框的类别是狗，但IoU低于预定义的阈值（0.5），因此该类别被标记为背景；\n",
|
||
"对于$A_2$，与其拥有最大IoU的真实边界框的类别是猫，IoU超过阈值，所以类别被标记为猫；\n",
|
||
"对于$A_3$，与其拥有最大IoU的真实边界框的类别是猫，但值低于阈值，因此该类别被标记为背景。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"id": "78a2e091",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.075902Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.075000Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.084256Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.083114Z"
|
||
},
|
||
"origin_pos": 40,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"tensor([[0, 1, 2, 0, 2]])"
|
||
]
|
||
},
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"labels[2]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "cffb366b",
|
||
"metadata": {
|
||
"origin_pos": 41
|
||
},
|
||
"source": [
|
||
"返回的第二个元素是掩码（mask）变量，形状为（批量大小，锚框数的四倍）。\n",
|
||
"掩码变量中的元素与每个锚框的4个偏移量一一对应。\n",
|
||
"由于我们不关心对背景的检测，负类的偏移量不应影响目标函数。\n",
|
||
"通过元素乘法，掩码变量中的零将在计算目标函数之前过滤掉负类偏移量。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"id": "94a1597f",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.097601Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.097228Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.104883Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.103744Z"
|
||
},
|
||
"origin_pos": 42,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"tensor([[0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 1., 1.,\n",
|
||
" 1., 1.]])"
|
||
]
|
||
},
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"labels[1]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1cfc7bb3",
|
||
"metadata": {
|
||
"origin_pos": 43
|
||
},
|
||
"source": [
|
||
"返回的第一个元素包含了为每个锚框标记的四个偏移值。\n",
|
||
"请注意，负类锚框的偏移量被标记为零。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"id": "25e7f69b",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.112301Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.111934Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.118802Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.117910Z"
|
||
},
|
||
"origin_pos": 44,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"tensor([[-0.00e+00, -0.00e+00, -0.00e+00, -0.00e+00, 1.40e+00, 1.00e+01,\n",
|
||
" 2.59e+00, 7.18e+00, -1.20e+00, 2.69e-01, 1.68e+00, -1.57e+00,\n",
|
||
" -0.00e+00, -0.00e+00, -0.00e+00, -0.00e+00, -5.71e-01, -1.00e+00,\n",
|
||
" 4.17e-06, 6.26e-01]])"
|
||
]
|
||
},
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"labels[0]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ada70fbf",
|
||
"metadata": {
|
||
"origin_pos": 45
|
||
},
|
||
"source": [
|
||
"## 使用非极大值抑制预测边界框\n",
|
||
":label:`subsec_predicting-bounding-boxes-nms`\n",
|
||
"\n",
|
||
"在预测时，我们先为图像生成多个锚框，再为这些锚框一一预测类别和偏移量。\n",
|
||
"一个*预测好的边界框*则根据其中某个带有预测偏移量的锚框而生成。\n",
|
||
"下面我们实现了`offset_inverse`函数，该函数将锚框和偏移量预测作为输入，并[**应用逆偏移变换来返回预测的边界框坐标**]。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"id": "227ae1a8",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.127370Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.127014Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.133873Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.132925Z"
|
||
},
|
||
"origin_pos": 46,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def offset_inverse(anchors, offset_preds):\n",
|
||
" \"\"\"根据带有预测偏移量的锚框来预测边界框\"\"\"\n",
|
||
" anc = d2l.box_corner_to_center(anchors)\n",
|
||
" pred_bbox_xy = (offset_preds[:, :2] * anc[:, 2:] / 10) + anc[:, :2]\n",
|
||
" pred_bbox_wh = torch.exp(offset_preds[:, 2:] / 5) * anc[:, 2:]\n",
|
||
" pred_bbox = torch.cat((pred_bbox_xy, pred_bbox_wh), axis=1)\n",
|
||
" predicted_bbox = d2l.box_center_to_corner(pred_bbox)\n",
|
||
" return predicted_bbox"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c8a5c307",
|
||
"metadata": {
|
||
"origin_pos": 47
|
||
},
|
||
"source": [
|
||
"当有许多锚框时，可能会输出许多相似的具有明显重叠的预测边界框，都围绕着同一目标。\n",
|
||
"为了简化输出，我们可以使用*非极大值抑制*（non-maximum suppression，NMS）合并属于同一目标的类似的预测边界框。\n",
|
||
"\n",
|
||
"以下是非极大值抑制的工作原理。\n",
|
||
"对于一个预测边界框$B$，目标检测模型会计算每个类别的预测概率。\n",
|
||
"假设最大的预测概率为$p$，则该概率所对应的类别$B$即为预测的类别。\n",
|
||
"具体来说，我们将$p$称为预测边界框$B$的*置信度*（confidence）。\n",
|
||
"在同一张图像中，所有预测的非背景边界框都按置信度降序排序，以生成列表$L$。然后我们通过以下步骤操作排序列表$L$。\n",
|
||
"\n",
|
||
"1. 从$L$中选取置信度最高的预测边界框$B_1$作为基准，然后将所有与$B_1$的IoU超过预定阈值$\\epsilon$的非基准预测边界框从$L$中移除。这时，$L$保留了置信度最高的预测边界框，去除了与其太过相似的其他预测边界框。简而言之，那些具有*非极大值*置信度的边界框被*抑制*了。\n",
|
||
"1. 从$L$中选取置信度第二高的预测边界框$B_2$作为又一个基准，然后将所有与$B_2$的IoU大于$\\epsilon$的非基准预测边界框从$L$中移除。\n",
|
||
"1. 重复上述过程，直到$L$中的所有预测边界框都曾被用作基准。此时，$L$中任意一对预测边界框的IoU都小于阈值$\\epsilon$；因此，没有一对边界框过于相似。\n",
|
||
"1. 输出列表$L$中的所有预测边界框。\n",
|
||
"\n",
|
||
"[**以下`nms`函数按降序对置信度进行排序并返回其索引**]。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 17,
|
||
"id": "ac5c4e3c",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.138652Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.138060Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.151360Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.150447Z"
|
||
},
|
||
"origin_pos": 49,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def nms(boxes, scores, iou_threshold):\n",
|
||
" \"\"\"对预测边界框的置信度进行排序\"\"\"\n",
|
||
" B = torch.argsort(scores, dim=-1, descending=True)\n",
|
||
" keep = [] # 保留预测边界框的指标\n",
|
||
" while B.numel() > 0:\n",
|
||
" i = B[0]\n",
|
||
" keep.append(i)\n",
|
||
" if B.numel() == 1: break\n",
|
||
" iou = box_iou(boxes[i, :].reshape(-1, 4),\n",
|
||
" boxes[B[1:], :].reshape(-1, 4)).reshape(-1)\n",
|
||
" inds = torch.nonzero(iou <= iou_threshold).reshape(-1)\n",
|
||
" B = B[inds + 1]\n",
|
||
" return torch.tensor(keep, device=boxes.device)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a21e7812",
|
||
"metadata": {
|
||
"origin_pos": 51
|
||
},
|
||
"source": [
|
||
"我们定义以下`multibox_detection`函数来[**将非极大值抑制应用于预测边界框**]。\n",
|
||
"这里的实现有点复杂，请不要担心。我们将在实现之后，马上用一个具体的例子来展示它是如何工作的。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 18,
|
||
"id": "baa9f34f",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.157117Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.156701Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.175104Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.174174Z"
|
||
},
|
||
"origin_pos": 53,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def multibox_detection(cls_probs, offset_preds, anchors, nms_threshold=0.5,\n",
|
||
" pos_threshold=0.009999999):\n",
|
||
" \"\"\"使用非极大值抑制来预测边界框\"\"\"\n",
|
||
" device, batch_size = cls_probs.device, cls_probs.shape[0]\n",
