2781 lines
97 KiB
Plaintext
2781 lines
97 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "06c5b1d6",
|
||
"metadata": {
|
||
"origin_pos": 0
|
||
},
|
||
"source": [
|
||
"# 实战Kaggle比赛:狗的品种识别(ImageNet Dogs)\n",
|
||
"\n",
|
||
"本节我们将在Kaggle上实战狗品种识别问题。\n",
|
||
"本次(**比赛网址是https://www.kaggle.com/c/dog-breed-identification**)。\n",
|
||
" :numref:`fig_kaggle_dog`显示了鉴定比赛网页上的信息。\n",
|
||
"需要一个Kaggle账户才能提交结果。\n",
|
||
"\n",
|
||
"在这场比赛中,我们将识别120类不同品种的狗。\n",
|
||
"这个数据集实际上是著名的ImageNet的数据集子集。与 :numref:`sec_kaggle_cifar10`中CIFAR-10数据集中的图像不同,\n",
|
||
"ImageNet数据集中的图像更高更宽,且尺寸不一。\n",
|
||
"\n",
|
||
"\n",
|
||
":width:`400px`\n",
|
||
":label:`fig_kaggle_dog`\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "b6e1a2a2",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:14.555794Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:14.555246Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:16.563976Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:16.563095Z"
|
||
},
|
||
"origin_pos": 2,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os\n",
|
||
"import torch\n",
|
||
"import torchvision\n",
|
||
"from torch import nn\n",
|
||
"from d2l import torch as d2l"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "13880384",
|
||
"metadata": {
|
||
"origin_pos": 4
|
||
},
|
||
"source": [
|
||
"## 获取和整理数据集\n",
|
||
"\n",
|
||
"比赛数据集分为训练集和测试集,分别包含RGB(彩色)通道的10222张、10357张JPEG图像。\n",
|
||
"在训练数据集中,有120种犬类,如拉布拉多、贵宾、腊肠、萨摩耶、哈士奇、吉娃娃和约克夏等。\n",
|
||
"\n",
|
||
"### 下载数据集\n",
|
||
"\n",
|
||
"登录Kaggle后,可以点击 :numref:`fig_kaggle_dog`中显示的竞争网页上的“数据”选项卡,然后点击“全部下载”按钮下载数据集。在`../data`中解压下载的文件后,将在以下路径中找到整个数据集:\n",
|
||
"\n",
|
||
"* ../data/dog-breed-identification/labels.csv\n",
|
||
"* ../data/dog-breed-identification/sample_submission.csv\n",
|
||
"* ../data/dog-breed-identification/train\n",
|
||
"* ../data/dog-breed-identification/test\n",
|
||
"\n",
|
||
"\n",
|
||
"上述结构与 :numref:`sec_kaggle_cifar10`的CIFAR-10类似,其中文件夹`train/`和`test/`分别包含训练和测试狗图像,`labels.csv`包含训练图像的标签。\n",
|
||
"\n",
|
||
"同样,为了便于入门,[**我们提供完整数据集的小规模样本**]:`train_valid_test_tiny.zip`。\n",
|
||
"如果要在Kaggle比赛中使用完整的数据集,则需要将下面的`demo`变量更改为`False`。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "9ecb1309",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:16.567802Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:16.567412Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.348683Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.347865Z"
|
||
},
|
||
"origin_pos": 5,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Downloading ../data/kaggle_dog_tiny.zip from http://d2l-data.s3-accelerate.amazonaws.com/kaggle_dog_tiny.zip...\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#@save\n",
|
||
"d2l.DATA_HUB['dog_tiny'] = (d2l.DATA_URL + 'kaggle_dog_tiny.zip',\n",
|
||
" '0cb91d09b814ecdc07b50f31f8dcad3e81d6a86d')\n",
|
||
"\n",
|
||
"# 如果使用Kaggle比赛的完整数据集,请将下面的变量更改为False\n",
|
||
"demo = True\n",
|
||
"if demo:\n",
|
||
" data_dir = d2l.download_extract('dog_tiny')\n",
|
||
"else:\n",
|
||
" data_dir = os.path.join('..', 'data', 'dog-breed-identification')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "be63041f",
|
||
"metadata": {
|
||
"origin_pos": 6
|
||
},
|
||
"source": [
|
||
"### [**整理数据集**]\n",
|
||
"\n",
|
||
"我们可以像 :numref:`sec_kaggle_cifar10`中所做的那样整理数据集,即从原始训练集中拆分验证集,然后将图像移动到按标签分组的子文件夹中。\n",
|
||
"\n",
|
||