|
||
" anchors = anchors.squeeze(0)\n",
|
||
" num_classes, num_anchors = cls_probs.shape[1], cls_probs.shape[2]\n",
|
||
" out = []\n",
|
||
" for i in range(batch_size):\n",
|
||
" cls_prob, offset_pred = cls_probs[i], offset_preds[i].reshape(-1, 4)\n",
|
||
" conf, class_id = torch.max(cls_prob[1:], 0)\n",
|
||
" predicted_bb = offset_inverse(anchors, offset_pred)\n",
|
||
" keep = nms(predicted_bb, conf, nms_threshold)\n",
|
||
"\n",
|
||
" # 找到所有的non_keep索引，并将类设置为背景\n",
|
||
" all_idx = torch.arange(num_anchors, dtype=torch.long, device=device)\n",
|
||
" combined = torch.cat((keep, all_idx))\n",
|
||
" uniques, counts = combined.unique(return_counts=True)\n",
|
||
" non_keep = uniques[counts == 1]\n",
|
||
" all_id_sorted = torch.cat((keep, non_keep))\n",
|
||
" class_id[non_keep] = -1\n",
|
||
" class_id = class_id[all_id_sorted]\n",
|
||
" conf, predicted_bb = conf[all_id_sorted], predicted_bb[all_id_sorted]\n",
|
||
" # pos_threshold是一个用于非背景预测的阈值\n",
|
||
" below_min_idx = (conf < pos_threshold)\n",
|
||
" class_id[below_min_idx] = -1\n",
|
||
" conf[below_min_idx] = 1 - conf[below_min_idx]\n",
|
||
" pred_info = torch.cat((class_id.unsqueeze(1),\n",
|
||
" conf.unsqueeze(1),\n",
|
||
" predicted_bb), dim=1)\n",
|
||
" out.append(pred_info)\n",
|
||
" return torch.stack(out)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3952b7dd",
|
||
"metadata": {
|
||
"origin_pos": 55
|
||
},
|
||
"source": [
|
||
"现在让我们[**将上述算法应用到一个带有四个锚框的具体示例中**]。\n",
|
||
"为简单起见，我们假设预测的偏移量都是零，这意味着预测的边界框即是锚框。\n",
|
||
"对于背景、狗和猫其中的每个类，我们还定义了它的预测概率。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"id": "4654e2f7",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.179666Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.179298Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.188634Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.187737Z"
|
||
},
|
||
"origin_pos": 56,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"anchors = torch.tensor([[0.1, 0.08, 0.52, 0.92], [0.08, 0.2, 0.56, 0.95],\n",
|
||
" [0.15, 0.3, 0.62, 0.91], [0.55, 0.2, 0.9, 0.88]])\n",
|
||
"offset_preds = torch.tensor([0] * anchors.numel())\n",
|
||
"cls_probs = torch.tensor([[0] * 4, # 背景的预测概率\n",
|
||
" [0.9, 0.8, 0.7, 0.1], # 狗的预测概率\n",
|
||
" [0.1, 0.2, 0.3, 0.9]]) # 猫的预测概率"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "96915571",
|
||
"metadata": {
|
||
"origin_pos": 58
|
||
},
|
||
"source": [
|
||
"我们可以[**在图像上绘制这些预测边界框和置信度**]。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"id": "b9619cba",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.193833Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.193198Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.435994Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.434923Z"
|
||
},
|
||
"origin_pos": 59,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/svg+xml": [
|
||
"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n",
|
||
"<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
|
||
" \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
|
||
"<svg xmlns:xlink=\"http://www.w3.org/1999/xlink\" width=\"216.84258pt\" height=\"170.656221pt\" viewBox=\"0 0 216.84258 170.656221\" xmlns=\"http://www.w3.org/2000/svg\" version=\"1.1\">\n",
|
||
" <metadata>\n",
|
||
" <rdf:RDF xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n",
|
||
" <cc:Work>\n",
|
||
" <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n",
|
||
" <dc:date>2023-08-18T07:00:46.369699</dc:date>\n",
|
||
" <dc:format>image/svg+xml</dc:format>\n",
|
||
" <dc:creator>\n",
|
||
" <cc:Agent>\n",
|
||
" <dc:title>Matplotlib v3.5.1, https://matplotlib.org/</dc:title>\n",
|
||
" </cc:Agent>\n",
|
||
" </dc:creator>\n",
|
||
" </cc:Work>\n",
|
||
" </rdf:RDF>\n",
|
||
" </metadata>\n",
|
||
" <defs>\n",
|
||
" <style type=\"text/css\">*{stroke-linejoin: round; stroke-linecap: butt}</style>\n",
|
||
" </defs>\n",
|
||
" <g id=\"figure_1\">\n",
|
||
" <g id=\"patch_1\">\n",
|
||
" <path d=\"M 0 170.656221 \n",
|
||
"L 216.84258 170.656221 \n",
|
||
"L 216.84258 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 170.656221 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 209.64258 146.778096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"L 33.2875 10.878096 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g clip-path=\"url(#pd3121bced0)\">\n",
|
||
" <image xlink:href=\"data:image/png;base64,\n",
|
||
"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\" id=\"image00b8f1d6f0\" transform=\"scale(1 -1)translate(0 -136)\" x=\"33.2875\" y=\"-10.778096\" width=\"177\" height=\"136\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 51.044132 21.871218 \n",
|
||
"L 125.113264 21.871218 \n",
|
||
"L 125.113264 136.027218 \n",
|
||
"L 51.044132 136.027218 \n",
|
||
"L 51.044132 21.871218 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pd3121bced0)\" style=\"fill: none; stroke: #0000ff; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 47.517029 38.17922 \n",
|
||
"L 132.167466 38.17922 \n",
|
||
"L 132.167466 140.104222 \n",
|
||
"L 47.517029 140.104222 \n",
|
||
"L 47.517029 38.17922 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pd3121bced0)\" style=\"fill: none; stroke: #008000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 59.861886 51.769219 \n",
|
||
"L 142.748777 51.769219 \n",
|
||
"L 142.748777 134.668221 \n",
|
||
"L 59.861886 134.668221 \n",
|
||
"L 59.861886 51.769219 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pd3121bced0)\" style=\"fill: none; stroke: #ff0000; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_6\">\n",
|
||
" <path d=\"M 130.403916 38.17922 \n",
|
||
"L 192.128198 38.17922 \n",
|
||
"L 192.128198 130.591217 \n",
|
||
"L 130.403916 130.591217 \n",
|
||
"L 130.403916 38.17922 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pd3121bced0)\" style=\"fill: none; stroke: #bf00bf; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m23a4e1cd1f\" d=\"M 0 0 \n",
|
||
"L 0 3.5 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m23a4e1cd1f\" x=\"33.408623\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(30.227373 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-30\" d=\"M 2034 4250 \n",
|
||
"Q 1547 4250 1301 3770 \n",
|
||
"Q 1056 3291 1056 2328 \n",
|
||
"Q 1056 1369 1301 889 \n",
|
||
"Q 1547 409 2034 409 \n",
|
||
"Q 2525 409 2770 889 \n",
|
||
"Q 3016 1369 3016 2328 \n",
|
||