"下面的`reorg_dog_data`函数读取训练数据标签、拆分验证集并整理训练集。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "3b420853",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.352573Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.352101Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.685237Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.683473Z"
|
||
},
|
||
"origin_pos": 7,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"def reorg_dog_data(data_dir, valid_ratio):\n",
|
||
" labels = d2l.read_csv_labels(os.path.join(data_dir, 'labels.csv'))\n",
|
||
" d2l.reorg_train_valid(data_dir, labels, valid_ratio)\n",
|
||
" d2l.reorg_test(data_dir)\n",
|
||
"\n",
|
||
"\n",
|
||
"batch_size = 32 if demo else 128\n",
|
||
"valid_ratio = 0.1\n",
|
||
"reorg_dog_data(data_dir, valid_ratio)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7e0ef8e3",
|
||
"metadata": {
|
||
"origin_pos": 8
|
||
},
|
||
"source": [
|
||
"## [**图像增广**]\n",
|
||
"\n",
|
||
"回想一下,这个狗品种数据集是ImageNet数据集的子集,其图像大于 :numref:`sec_kaggle_cifar10`中CIFAR-10数据集的图像。\n",
|
||
"下面我们看一下如何在相对较大的图像上使用图像增广。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "7dd17ade",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.691169Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.690438Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.698895Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.697847Z"
|
||
},
|
||
"origin_pos": 10,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"transform_train = torchvision.transforms.Compose([\n",
|
||
" # 随机裁剪图像,所得图像为原始面积的0.08~1之间,高宽比在3/4和4/3之间。\n",
|
||
" # 然后,缩放图像以创建224x224的新图像\n",
|
||
" torchvision.transforms.RandomResizedCrop(224, scale=(0.08, 1.0),\n",
|
||
" ratio=(3.0/4.0, 4.0/3.0)),\n",
|
||
" torchvision.transforms.RandomHorizontalFlip(),\n",
|
||
" # 随机更改亮度,对比度和饱和度\n",
|
||
" torchvision.transforms.ColorJitter(brightness=0.4,\n",
|
||
" contrast=0.4,\n",
|
||
" saturation=0.4),\n",
|
||
" # 添加随机噪声\n",
|
||
" torchvision.transforms.ToTensor(),\n",
|
||
" # 标准化图像的每个通道\n",
|
||
" torchvision.transforms.Normalize([0.485, 0.456, 0.406],\n",
|
||
" [0.229, 0.224, 0.225])])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "f1657506",
|
||
"metadata": {
|
||
"origin_pos": 12
|
||
},
|
||
"source": [
|
||
"测试时,我们只使用确定性的图像预处理操作。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "0b467084",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.704258Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.703547Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.710398Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.709360Z"
|
||
},
|
||
"origin_pos": 14,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"transform_test = torchvision.transforms.Compose([\n",
|
||
" torchvision.transforms.Resize(256),\n",
|
||
" # 从图像中心裁切224x224大小的图片\n",
|
||
" torchvision.transforms.CenterCrop(224),\n",
|
||
" torchvision.transforms.ToTensor(),\n",
|
||
" torchvision.transforms.Normalize([0.485, 0.456, 0.406],\n",
|
||
" [0.229, 0.224, 0.225])])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9c375dab",
|
||
"metadata": {
|
||
"origin_pos": 16
|
||
},
|
||
"source": [
|
||
"## [**读取数据集**]\n",
|
||
"\n",
|
||
"与 :numref:`sec_kaggle_cifar10`一样,我们可以读取整理后的含原始图像文件的数据集。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "bc8d11c0",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.715826Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.715055Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.750393Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.749301Z"