"Q 3016 3291 2770 3770 \n",
|
||
"Q 2525 4250 2034 4250 \n",
|
||
"z\n",
|
||
"M 2034 4750 \n",
|
||
"Q 2819 4750 3233 4129 \n",
|
||
"Q 3647 3509 3647 2328 \n",
|
||
"Q 3647 1150 3233 529 \n",
|
||
"Q 2819 -91 2034 -91 \n",
|
||
"Q 1250 -91 836 529 \n",
|
||
"Q 422 1150 422 2328 \n",
|
||
"Q 422 3509 836 4129 \n",
|
||
"Q 1250 4750 2034 4750 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m23a4e1cd1f\" x=\"81.857821\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(72.314071 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-32\" d=\"M 1228 531 \n",
|
||
"L 3431 531 \n",
|
||
"L 3431 0 \n",
|
||
"L 469 0 \n",
|
||
"L 469 531 \n",
|
||
"Q 828 903 1448 1529 \n",
|
||
"Q 2069 2156 2228 2338 \n",
|
||
"Q 2531 2678 2651 2914 \n",
|
||
"Q 2772 3150 2772 3378 \n",
|
||
"Q 2772 3750 2511 3984 \n",
|
||
"Q 2250 4219 1831 4219 \n",
|
||
"Q 1534 4219 1204 4116 \n",
|
||
"Q 875 4013 500 3803 \n",
|
||
"L 500 4441 \n",
|
||
"Q 881 4594 1212 4672 \n",
|
||
"Q 1544 4750 1819 4750 \n",
|
||
"Q 2544 4750 2975 4387 \n",
|
||
"Q 3406 4025 3406 3419 \n",
|
||
"Q 3406 3131 3298 2873 \n",
|
||
"Q 3191 2616 2906 2266 \n",
|
||
"Q 2828 2175 2409 1742 \n",
|
||
"Q 1991 1309 1228 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m23a4e1cd1f\" x=\"130.307019\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(120.763269 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-34\" d=\"M 2419 4116 \n",
|
||
"L 825 1625 \n",
|
||
"L 2419 1625 \n",
|
||
"L 2419 4116 \n",
|
||
"z\n",
|
||
"M 2253 4666 \n",
|
||
"L 3047 4666 \n",
|
||
"L 3047 1625 \n",
|
||
"L 3713 1625 \n",
|
||
"L 3713 1100 \n",
|
||
"L 3047 1100 \n",
|
||
"L 3047 0 \n",
|
||
"L 2419 0 \n",
|
||
"L 2419 1100 \n",
|
||
"L 313 1100 \n",
|
||
"L 313 1709 \n",
|
||
"L 2253 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m23a4e1cd1f\" x=\"178.756217\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 600 -->\n",
|
||
" <g transform=\"translate(169.212467 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-36\" d=\"M 2113 2584 \n",
|
||
"Q 1688 2584 1439 2293 \n",
|
||
"Q 1191 2003 1191 1497 \n",
|
||
"Q 1191 994 1439 701 \n",
|
||
"Q 1688 409 2113 409 \n",
|
||
"Q 2538 409 2786 701 \n",
|
||
"Q 3034 994 3034 1497 \n",
|
||
"Q 3034 2003 2786 2293 \n",
|
||
"Q 2538 2584 2113 2584 \n",
|
||
"z\n",
|
||
"M 3366 4563 \n",
|
||
"L 3366 3988 \n",
|
||
"Q 3128 4100 2886 4159 \n",
|
||
"Q 2644 4219 2406 4219 \n",
|
||
"Q 1781 4219 1451 3797 \n",
|
||
"Q 1122 3375 1075 2522 \n",
|
||
"Q 1259 2794 1537 2939 \n",
|
||
"Q 1816 3084 2150 3084 \n",
|
||
"Q 2853 3084 3261 2657 \n",
|
||
"Q 3669 2231 3669 1497 \n",
|
||
"Q 3669 778 3244 343 \n",
|
||
"Q 2819 -91 2113 -91 \n",
|
||
"Q 1303 -91 875 529 \n",
|
||
"Q 447 1150 447 2328 \n",
|
||
"Q 447 3434 972 4092 \n",
|
||
"Q 1497 4750 2381 4750 \n",
|
||
"Q 2619 4750 2861 4703 \n",
|
||
"Q 3103 4656 3366 4563 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-36\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m8fd292e66e\" d=\"M 0 0 \n",
|
||
"L -3.5 0 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m8fd292e66e\" x=\"33.2875\" y=\"10.999219\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(19.925 14.798437)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m8fd292e66e\" x=\"33.2875\" y=\"35.223818\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- 100 -->\n",
|
||
" <g transform=\"translate(7.2 39.023036)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-31\" d=\"M 794 531 \n",
|
||
"L 1825 531 \n",
|
||
"L 1825 4091 \n",
|
||
"L 703 3866 \n",
|
||
"L 703 4441 \n",
|
||
"L 1819 4666 \n",
|
||
"L 2450 4666 \n",
|
||
"L 2450 531 \n",
|
||
"L 3481 531 \n",
|
||
"L 3481 0 \n",
|
||
"L 794 0 \n",
|
||
"L 794 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m8fd292e66e\" x=\"33.2875\" y=\"59.448417\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(7.2 63.247635)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m8fd292e66e\" x=\"33.2875\" y=\"83.673016\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 300 -->\n",
|
||
" <g transform=\"translate(7.2 87.472234)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-33\" d=\"M 2597 2516 \n",
|
||
"Q 3050 2419 3304 2112 \n",
|
||
"Q 3559 1806 3559 1356 \n",
|
||
"Q 3559 666 3084 287 \n",
|
||
"Q 2609 -91 1734 -91 \n",
|
||
"Q 1441 -91 1130 -33 \n",
|
||
"Q 819 25 488 141 \n",
|
||
"L 488 750 \n",
|
||
"Q 750 597 1062 519 \n",
|
||
"Q 1375 441 1716 441 \n",
|
||
"Q 2309 441 2620 675 \n",
|
||
"Q 2931 909 2931 1356 \n",
|
||
"Q 2931 1769 2642 2001 \n",
|
||
"Q 2353 2234 1838 2234 \n",
|
||
"L 1294 2234 \n",
|
||
"L 1294 2753 \n",
|
||
"L 1863 2753 \n",
|
||
"Q 2328 2753 2575 2939 \n",
|
||
"Q 2822 3125 2822 3475 \n",
|
||
"Q 2822 3834 2567 4026 \n",
|
||
"Q 2313 4219 1838 4219 \n",
|
||
"Q 1578 4219 1281 4162 \n",
|
||
"Q 984 4106 628 3988 \n",
|
||
"L 628 4550 \n",
|
||
"Q 988 4650 1302 4700 \n",
|
||
"Q 1616 4750 1894 4750 \n",
|
||
"Q 2613 4750 3031 4423 \n",
|
||
"Q 3450 4097 3450 3541 \n",
|
||
"Q 3450 3153 3228 2886 \n",
|
||
"Q 3006 2619 2597 2516 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-33\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m8fd292e66e\" x=\"33.2875\" y=\"107.897614\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(7.2 111.696833)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_6\">\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m8fd292e66e\" x=\"33.2875\" y=\"132.122213\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 500 -->\n",
|
||
" <g transform=\"translate(7.2 135.921432)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-35\" d=\"M 691 4666 \n",
|
||
"L 3169 4666 \n",
|
||
"L 3169 4134 \n",
|
||
"L 1269 4134 \n",
|
||
"L 1269 2991 \n",
|
||
"Q 1406 3038 1543 3061 \n",
|
||
"Q 1681 3084 1819 3084 \n",
|
||
"Q 2600 3084 3056 2656 \n",
|
||
"Q 3513 2228 3513 1497 \n",
|
||
"Q 3513 744 3044 326 \n",
|
||
"Q 2575 -91 1722 -91 \n",
|
||
"Q 1428 -91 1123 -41 \n",
|
||
"Q 819 9 494 109 \n",
|
||
"L 494 744 \n",
|
||
"Q 775 591 1075 516 \n",
|
||
"Q 1375 441 1709 441 \n",
|
||
"Q 2250 441 2565 725 \n",
|
||
"Q 2881 1009 2881 1497 \n",
|
||
"Q 2881 1984 2565 2268 \n",
|
||
"Q 2250 2553 1709 2553 \n",
|
||
"Q 1456 2553 1204 2497 \n",
|
||
"Q 953 2441 691 2322 \n",
|
||
"L 691 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 33.2875 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_8\">\n",
|
||
" <path d=\"M 209.64258 146.778096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_9\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 209.64258 146.778096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_10\">\n",
|
||
" <path d=\"M 33.2875 10.878096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <g id=\"patch_11\">\n",
|
||
" <path d=\"M 27.689835 30.186374 \n",
|
||
"L 74.398429 30.186374 \n",
|
||
"L 74.398429 13.556062 \n",
|
||
"L 27.689835 13.556062 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #0000ff\"/>\n",
|
||
" </g>\n",
|
||
" <!-- dog=0.9 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(31.649835 24.354656)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-64\" d=\"M 2906 2969 \n",
|
||
"L 2906 4863 \n",
|
||
"L 3481 4863 \n",
|
||
"L 3481 0 \n",
|
||
"L 2906 0 \n",
|
||
"L 2906 525 \n",
|
||
"Q 2725 213 2448 61 \n",
|
||
"Q 2172 -91 1784 -91 \n",
|
||
"Q 1150 -91 751 415 \n",
|
||
"Q 353 922 353 1747 \n",
|
||
"Q 353 2572 751 3078 \n",
|
||
"Q 1150 3584 1784 3584 \n",
|
||
"Q 2172 3584 2448 3432 \n",
|
||
"Q 2725 3281 2906 2969 \n",
|
||
"z\n",
|
||
"M 947 1747 \n",
|
||
"Q 947 1113 1208 752 \n",
|
||
"Q 1469 391 1925 391 \n",
|
||
"Q 2381 391 2643 752 \n",
|
||
"Q 2906 1113 2906 1747 \n",
|
||
"Q 2906 2381 2643 2742 \n",
|
||
"Q 2381 3103 1925 3103 \n",
|
||
"Q 1469 3103 1208 2742 \n",
|
||
"Q 947 2381 947 1747 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6f\" d=\"M 1959 3097 \n",
|
||
"Q 1497 3097 1228 2736 \n",
|
||
"Q 959 2375 959 1747 \n",
|
||
"Q 959 1119 1226 758 \n",
|
||
"Q 1494 397 1959 397 \n",
|
||
"Q 2419 397 2687 759 \n",
|
||
"Q 2956 1122 2956 1747 \n",
|
||
"Q 2956 2369 2687 2733 \n",
|
||
"Q 2419 3097 1959 3097 \n",
|
||
"z\n",
|
||
"M 1959 3584 \n",
|
||
"Q 2709 3584 3137 3096 \n",
|
||
"Q 3566 2609 3566 1747 \n",
|
||
"Q 3566 888 3137 398 \n",
|
||
"Q 2709 -91 1959 -91 \n",
|
||
"Q 1206 -91 779 398 \n",
|
||
"Q 353 888 353 1747 \n",
|
||
"Q 353 2609 779 3096 \n",
|
||
"Q 1206 3584 1959 3584 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-67\" d=\"M 2906 1791 \n",
|
||
"Q 2906 2416 2648 2759 \n",
|
||
"Q 2391 3103 1925 3103 \n",
|
||
"Q 1463 3103 1205 2759 \n",
|
||
"Q 947 2416 947 1791 \n",
|
||
"Q 947 1169 1205 825 \n",
|
||
"Q 1463 481 1925 481 \n",
|
||
"Q 2391 481 2648 825 \n",
|
||
"Q 2906 1169 2906 1791 \n",
|
||
"z\n",
|
||
"M 3481 434 \n",
|
||
"Q 3481 -459 3084 -895 \n",
|
||
"Q 2688 -1331 1869 -1331 \n",
|
||
"Q 1566 -1331 1297 -1286 \n",
|
||
"Q 1028 -1241 775 -1147 \n",
|
||
"L 775 -588 \n",
|
||
"Q 1028 -725 1275 -790 \n",
|
||
"Q 1522 -856 1778 -856 \n",
|
||
"Q 2344 -856 2625 -561 \n",
|
||
"Q 2906 -266 2906 331 \n",
|
||
"L 2906 616 \n",
|
||
"Q 2728 306 2450 153 \n",
|
||
"Q 2172 0 1784 0 \n",
|
||
"Q 1141 0 747 490 \n",
|
||
"Q 353 981 353 1791 \n",
|
||
"Q 353 2603 747 3093 \n",
|
||
"Q 1141 3584 1784 3584 \n",
|
||
"Q 2172 3584 2450 3431 \n",
|
||
"Q 2728 3278 2906 2969 \n",
|
||
"L 2906 3500 \n",
|
||
"L 3481 3500 \n",
|
||
"L 3481 434 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-3d\" d=\"M 678 2906 \n",
|
||
"L 4684 2906 \n",
|
||
"L 4684 2381 \n",
|
||
"L 678 2381 \n",
|
||
"L 678 2906 \n",
|
||
"z\n",
|
||
"M 678 1631 \n",
|
||
"L 4684 1631 \n",
|
||
"L 4684 1100 \n",
|
||
"L 678 1100 \n",
|
||
"L 678 1631 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-2e\" d=\"M 684 794 \n",
|
||
"L 1344 794 \n",
|
||
"L 1344 0 \n",
|
||
"L 684 0 \n",
|
||
"L 684 794 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-39\" d=\"M 703 97 \n",
|
||
"L 703 672 \n",
|
||
"Q 941 559 1184 500 \n",
|
||
"Q 1428 441 1663 441 \n",
|
||
"Q 2288 441 2617 861 \n",
|
||
"Q 2947 1281 2994 2138 \n",
|
||
"Q 2813 1869 2534 1725 \n",
|
||
"Q 2256 1581 1919 1581 \n",
|
||
"Q 1219 1581 811 2004 \n",
|
||
"Q 403 2428 403 3163 \n",
|
||
"Q 403 3881 828 4315 \n",
|
||
"Q 1253 4750 1959 4750 \n",
|
||
"Q 2769 4750 3195 4129 \n",
|
||
"Q 3622 3509 3622 2328 \n",
|
||
"Q 3622 1225 3098 567 \n",
|
||
"Q 2575 -91 1691 -91 \n",
|
||
"Q 1453 -91 1209 -44 \n",
|
||
"Q 966 3 703 97 \n",
|
||
"z\n",
|
||
"M 1959 2075 \n",
|
||
"Q 2384 2075 2632 2365 \n",
|
||
"Q 2881 2656 2881 3163 \n",
|
||
"Q 2881 3666 2632 3958 \n",
|
||
"Q 2384 4250 1959 4250 \n",
|
||
"Q 1534 4250 1286 3958 \n",
|
||
"Q 1038 3666 1038 3163 \n",
|
||
"Q 1038 2656 1286 2365 \n",
|
||
"Q 1534 2075 1959 2075 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-64\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"63.476562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-67\" x=\"124.658203\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"188.134766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"271.923828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"335.546875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-39\" x=\"367.333984\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <g id=\"patch_12\">\n",
|
||
" <path d=\"M 24.162732 46.494376 \n",
|
||
"L 70.871326 46.494376 \n",
|
||
"L 70.871326 29.864064 \n",
|
||
"L 24.162732 29.864064 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #008000\"/>\n",
|
||
" </g>\n",
|
||
" <!-- dog=0.8 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(28.122732 40.662657)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-38\" d=\"M 2034 2216 \n",
|
||
"Q 1584 2216 1326 1975 \n",
|
||
"Q 1069 1734 1069 1313 \n",
|
||
"Q 1069 891 1326 650 \n",
|
||
"Q 1584 409 2034 409 \n",
|
||
"Q 2484 409 2743 651 \n",
|
||
"Q 3003 894 3003 1313 \n",
|
||
"Q 3003 1734 2745 1975 \n",
|
||
"Q 2488 2216 2034 2216 \n",
|
||
"z\n",
|
||
"M 1403 2484 \n",
|
||
"Q 997 2584 770 2862 \n",
|
||
"Q 544 3141 544 3541 \n",
|
||
"Q 544 4100 942 4425 \n",
|
||
"Q 1341 4750 2034 4750 \n",
|
||
"Q 2731 4750 3128 4425 \n",
|
||
"Q 3525 4100 3525 3541 \n",
|
||
"Q 3525 3141 3298 2862 \n",
|
||
"Q 3072 2584 2669 2484 \n",
|
||
"Q 3125 2378 3379 2068 \n",
|
||
"Q 3634 1759 3634 1313 \n",
|
||
"Q 3634 634 3220 271 \n",
|
||
"Q 2806 -91 2034 -91 \n",
|
||
"Q 1263 -91 848 271 \n",
|
||
"Q 434 634 434 1313 \n",
|
||
"Q 434 1759 690 2068 \n",
|
||
"Q 947 2378 1403 2484 \n",
|
||
"z\n",
|
||
"M 1172 3481 \n",
|
||
"Q 1172 3119 1398 2916 \n",
|
||
"Q 1625 2713 2034 2713 \n",
|
||
"Q 2441 2713 2670 2916 \n",
|
||
"Q 2900 3119 2900 3481 \n",
|
||
"Q 2900 3844 2670 4047 \n",
|
||
"Q 2441 4250 2034 4250 \n",
|
||
"Q 1625 4250 1398 4047 \n",
|
||