|
||
},
|
||
"origin_pos": 18,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"train_ds, train_valid_ds = [torchvision.datasets.ImageFolder(\n",
|
||
" os.path.join(data_dir, 'train_valid_test', folder),\n",
|
||
" transform=transform_train) for folder in ['train', 'train_valid']]\n",
|
||
"\n",
|
||
"valid_ds, test_ds = [torchvision.datasets.ImageFolder(\n",
|
||
" os.path.join(data_dir, 'train_valid_test', folder),\n",
|
||
" transform=transform_test) for folder in ['valid', 'test']]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "cb0b1b9e",
|
||
"metadata": {
|
||
"origin_pos": 20
|
||
},
|
||
"source": [
|
||
"下面我们创建数据加载器实例的方式与 :numref:`sec_kaggle_cifar10`相同。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "8ef84d02",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.756485Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.755671Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.764122Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.762916Z"
|
||
},
|
||
"origin_pos": 22,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"train_iter, train_valid_iter = [torch.utils.data.DataLoader(\n",
|
||
" dataset, batch_size, shuffle=True, drop_last=True)\n",
|
||
" for dataset in (train_ds, train_valid_ds)]\n",
|
||
"\n",
|
||
"valid_iter = torch.utils.data.DataLoader(valid_ds, batch_size, shuffle=False,\n",
|
||
" drop_last=True)\n",
|
||
"\n",
|
||
"test_iter = torch.utils.data.DataLoader(test_ds, batch_size, shuffle=False,\n",
|
||
" drop_last=False)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "78c1647e",
|
||
"metadata": {
|
||
"origin_pos": 24
|
||
},
|
||
"source": [
|
||
"## [**微调预训练模型**]\n",
|
||
"\n",
|
||
"同样,本次比赛的数据集是ImageNet数据集的子集。\n",
|
||
"因此,我们可以使用 :numref:`sec_fine_tuning`中讨论的方法在完整ImageNet数据集上选择预训练的模型,然后使用该模型提取图像特征,以便将其输入到定制的小规模输出网络中。\n",
|
||
"深度学习框架的高级API提供了在ImageNet数据集上预训练的各种模型。\n",
|
||
"在这里,我们选择预训练的ResNet-34模型,我们只需重复使用此模型的输出层(即提取的特征)的输入。\n",
|
||
"然后,我们可以用一个可以训练的小型自定义输出网络替换原始输出层,例如堆叠两个完全连接的图层。\n",
|
||
"与 :numref:`sec_fine_tuning`中的实验不同,以下内容不重新训练用于特征提取的预训练模型,这节省了梯度下降的时间和内存空间。\n",
|
||
"\n",
|
||
"回想一下,我们使用三个RGB通道的均值和标准差来对完整的ImageNet数据集进行图像标准化。\n",
|
||
"事实上,这也符合ImageNet上预训练模型的标准化操作。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "1fd0cd74",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.769780Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.768697Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.777622Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.776303Z"
|
||
},
|
||
"origin_pos": 26,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"def get_net(devices):\n",
|
||
" finetune_net = nn.Sequential()\n",
|
||
" finetune_net.features = torchvision.models.resnet34(pretrained=True)\n",
|
||
" # 定义一个新的输出网络,共有120个输出类别\n",
|
||
" finetune_net.output_new = nn.Sequential(nn.Linear(1000, 256),\n",
|
||
" nn.ReLU(),\n",
|
||
" nn.Linear(256, 120))\n",
|
||
" # 将模型参数分配给用于计算的CPU或GPU\n",
|
||
" finetune_net = finetune_net.to(devices[0])\n",
|
||
" # 冻结参数\n",
|
||
" for param in finetune_net.features.parameters():\n",
|
||
" param.requires_grad = False\n",
|
||
" return finetune_net"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "597655d7",
|
||
"metadata": {
|
||
"origin_pos": 28
|
||
},
|
||
"source": [
|
||
"在[**计算损失**]之前,我们首先获取预训练模型的输出层的输入,即提取的特征。\n",
|
||