"Q 1172 3844 1172 3481 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-64\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"63.476562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-67\" x=\"124.658203\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"188.134766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"271.923828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"335.546875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-38\" x=\"367.333984\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_13\">\n",
|
||
" <g id=\"patch_13\">\n",
|
||
" <path d=\"M 36.507589 60.084376 \n",
|
||
"L 83.216183 60.084376 \n",
|
||
"L 83.216183 43.454063 \n",
|
||
"L 36.507589 43.454063 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ff0000\"/>\n",
|
||
" </g>\n",
|
||
" <!-- dog=0.7 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(40.467589 54.252657)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-37\" d=\"M 525 4666 \n",
|
||
"L 3525 4666 \n",
|
||
"L 3525 4397 \n",
|
||
"L 1831 0 \n",
|
||
"L 1172 0 \n",
|
||
"L 2766 4134 \n",
|
||
"L 525 4134 \n",
|
||
"L 525 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-64\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"63.476562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-67\" x=\"124.658203\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"188.134766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"271.923828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"335.546875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-37\" x=\"367.333984\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_14\">\n",
|
||
" <g id=\"patch_14\">\n",
|
||
" <path d=\"M 108.520556 46.494376 \n",
|
||
"L 152.287275 46.494376 \n",
|
||
"L 152.287275 29.864064 \n",
|
||
"L 108.520556 29.864064 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #bf00bf\"/>\n",
|
||
" </g>\n",
|
||
" <!-- cat=0.9 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(112.480556 40.662657)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-63\" d=\"M 3122 3366 \n",
|
||
"L 3122 2828 \n",
|
||
"Q 2878 2963 2633 3030 \n",
|
||
"Q 2388 3097 2138 3097 \n",
|
||
"Q 1578 3097 1268 2742 \n",
|
||
"Q 959 2388 959 1747 \n",
|
||
"Q 959 1106 1268 751 \n",
|
||
"Q 1578 397 2138 397 \n",
|
||
"Q 2388 397 2633 464 \n",
|
||
"Q 2878 531 3122 666 \n",
|
||
"L 3122 134 \n",
|
||
"Q 2881 22 2623 -34 \n",
|
||
"Q 2366 -91 2075 -91 \n",
|
||
"Q 1284 -91 818 406 \n",
|
||
"Q 353 903 353 1747 \n",
|
||
"Q 353 2603 823 3093 \n",
|
||
"Q 1294 3584 2113 3584 \n",
|
||
"Q 2378 3584 2631 3529 \n",
|
||
"Q 2884 3475 3122 3366 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-61\" d=\"M 2194 1759 \n",
|
||
"Q 1497 1759 1228 1600 \n",
|
||
"Q 959 1441 959 1056 \n",
|
||
"Q 959 750 1161 570 \n",
|
||
"Q 1363 391 1709 391 \n",
|
||
"Q 2188 391 2477 730 \n",
|
||
"Q 2766 1069 2766 1631 \n",
|
||
"L 2766 1759 \n",
|
||
"L 2194 1759 \n",
|
||
"z\n",
|
||
"M 3341 1997 \n",
|
||
"L 3341 0 \n",
|
||
"L 2766 0 \n",
|
||
"L 2766 531 \n",
|
||
"Q 2569 213 2275 61 \n",
|
||
"Q 1981 -91 1556 -91 \n",
|
||
"Q 1019 -91 701 211 \n",
|
||
"Q 384 513 384 1019 \n",
|
||
"Q 384 1609 779 1909 \n",
|
||
"Q 1175 2209 1959 2209 \n",
|
||
"L 2766 2209 \n",
|
||
"L 2766 2266 \n",
|
||
"Q 2766 2663 2505 2880 \n",
|
||
"Q 2244 3097 1772 3097 \n",
|
||
"Q 1472 3097 1187 3025 \n",
|
||
"Q 903 2953 641 2809 \n",
|
||
"L 641 3341 \n",
|
||
"Q 956 3463 1253 3523 \n",
|
||
"Q 1550 3584 1831 3584 \n",
|
||
"Q 2591 3584 2966 3190 \n",
|
||
"Q 3341 2797 3341 1997 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-74\" d=\"M 1172 4494 \n",
|
||
"L 1172 3500 \n",
|
||
"L 2356 3500 \n",
|
||
"L 2356 3053 \n",
|
||
"L 1172 3053 \n",
|
||
"L 1172 1153 \n",
|
||
"Q 1172 725 1289 603 \n",
|
||
"Q 1406 481 1766 481 \n",
|
||
"L 2356 481 \n",
|
||
"L 2356 0 \n",
|
||
"L 1766 0 \n",
|
||
"Q 1100 0 847 248 \n",
|
||
"Q 594 497 594 1153 \n",
|
||
"L 594 3053 \n",
|
||
"L 172 3053 \n",
|
||
"L 172 3500 \n",
|
||
"L 594 3500 \n",
|
||
"L 594 4494 \n",
|
||
"L 1172 4494 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"54.980469\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\" x=\"116.259766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"155.46875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"239.257812\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"302.880859\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-39\" x=\"334.667969\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"pd3121bced0\">\n",
|
||
" <rect x=\"33.2875\" y=\"10.878096\" width=\"176.35508\" height=\"135.9\"/>\n",
|
||
" </clipPath>\n",
|
||
" </defs>\n",
|
||
"</svg>\n"
|
||
],
|
||
"text/plain": [
|
||
"<Figure size 252x180 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"fig = d2l.plt.imshow(img)\n",
|
||
"show_bboxes(fig.axes, anchors * bbox_scale,\n",
|
||
" ['dog=0.9', 'dog=0.8', 'dog=0.7', 'cat=0.9'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "25b63f89",
|
||
"metadata": {
|
||
"origin_pos": 60
|
||
},
|
||
"source": [
|
||
"现在我们可以调用`multibox_detection`函数来执行非极大值抑制，其中阈值设置为0.5。\n",
|
||
"请注意，我们在示例的张量输入中添加了维度。\n",
|
||
"\n",
|
||
"我们可以看到[**返回结果的形状是（批量大小，锚框的数量，6）**]。\n",
|
||
"最内层维度中的六个元素提供了同一预测边界框的输出信息。\n",
|
||
"第一个元素是预测的类索引，从0开始（0代表狗，1代表猫），值-1表示背景或在非极大值抑制中被移除了。\n",
|
||
"第二个元素是预测的边界框的置信度。\n",
|
||
"其余四个元素分别是预测边界框左上角和右下角的$(x, y)$轴坐标（范围介于0和1之间）。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"id": "ab9c180c",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.440560Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.439738Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.458973Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.457996Z"
|
||
},
|
||
"origin_pos": 62,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"tensor([[[ 0.00, 0.90, 0.10, 0.08, 0.52, 0.92],\n",
|
||
" [ 1.00, 0.90, 0.55, 0.20, 0.90, 0.88],\n",
|
||
" [-1.00, 0.80, 0.08, 0.20, 0.56, 0.95],\n",
|
||
" [-1.00, 0.70, 0.15, 0.30, 0.62, 0.91]]])"
|
||
]
|
||
},
|
||
"execution_count": 21,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"output = multibox_detection(cls_probs.unsqueeze(dim=0),\n",
|
||
" offset_preds.unsqueeze(dim=0),\n",
|
||
" anchors.unsqueeze(dim=0),\n",
|
||
" nms_threshold=0.5)\n",
|
||
"output"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "79cb8b53",
|
||
"metadata": {
|
||
"origin_pos": 64
|
||
},
|
||
"source": [
|
||
"删除-1类别（背景）的预测边界框后，我们可以[**输出由非极大值抑制保存的最终预测边界框**]。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"id": "f1e04b3f",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:46.496750Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:46.495866Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:46.753536Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:46.752302Z"
|
||
},
|
||
"origin_pos": 65,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/svg+xml": [
|
||
"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n",
|
||
"<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
|
||
" \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
|
||
"<svg xmlns:xlink=\"http://www.w3.org/1999/xlink\" width=\"216.84258pt\" height=\"170.656221pt\" viewBox=\"0 0 216.84258 170.656221\" xmlns=\"http://www.w3.org/2000/svg\" version=\"1.1\">\n",
|
||
" <metadata>\n",
|
||
" <rdf:RDF xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n",
|
||
" <cc:Work>\n",
|
||
" <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n",
|
||
" <dc:date>2023-08-18T07:00:46.686810</dc:date>\n",
|
||
" <dc:format>image/svg+xml</dc:format>\n",
|
||
" <dc:creator>\n",
|
||
" <cc:Agent>\n",
|
||
" <dc:title>Matplotlib v3.5.1, https://matplotlib.org/</dc:title>\n",
|
||
" </cc:Agent>\n",
|
||
" </dc:creator>\n",
|
||
" </cc:Work>\n",
|
||
" </rdf:RDF>\n",
|
||
" </metadata>\n",
|
||
" <defs>\n",
|
||
" <style type=\"text/css\">*{stroke-linejoin: round; stroke-linecap: butt}</style>\n",
|
||
" </defs>\n",
|
||
" <g id=\"figure_1\">\n",
|
||
" <g id=\"patch_1\">\n",
|
||
" <path d=\"M 0 170.656221 \n",
|
||
"L 216.84258 170.656221 \n",
|
||
"L 216.84258 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 170.656221 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 209.64258 146.778096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"L 33.2875 10.878096 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g clip-path=\"url(#pe2aa6bfcac)\">\n",
|
||
" <image xlink:href=\"data:image/png;base64,\n",
|
||
"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\" id=\"image781ecba93e\" transform=\"scale(1 -1)translate(0 -136)\" x=\"33.2875\" y=\"-10.778096\" width=\"177\" height=\"136\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 51.044132 21.871216 \n",
|
||
"L 125.113264 21.871216 \n",
|
||
"L 125.113264 136.027218 \n",
|
||
"L 51.044132 136.027218 \n",
|
||
"L 51.044132 21.871216 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pe2aa6bfcac)\" style=\"fill: none; stroke: #0000ff; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 130.40393 38.179222 \n",
|
||
"L 192.128198 38.179222 \n",
|
||
"L 192.128198 130.591217 \n",
|
||
"L 130.40393 130.591217 \n",
|
||
"L 130.40393 38.179222 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#pe2aa6bfcac)\" style=\"fill: none; stroke: #0000ff; stroke-width: 2; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m9e013a9256\" d=\"M 0 0 \n",
|
||
"L 0 3.5 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9e013a9256\" x=\"33.408623\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(30.227373 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-30\" d=\"M 2034 4250 \n",
|
||
"Q 1547 4250 1301 3770 \n",
|
||
"Q 1056 3291 1056 2328 \n",
|
||
"Q 1056 1369 1301 889 \n",
|
||
"Q 1547 409 2034 409 \n",
|
||
"Q 2525 409 2770 889 \n",
|
||
"Q 3016 1369 3016 2328 \n",
|
||
"Q 3016 3291 2770 3770 \n",
|
||
"Q 2525 4250 2034 4250 \n",
|
||
"z\n",
|
||
"M 2034 4750 \n",
|
||
"Q 2819 4750 3233 4129 \n",
|
||
"Q 3647 3509 3647 2328 \n",
|
||
"Q 3647 1150 3233 529 \n",
|
||
"Q 2819 -91 2034 -91 \n",
|
||
"Q 1250 -91 836 529 \n",
|
||
"Q 422 1150 422 2328 \n",
|
||
"Q 422 3509 836 4129 \n",
|
||
"Q 1250 4750 2034 4750 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9e013a9256\" x=\"81.857821\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(72.314071 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-32\" d=\"M 1228 531 \n",
|
||
"L 3431 531 \n",
|
||
"L 3431 0 \n",
|
||
"L 469 0 \n",
|
||
"L 469 531 \n",
|
||
"Q 828 903 1448 1529 \n",
|
||
"Q 2069 2156 2228 2338 \n",
|
||
"Q 2531 2678 2651 2914 \n",
|
||
"Q 2772 3150 2772 3378 \n",
|
||
"Q 2772 3750 2511 3984 \n",
|
||
"Q 2250 4219 1831 4219 \n",
|
||
"Q 1534 4219 1204 4116 \n",
|
||
"Q 875 4013 500 3803 \n",
|
||
"L 500 4441 \n",
|
||
"Q 881 4594 1212 4672 \n",
|
||
"Q 1544 4750 1819 4750 \n",
|
||
"Q 2544 4750 2975 4387 \n",
|
||
"Q 3406 4025 3406 3419 \n",
|
||
"Q 3406 3131 3298 2873 \n",
|
||
"Q 3191 2616 2906 2266 \n",
|
||
"Q 2828 2175 2409 1742 \n",
|
||
"Q 1991 1309 1228 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9e013a9256\" x=\"130.307019\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(120.763269 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-34\" d=\"M 2419 4116 \n",
|
||
"L 825 1625 \n",
|
||
"L 2419 1625 \n",
|
||
"L 2419 4116 \n",
|
||
"z\n",
|
||
"M 2253 4666 \n",
|
||
"L 3047 4666 \n",
|
||
"L 3047 1625 \n",
|
||
"L 3713 1625 \n",
|
||
"L 3713 1100 \n",
|
||
"L 3047 1100 \n",
|
||
"L 3047 0 \n",
|
||
"L 2419 0 \n",
|
||
"L 2419 1100 \n",
|
||
"L 313 1100 \n",
|
||
"L 313 1709 \n",
|
||
"L 2253 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9e013a9256\" x=\"178.756217\" y=\"146.778096\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 600 -->\n",
|
||
" <g transform=\"translate(169.212467 161.376533)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-36\" d=\"M 2113 2584 \n",
|
||
"Q 1688 2584 1439 2293 \n",
|
||
"Q 1191 2003 1191 1497 \n",
|
||
"Q 1191 994 1439 701 \n",
|
||
"Q 1688 409 2113 409 \n",
|
||
"Q 2538 409 2786 701 \n",
|
||
"Q 3034 994 3034 1497 \n",
|
||
"Q 3034 2003 2786 2293 \n",
|
||
"Q 2538 2584 2113 2584 \n",
|
||
"z\n",
|
||
"M 3366 4563 \n",
|
||
"L 3366 3988 \n",
|
||
"Q 3128 4100 2886 4159 \n",
|
||
"Q 2644 4219 2406 4219 \n",
|
||
"Q 1781 4219 1451 3797 \n",
|
||
"Q 1122 3375 1075 2522 \n",
|
||
"Q 1259 2794 1537 2939 \n",
|
||
"Q 1816 3084 2150 3084 \n",
|
||
"Q 2853 3084 3261 2657 \n",
|
||
"Q 3669 2231 3669 1497 \n",
|
||
"Q 3669 778 3244 343 \n",
|
||
"Q 2819 -91 2113 -91 \n",
|
||
"Q 1303 -91 875 529 \n",
|
||
"Q 447 1150 447 2328 \n",
|
||
"Q 447 3434 972 4092 \n",
|
||
"Q 1497 4750 2381 4750 \n",
|
||
"Q 2619 4750 2861 4703 \n",
|
||
"Q 3103 4656 3366 4563 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-36\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"mb1b03cd978\" d=\"M 0 0 \n",
|
||
"L -3.5 0 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1b03cd978\" x=\"33.2875\" y=\"10.999219\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(19.925 14.798437)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1b03cd978\" x=\"33.2875\" y=\"35.223818\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- 100 -->\n",