"然后我们使用此特征作为我们小型自定义输出网络的输入来计算损失。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "d6936a15",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.783286Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.782296Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.791061Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.789830Z"
|
||
},
|
||
"origin_pos": 30,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"loss = nn.CrossEntropyLoss(reduction='none')\n",
|
||
"\n",
|
||
"def evaluate_loss(data_iter, net, devices):\n",
|
||
" l_sum, n = 0.0, 0\n",
|
||
" for features, labels in data_iter:\n",
|
||
" features, labels = features.to(devices[0]), labels.to(devices[0])\n",
|
||
" outputs = net(features)\n",
|
||
" l = loss(outputs, labels)\n",
|
||
" l_sum += l.sum()\n",
|
||
" n += labels.numel()\n",
|
||
" return (l_sum / n).to('cpu')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "26ee460a",
|
||
"metadata": {
|
||
"origin_pos": 32
|
||
},
|
||
"source": [
|
||
"## 定义[**训练函数**]\n",
|
||
"\n",
|
||
"我们将根据模型在验证集上的表现选择模型并调整超参数。\n",
|
||
"模型训练函数`train`只迭代小型自定义输出网络的参数。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "4a196c68",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.796668Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.795696Z",
|
||
"iopub.status.idle": "2023-08-18T06:58:17.813822Z",
|
||
"shell.execute_reply": "2023-08-18T06:58:17.812372Z"
|
||
},
|
||
"origin_pos": 34,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"def train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,\n",
|
||
" lr_decay):\n",
|
||
" # 只训练小型自定义输出网络\n",
|
||
" net = nn.DataParallel(net, device_ids=devices).to(devices[0])\n",
|
||
" trainer = torch.optim.SGD((param for param in net.parameters()\n",
|
||
" if param.requires_grad), lr=lr,\n",
|
||
" momentum=0.9, weight_decay=wd)\n",
|
||
" scheduler = torch.optim.lr_scheduler.StepLR(trainer, lr_period, lr_decay)\n",
|
||
" num_batches, timer = len(train_iter), d2l.Timer()\n",
|
||
" legend = ['train loss']\n",
|
||
" if valid_iter is not None:\n",
|
||
" legend.append('valid loss')\n",
|
||
" animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],\n",
|
||
" legend=legend)\n",
|
||
" for epoch in range(num_epochs):\n",
|
||
" metric = d2l.Accumulator(2)\n",
|
||
" for i, (features, labels) in enumerate(train_iter):\n",
|
||
" timer.start()\n",
|
||
" features, labels = features.to(devices[0]), labels.to(devices[0])\n",
|
||
" trainer.zero_grad()\n",
|
||
" output = net(features)\n",
|
||
" l = loss(output, labels).sum()\n",
|
||
" l.backward()\n",
|
||
" trainer.step()\n",
|
||
" metric.add(l, labels.shape[0])\n",
|
||
" timer.stop()\n",
|
||
" if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:\n",
|
||
" animator.add(epoch + (i + 1) / num_batches,\n",
|
||
" (metric[0] / metric[1], None))\n",
|
||
" measures = f'train loss {metric[0] / metric[1]:.3f}'\n",
|
||
" if valid_iter is not None:\n",
|
||
" valid_loss = evaluate_loss(valid_iter, net, devices)\n",
|
||
" animator.add(epoch + 1, (None, valid_loss.detach().cpu()))\n",
|
||
" scheduler.step()\n",
|
||
" if valid_iter is not None:\n",
|
||
" measures += f', valid loss {valid_loss:.3f}'\n",
|
||
" print(measures + f'\\n{metric[1] * num_epochs / timer.sum():.1f}'\n",
|
||
" f' examples/sec on {str(devices)}')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "13bb871a",
|
||
"metadata": {
|
||