|
||
" <g transform=\"translate(7.2 39.023036)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-31\" d=\"M 794 531 \n",
|
||
"L 1825 531 \n",
|
||
"L 1825 4091 \n",
|
||
"L 703 3866 \n",
|
||
"L 703 4441 \n",
|
||
"L 1819 4666 \n",
|
||
"L 2450 4666 \n",
|
||
"L 2450 531 \n",
|
||
"L 3481 531 \n",
|
||
"L 3481 0 \n",
|
||
"L 794 0 \n",
|
||
"L 794 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1b03cd978\" x=\"33.2875\" y=\"59.448417\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 200 -->\n",
|
||
" <g transform=\"translate(7.2 63.247635)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1b03cd978\" x=\"33.2875\" y=\"83.673016\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 300 -->\n",
|
||
" <g transform=\"translate(7.2 87.472234)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-33\" d=\"M 2597 2516 \n",
|
||
"Q 3050 2419 3304 2112 \n",
|
||
"Q 3559 1806 3559 1356 \n",
|
||
"Q 3559 666 3084 287 \n",
|
||
"Q 2609 -91 1734 -91 \n",
|
||
"Q 1441 -91 1130 -33 \n",
|
||
"Q 819 25 488 141 \n",
|
||
"L 488 750 \n",
|
||
"Q 750 597 1062 519 \n",
|
||
"Q 1375 441 1716 441 \n",
|
||
"Q 2309 441 2620 675 \n",
|
||
"Q 2931 909 2931 1356 \n",
|
||
"Q 2931 1769 2642 2001 \n",
|
||
"Q 2353 2234 1838 2234 \n",
|
||
"L 1294 2234 \n",
|
||
"L 1294 2753 \n",
|
||
"L 1863 2753 \n",
|
||
"Q 2328 2753 2575 2939 \n",
|
||
"Q 2822 3125 2822 3475 \n",
|
||
"Q 2822 3834 2567 4026 \n",
|
||
"Q 2313 4219 1838 4219 \n",
|
||
"Q 1578 4219 1281 4162 \n",
|
||
"Q 984 4106 628 3988 \n",
|
||
"L 628 4550 \n",
|
||
"Q 988 4650 1302 4700 \n",
|
||
"Q 1616 4750 1894 4750 \n",
|
||
"Q 2613 4750 3031 4423 \n",
|
||
"Q 3450 4097 3450 3541 \n",
|
||
"Q 3450 3153 3228 2886 \n",
|
||
"Q 3006 2619 2597 2516 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-33\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1b03cd978\" x=\"33.2875\" y=\"107.897614\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 400 -->\n",
|
||
" <g transform=\"translate(7.2 111.696833)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_6\">\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1b03cd978\" x=\"33.2875\" y=\"132.122213\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 500 -->\n",
|
||
" <g transform=\"translate(7.2 135.921432)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-35\" d=\"M 691 4666 \n",
|
||
"L 3169 4666 \n",
|
||
"L 3169 4134 \n",
|
||
"L 1269 4134 \n",
|
||
"L 1269 2991 \n",
|
||
"Q 1406 3038 1543 3061 \n",
|
||
"Q 1681 3084 1819 3084 \n",
|
||
"Q 2600 3084 3056 2656 \n",
|
||
"Q 3513 2228 3513 1497 \n",
|
||
"Q 3513 744 3044 326 \n",
|
||
"Q 2575 -91 1722 -91 \n",
|
||
"Q 1428 -91 1123 -41 \n",
|
||
"Q 819 9 494 109 \n",
|
||
"L 494 744 \n",
|
||
"Q 775 591 1075 516 \n",
|
||
"Q 1375 441 1709 441 \n",
|
||
"Q 2250 441 2565 725 \n",
|
||
"Q 2881 1009 2881 1497 \n",
|
||
"Q 2881 1984 2565 2268 \n",
|
||
"Q 2250 2553 1709 2553 \n",
|
||
"Q 1456 2553 1204 2497 \n",
|
||
"Q 953 2441 691 2322 \n",
|
||
"L 691 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-35\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 33.2875 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_6\">\n",
|
||
" <path d=\"M 209.64258 146.778096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 33.2875 146.778096 \n",
|
||
"L 209.64258 146.778096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_8\">\n",
|
||
" <path d=\"M 33.2875 10.878096 \n",
|
||
"L 209.64258 10.878096 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <g id=\"patch_9\">\n",
|
||
" <path d=\"M 27.689835 30.186372 \n",
|
||
"L 74.398429 30.186372 \n",
|
||
"L 74.398429 13.55606 \n",
|
||
"L 27.689835 13.55606 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #0000ff\"/>\n",
|
||
" </g>\n",
|
||
" <!-- dog=0.9 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(31.649835 24.354654)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-64\" d=\"M 2906 2969 \n",
|
||
"L 2906 4863 \n",
|
||
"L 3481 4863 \n",
|
||
"L 3481 0 \n",
|
||
"L 2906 0 \n",
|
||
"L 2906 525 \n",
|
||
"Q 2725 213 2448 61 \n",
|
||
"Q 2172 -91 1784 -91 \n",
|
||
"Q 1150 -91 751 415 \n",
|
||
"Q 353 922 353 1747 \n",
|
||
"Q 353 2572 751 3078 \n",
|
||
"Q 1150 3584 1784 3584 \n",
|
||
"Q 2172 3584 2448 3432 \n",
|
||
"Q 2725 3281 2906 2969 \n",
|
||
"z\n",
|
||
"M 947 1747 \n",
|
||
"Q 947 1113 1208 752 \n",
|
||
"Q 1469 391 1925 391 \n",
|
||
"Q 2381 391 2643 752 \n",
|
||
"Q 2906 1113 2906 1747 \n",
|
||
"Q 2906 2381 2643 2742 \n",
|
||
"Q 2381 3103 1925 3103 \n",
|
||
"Q 1469 3103 1208 2742 \n",
|
||
"Q 947 2381 947 1747 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6f\" d=\"M 1959 3097 \n",
|
||
"Q 1497 3097 1228 2736 \n",
|
||
"Q 959 2375 959 1747 \n",
|
||
"Q 959 1119 1226 758 \n",
|
||
"Q 1494 397 1959 397 \n",
|
||
"Q 2419 397 2687 759 \n",
|
||
"Q 2956 1122 2956 1747 \n",
|
||
"Q 2956 2369 2687 2733 \n",
|
||
"Q 2419 3097 1959 3097 \n",
|
||
"z\n",
|
||
"M 1959 3584 \n",
|
||
"Q 2709 3584 3137 3096 \n",
|
||
"Q 3566 2609 3566 1747 \n",
|
||
"Q 3566 888 3137 398 \n",
|
||
"Q 2709 -91 1959 -91 \n",
|
||
"Q 1206 -91 779 398 \n",
|
||
"Q 353 888 353 1747 \n",
|
||
"Q 353 2609 779 3096 \n",
|
||
"Q 1206 3584 1959 3584 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-67\" d=\"M 2906 1791 \n",
|
||
"Q 2906 2416 2648 2759 \n",
|
||
"Q 2391 3103 1925 3103 \n",
|
||
"Q 1463 3103 1205 2759 \n",
|
||
"Q 947 2416 947 1791 \n",
|
||
"Q 947 1169 1205 825 \n",
|
||
"Q 1463 481 1925 481 \n",
|
||
"Q 2391 481 2648 825 \n",
|
||
"Q 2906 1169 2906 1791 \n",
|
||
"z\n",
|
||
"M 3481 434 \n",
|
||
"Q 3481 -459 3084 -895 \n",
|
||
"Q 2688 -1331 1869 -1331 \n",
|
||
"Q 1566 -1331 1297 -1286 \n",
|
||
"Q 1028 -1241 775 -1147 \n",
|
||
"L 775 -588 \n",
|
||
"Q 1028 -725 1275 -790 \n",
|
||
"Q 1522 -856 1778 -856 \n",
|
||
"Q 2344 -856 2625 -561 \n",
|
||
"Q 2906 -266 2906 331 \n",
|
||
"L 2906 616 \n",
|
||
"Q 2728 306 2450 153 \n",
|
||
"Q 2172 0 1784 0 \n",
|
||
"Q 1141 0 747 490 \n",
|
||
"Q 353 981 353 1791 \n",
|
||
"Q 353 2603 747 3093 \n",
|
||
"Q 1141 3584 1784 3584 \n",
|
||
"Q 2172 3584 2450 3431 \n",
|
||
"Q 2728 3278 2906 2969 \n",
|
||
"L 2906 3500 \n",
|
||
"L 3481 3500 \n",
|
||
"L 3481 434 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-3d\" d=\"M 678 2906 \n",
|
||
"L 4684 2906 \n",
|
||
"L 4684 2381 \n",
|
||
"L 678 2381 \n",
|
||
"L 678 2906 \n",
|
||
"z\n",
|
||
"M 678 1631 \n",