"origin_pos": 36
|
||
},
|
||
"source": [
|
||
"## [**训练和验证模型**]\n",
|
||
"\n",
|
||
"现在我们可以训练和验证模型了,以下超参数都是可调的。\n",
|
||
"例如,我们可以增加迭代轮数。\n",
|
||
"另外,由于`lr_period`和`lr_decay`分别设置为2和0.9,\n",
|
||
"因此优化算法的学习速率将在每2个迭代后乘以0.9。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "d407d036",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T06:58:17.819464Z",
|
||
"iopub.status.busy": "2023-08-18T06:58:17.818676Z",
|
||
"iopub.status.idle": "2023-08-18T07:00:28.078597Z",
|
||
"shell.execute_reply": "2023-08-18T07:00:28.077772Z"
|
||
},
|
||
"origin_pos": 38,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"train loss 1.237, valid loss 1.503\n",
|
||
"442.6 examples/sec on [device(type='cuda', index=0), device(type='cuda', index=1)]\n"
|
||
]
|
||
},
|
||
{
|
||
"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=\"229.425pt\" height=\"182.167893pt\" viewBox=\"0 0 229.425 182.167893\" 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>2023-08-18T07:00:28.024498</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 0 182.167893 \n",
|
||
"L 229.425 182.167893 \n",
|
||
"L 229.425 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 182.167893 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 20.5625 144.611643 \n",
|
||
"L 215.8625 144.611643 \n",
|
||
"L 215.8625 8.711643 \n",
|
||
"L 20.5625 8.711643 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <path d=\"M 42.2625 144.611643 \n",
|
||
"L 42.2625 8.711643 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"mb1083cb384\" 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=\"#mb1083cb384\" x=\"42.2625\" y=\"144.611643\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 2 -->\n",
|
||
" <g transform=\"translate(39.08125 159.21008)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <path d=\"M 85.6625 144.611643 \n",
|
||
"L 85.6625 8.711643 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1083cb384\" x=\"85.6625\" y=\"144.611643\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 4 -->\n",
|
||
" <g transform=\"translate(82.48125 159.21008)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <path d=\"M 129.0625 144.611643 \n",
|
||
"L 129.0625 8.711643 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1083cb384\" x=\"129.0625\" y=\"144.611643\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 6 -->\n",
|
||
" <g transform=\"translate(125.88125 159.21008)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <path d=\"M 172.4625 144.611643 \n",
|
||
"L 172.4625 8.711643 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1083cb384\" x=\"172.4625\" y=\"144.611643\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 8 -->\n",
|
||
" <g transform=\"translate(169.28125 159.21008)scale(0.1 -0.1)\">\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-38\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <path d=\"M 215.8625 144.611643 \n",
|
||
"L 215.8625 8.711643 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mb1083cb384\" x=\"215.8625\" y=\"144.611643\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- 10 -->\n",
|
||
" <g transform=\"translate(209.5 159.21008)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",
|
||
" <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-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- epoch -->\n",
|
||
" <g transform=\"translate(102.984375 172.888205)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-65\" d=\"M 3597 1894 \n",
|
||
"L 3597 1613 \n",
|
||
"L 953 1613 \n",
|
||
"Q 991 1019 1311 708 \n",
|
||
"Q 1631 397 2203 397 \n",
|
||
"Q 2534 397 2845 478 \n",
|
||
"Q 3156 559 3463 722 \n",
|
||
"L 3463 178 \n",
|
||
"Q 3153 47 2828 -22 \n",
|
||
"Q 2503 -91 2169 -91 \n",
|
||
"Q 1331 -91 842 396 \n",
|
||
"Q 353 884 353 1716 \n",
|
||
"Q 353 2575 817 3079 \n",
|
||
"Q 1281 3584 2069 3584 \n",
|
||
"Q 2775 3584 3186 3129 \n",
|
||
"Q 3597 2675 3597 1894 \n",
|
||
"z\n",
|
||
"M 3022 2063 \n",
|
||
"Q 3016 2534 2758 2815 \n",
|
||
"Q 2500 3097 2075 3097 \n",
|
||
"Q 1594 3097 1305 2825 \n",
|
||
"Q 1016 2553 972 2059 \n",
|
||
"L 3022 2063 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-70\" d=\"M 1159 525 \n",
|
||
"L 1159 -1331 \n",
|
||
"L 581 -1331 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2969 \n",
|
||
"Q 1341 3281 1617 3432 \n",
|
||
"Q 1894 3584 2278 3584 \n",
|
||
"Q 2916 3584 3314 3078 \n",
|
||
"Q 3713 2572 3713 1747 \n",
|
||
"Q 3713 922 3314 415 \n",
|
||
"Q 2916 -91 2278 -91 \n",
|
||
"Q 1894 -91 1617 61 \n",
|
||
"Q 1341 213 1159 525 \n",
|
||
"z\n",
|
||
"M 3116 1747 \n",
|
||
"Q 3116 2381 2855 2742 \n",
|
||
"Q 2594 3103 2138 3103 \n",
|
||
"Q 1681 3103 1420 2742 \n",
|
||
"Q 1159 2381 1159 1747 \n",
|
||
"Q 1159 1113 1420 752 \n",
|
||
"Q 1681 391 2138 391 \n",
|
||
"Q 2594 391 2855 752 \n",
|
||
"Q 3116 1113 3116 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-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-68\" d=\"M 3513 2113 \n",
|
||
"L 3513 0 \n",
|
||
"L 2938 0 \n",
|
||
"L 2938 2094 \n",
|
||
"Q 2938 2591 2744 2837 \n",
|
||
"Q 2550 3084 2163 3084 \n",
|
||
"Q 1697 3084 1428 2787 \n",
|
||
"Q 1159 2491 1159 1978 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 4863 \n",
|
||
"L 1159 4863 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1366 3272 1645 3428 \n",
|
||
"Q 1925 3584 2291 3584 \n",
|
||
"Q 2894 3584 3203 3211 \n",
|
||
"Q 3513 2838 3513 2113 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-70\" x=\"61.523438\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"125\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\" x=\"186.181641\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-68\" x=\"241.162109\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_11\">\n",
|
||
" <path d=\"M 20.5625 111.370052 \n",
|
||
"L 215.8625 111.370052 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_12\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m5ce118da3a\" 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=\"#m5ce118da3a\" x=\"20.5625\" y=\"111.370052\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 2 -->\n",
|
||
" <g transform=\"translate(7.2 115.169271)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_13\">\n",
|
||
" <path d=\"M 20.5625 77.913107 \n",
|
||
"L 215.8625 77.913107 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_14\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m5ce118da3a\" x=\"20.5625\" y=\"77.913107\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 3 -->\n",
|
||
" <g transform=\"translate(7.2 81.712326)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_15\">\n",
|
||
" <path d=\"M 20.5625 44.456163 \n",
|
||
"L 215.8625 44.456163 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_16\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m5ce118da3a\" x=\"20.5625\" y=\"44.456163\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 4 -->\n",