|
||
"L 4684 1631 \n",
|
||
"L 4684 1100 \n",
|
||
"L 678 1100 \n",
|
||
"L 678 1631 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-2e\" d=\"M 684 794 \n",
|
||
"L 1344 794 \n",
|
||
"L 1344 0 \n",
|
||
"L 684 0 \n",
|
||
"L 684 794 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-39\" d=\"M 703 97 \n",
|
||
"L 703 672 \n",
|
||
"Q 941 559 1184 500 \n",
|
||
"Q 1428 441 1663 441 \n",
|
||
"Q 2288 441 2617 861 \n",
|
||
"Q 2947 1281 2994 2138 \n",
|
||
"Q 2813 1869 2534 1725 \n",
|
||
"Q 2256 1581 1919 1581 \n",
|
||
"Q 1219 1581 811 2004 \n",
|
||
"Q 403 2428 403 3163 \n",
|
||
"Q 403 3881 828 4315 \n",
|
||
"Q 1253 4750 1959 4750 \n",
|
||
"Q 2769 4750 3195 4129 \n",
|
||
"Q 3622 3509 3622 2328 \n",
|
||
"Q 3622 1225 3098 567 \n",
|
||
"Q 2575 -91 1691 -91 \n",
|
||
"Q 1453 -91 1209 -44 \n",
|
||
"Q 966 3 703 97 \n",
|
||
"z\n",
|
||
"M 1959 2075 \n",
|
||
"Q 2384 2075 2632 2365 \n",
|
||
"Q 2881 2656 2881 3163 \n",
|
||
"Q 2881 3666 2632 3958 \n",
|
||
"Q 2384 4250 1959 4250 \n",
|
||
"Q 1534 4250 1286 3958 \n",
|
||
"Q 1038 3666 1038 3163 \n",
|
||
"Q 1038 2656 1286 2365 \n",
|
||
"Q 1534 2075 1959 2075 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-64\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"63.476562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-67\" x=\"124.658203\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"188.134766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"271.923828\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"335.546875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-39\" x=\"367.333984\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <g id=\"patch_10\">\n",
|
||
" <path d=\"M 108.520571 46.494378 \n",
|
||
"L 152.28729 46.494378 \n",
|
||
"L 152.28729 29.864065 \n",
|
||
"L 108.520571 29.864065 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #0000ff\"/>\n",
|
||
" </g>\n",
|
||
" <!-- cat=0.9 -->\n",
|
||
" <g style=\"fill: #ffffff\" transform=\"translate(112.480571 40.662659)scale(0.09 -0.09)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-63\" d=\"M 3122 3366 \n",
|
||
"L 3122 2828 \n",
|
||
"Q 2878 2963 2633 3030 \n",
|
||
"Q 2388 3097 2138 3097 \n",
|
||
"Q 1578 3097 1268 2742 \n",
|
||
"Q 959 2388 959 1747 \n",
|
||
"Q 959 1106 1268 751 \n",
|
||
"Q 1578 397 2138 397 \n",
|
||
"Q 2388 397 2633 464 \n",
|
||
"Q 2878 531 3122 666 \n",
|
||
"L 3122 134 \n",
|
||
"Q 2881 22 2623 -34 \n",
|
||
"Q 2366 -91 2075 -91 \n",
|
||
"Q 1284 -91 818 406 \n",
|
||
"Q 353 903 353 1747 \n",
|
||
"Q 353 2603 823 3093 \n",
|
||
"Q 1294 3584 2113 3584 \n",
|
||
"Q 2378 3584 2631 3529 \n",
|
||
"Q 2884 3475 3122 3366 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-61\" d=\"M 2194 1759 \n",
|
||
"Q 1497 1759 1228 1600 \n",
|
||
"Q 959 1441 959 1056 \n",
|
||
"Q 959 750 1161 570 \n",
|
||
"Q 1363 391 1709 391 \n",
|
||
"Q 2188 391 2477 730 \n",
|
||
"Q 2766 1069 2766 1631 \n",
|
||
"L 2766 1759 \n",
|
||
"L 2194 1759 \n",
|
||
"z\n",
|
||
"M 3341 1997 \n",
|
||
"L 3341 0 \n",
|
||
"L 2766 0 \n",
|
||
"L 2766 531 \n",
|
||
"Q 2569 213 2275 61 \n",
|
||
"Q 1981 -91 1556 -91 \n",
|
||
"Q 1019 -91 701 211 \n",
|
||
"Q 384 513 384 1019 \n",
|
||
"Q 384 1609 779 1909 \n",
|
||
"Q 1175 2209 1959 2209 \n",
|
||
"L 2766 2209 \n",
|
||
"L 2766 2266 \n",
|
||
"Q 2766 2663 2505 2880 \n",
|
||
"Q 2244 3097 1772 3097 \n",
|
||
"Q 1472 3097 1187 3025 \n",
|
||
"Q 903 2953 641 2809 \n",
|
||
"L 641 3341 \n",
|
||
"Q 956 3463 1253 3523 \n",
|
||
"Q 1550 3584 1831 3584 \n",
|
||
"Q 2591 3584 2966 3190 \n",
|
||
"Q 3341 2797 3341 1997 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-74\" d=\"M 1172 4494 \n",
|
||
"L 1172 3500 \n",
|
||
"L 2356 3500 \n",
|
||
"L 2356 3053 \n",
|
||
"L 1172 3053 \n",
|
||
"L 1172 1153 \n",
|
||
"Q 1172 725 1289 603 \n",
|
||
"Q 1406 481 1766 481 \n",
|
||
"L 2356 481 \n",
|
||
"L 2356 0 \n",
|
||
"L 1766 0 \n",
|
||
"Q 1100 0 847 248 \n",
|
||
"Q 594 497 594 1153 \n",
|
||
"L 594 3053 \n",
|
||
"L 172 3053 \n",
|
||
"L 172 3500 \n",
|
||
"L 594 3500 \n",
|
||
"L 594 4494 \n",
|
||
"L 1172 4494 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"54.980469\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\" x=\"116.259766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-3d\" x=\"155.46875\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"239.257812\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-2e\" x=\"302.880859\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-39\" x=\"334.667969\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"pe2aa6bfcac\">\n",
|
||
" <rect x=\"33.2875\" y=\"10.878096\" width=\"176.35508\" height=\"135.9\"/>\n",
|
||
" </clipPath>\n",
|
||
" </defs>\n",
|
||
"</svg>\n"
|
||
],
|
||
"text/plain": [
|
||
"<Figure size 252x180 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"fig = d2l.plt.imshow(img)\n",
|
||
"for i in output[0].detach().numpy():\n",
|
||
" if i[0] == -1:\n",
|
||
" continue\n",
|
||
" label = ('dog=', 'cat=')[int(i[0])] + str(i[1])\n",
|
||
" show_bboxes(fig.axes, [torch.tensor(i[2:]) * bbox_scale], label)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "222c6994",
|
||
"metadata": {
|
||
"origin_pos": 66
|
||
},
|
||
"source": [
|
||
"实践中，在执行非极大值抑制前，我们甚至可以将置信度较低的预测边界框移除，从而减少此算法中的计算量。\n",
|
||
"我们也可以对非极大值抑制的输出结果进行后处理。例如，只保留置信度更高的结果作为最终输出。\n",
|
||
"\n",
|
||
"## 小结\n",
|
||
"\n",
|
||
"* 我们以图像的每个像素为中心生成不同形状的锚框。\n",
|
||
"* 交并比（IoU）也被称为杰卡德系数，用于衡量两个边界框的相似性。它是相交面积与相并面积的比率。\n",
|
||
"* 在训练集中，我们需要给每个锚框两种类型的标签。一个是与锚框中目标检测的类别，另一个是锚框真实相对于边界框的偏移量。\n",
|
||
"* 预测期间可以使用非极大值抑制（NMS）来移除类似的预测边界框，从而简化输出。\n",
|
||
"\n",
|
||
"## 练习\n",
|
||
"\n",
|
||
"1. 在`multibox_prior`函数中更改`sizes`和`ratios`的值。生成的锚框有什么变化？\n",
|
||
"1. 构建并可视化两个IoU为0.5的边界框。它们是怎样重叠的？\n",
|
||
"1. 在 :numref:`subsec_labeling-anchor-boxes`和 :numref:`subsec_predicting-bounding-boxes-nms`中修改变量`anchors`，结果如何变化？\n",
|
||
"1. 非极大值抑制是一种贪心算法，它通过*移除*来抑制预测的边界框。是否存在一种可能，被移除的一些框实际上是有用的？如何修改这个算法来柔和地抑制？可以参考Soft-NMS :cite:`Bodla.Singh.Chellappa.ea.2017`。\n",
|
||
"1. 如果非手动，非最大限度的抑制可以被学习吗？\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e48b2d07",
|
||
"metadata": {
|
||
"origin_pos": 68,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"source": [
|
||
"[Discussions](https://discuss.d2l.ai/t/2946)\n"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"language_info": {
|
||
"name": "python"
|
||
},
|
||
"required_libs": []
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
} |