|
||
" <g transform=\"translate(7.2 48.255382)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_17\">\n",
|
||
" <path d=\"M 20.5625 10.999219 \n",
|
||
"L 215.8625 10.999219 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_18\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m5ce118da3a\" x=\"20.5625\" y=\"10.999219\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 5 -->\n",
|
||
" <g transform=\"translate(7.2 14.798437)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_19\">\n",
|
||
" <path d=\"M 2.881019 14.992454 \n",
|
||
"L 6.899537 14.888915 \n",
|
||
"L 10.918056 17.173229 \n",
|
||
"L 14.936574 18.44277 \n",
|
||
"L 18.955093 20.077282 \n",
|
||
"L 20.5625 21.257508 \n",
|
||
"L 24.581019 42.222744 \n",
|
||
"L 28.599537 43.69615 \n",
|
||
"L 32.618056 46.96471 \n",
|
||
"L 36.636574 48.867303 \n",
|
||
"L 40.655093 51.687609 \n",
|
||
"L 42.2625 52.059249 \n",
|
||
"L 46.281019 75.237274 \n",
|
||
"L 50.299537 75.083878 \n",
|
||
"L 54.318056 75.090395 \n",
|
||
"L 58.336574 77.338915 \n",
|
||
"L 62.355093 77.638741 \n",
|
||
"L 63.9625 78.265228 \n",
|
||
"L 67.981019 93.411063 \n",
|
||
"L 71.999537 93.425359 \n",
|
||
"L 76.018056 94.454799 \n",
|
||
"L 80.036574 95.731629 \n",
|
||
"L 84.055093 96.609994 \n",
|
||
"L 85.6625 97.439972 \n",
|
||
"L 89.681019 116.048662 \n",
|
||
"L 93.699537 116.976946 \n",
|
||
"L 97.718056 113.580837 \n",
|
||
"L 101.736574 113.175423 \n",
|
||
"L 105.755093 112.776914 \n",
|
||
"L 107.3625 113.355488 \n",
|
||
"L 111.381019 122.606382 \n",
|
||
"L 115.399537 118.808008 \n",
|
||
"L 119.418056 118.468609 \n",
|
||
"L 123.436574 117.254135 \n",
|
||
"L 127.455093 119.382993 \n",
|
||
"L 129.0625 119.14437 \n",
|
||
"L 133.081019 127.664548 \n",
|
||
"L 137.099537 128.38983 \n",
|
||
"L 141.118056 128.268785 \n",
|
||
"L 145.136574 127.441208 \n",
|
||
"L 149.155093 127.673155 \n",
|
||
"L 150.7625 128.080992 \n",
|
||
"L 154.781019 126.501292 \n",
|
||
"L 158.799537 131.368937 \n",
|
||
"L 162.818056 131.367755 \n",
|
||
"L 166.836574 131.964252 \n",
|
||
"L 170.855093 131.563931 \n",
|
||
"L 172.4625 131.091281 \n",
|
||
"L 176.481019 133.913191 \n",
|
||
"L 180.499537 138.159565 \n",
|
||
"L 184.518056 135.82813 \n",
|
||
"L 188.536574 134.805587 \n",
|
||
"L 192.555093 135.16447 \n",
|
||
"L 194.1625 134.680643 \n",
|
||
"L 198.181019 137.903042 \n",
|
||
"L 202.199537 136.143225 \n",
|
||
"L 206.218056 138.43437 \n",
|
||
"L 210.236574 138.069581 \n",
|
||
"L 214.255093 137.309966 \n",
|
||
"L 215.8625 136.886404 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_20\">\n",
|
||
" <path d=\"M 20.5625 35.271533 \n",
|
||
"L 42.2625 63.41153 \n",
|
||
"L 63.9625 86.807718 \n",
|
||
"L 85.6625 102.824137 \n",
|
||
"L 107.3625 112.982856 \n",
|
||
"L 129.0625 119.345748 \n",
|
||
"L 150.7625 122.765827 \n",
|
||
"L 172.4625 124.957684 \n",
|
||
"L 194.1625 127.326669 \n",
|
||
"L 215.8625 128.006967 \n",
|
||
"\" clip-path=\"url(#p481b93a6a0)\" style=\"fill: none; stroke-dasharray: 5.55,2.4; stroke-dashoffset: 0; stroke: #bf00bf; stroke-width: 1.5\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 20.5625 144.611643 \n",
|
||
"L 20.5625 8.711643 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 215.8625 144.611643 \n",
|
||
"L 215.8625 8.711643 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 20.5625 144.611643 \n",
|
||
"L 215.8625 144.611643 \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 20.5625 8.711643 \n",
|
||
"L 215.8625 8.711643 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"legend_1\">\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 130.417188 46.067893 \n",
|
||
"L 208.8625 46.067893 \n",
|
||
"Q 210.8625 46.067893 210.8625 44.067893 \n",
|
||
"L 210.8625 15.711643 \n",
|
||
"Q 210.8625 13.711643 208.8625 13.711643 \n",
|
||
"L 130.417188 13.711643 \n",
|
||
"Q 128.417188 13.711643 128.417188 15.711643 \n",
|
||
"L 128.417188 44.067893 \n",
|
||
"Q 128.417188 46.067893 130.417188 46.067893 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff; opacity: 0.8; stroke: #cccccc; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_21\">\n",
|
||
" <path d=\"M 132.417188 21.81008 \n",
|
||
"L 142.417188 21.81008 \n",
|
||
"L 152.417188 21.81008 \n",
|
||
"\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <!-- train loss -->\n",
|
||
" <g transform=\"translate(160.417188 25.31008)scale(0.1 -0.1)\">\n",
|
||
" <defs>\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",
|
||
" <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",
|
||
" <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-69\" d=\"M 603 3500 \n",
|
||
"L 1178 3500 \n",
|
||
"L 1178 0 \n",
|
||
"L 603 0 \n",
|
||
"L 603 3500 \n",
|
||
"z\n",
|
||
"M 603 4863 \n",
|
||
"L 1178 4863 \n",
|
||
"L 1178 4134 \n",
|
||
"L 603 4134 \n",
|
||
"L 603 4863 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6e\" d=\"M 3513 2113 \n",
|
||
"L 3513 0 \n",
|
||
"L 2938 0 \n",
|
||
"L 2938 2094 \n",
|
||
"Q 2938 2591 2744 2837 \n",
|
||
"Q 2550 3084 2163 3084 \n",
|
||
"Q 1697 3084 1428 2787 \n",
|
||
"Q 1159 2491 1159 1978 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1366 3272 1645 3428 \n",
|
||
"Q 1925 3584 2291 3584 \n",
|
||
"Q 2894 3584 3203 3211 \n",
|
||
"Q 3513 2838 3513 2113 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6c\" d=\"M 603 4863 \n",
|
||
"L 1178 4863 \n",
|
||
"L 1178 0 \n",
|
||
"L 603 0 \n",
|
||
"L 603 4863 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\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",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"39.208984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"80.322266\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-69\" x=\"141.601562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6e\" x=\"169.384766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"232.763672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6c\" x=\"264.550781\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"292.333984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"353.515625\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"405.615234\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_22\">\n",
|
||
" <path d=\"M 132.417188 36.488205 \n",
|
||
"L 142.417188 36.488205 \n",
|
||
"L 152.417188 36.488205 \n",
|
||
"\" style=\"fill: none; stroke-dasharray: 5.55,2.4; stroke-dashoffset: 0; stroke: #bf00bf; stroke-width: 1.5\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <!-- valid loss -->\n",
|
||
" <g transform=\"translate(160.417188 39.988205)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-76\" d=\"M 191 3500 \n",
|
||
"L 800 3500 \n",
|
||
"L 1894 563 \n",
|
||
"L 2988 3500 \n",
|
||
"L 3597 3500 \n",
|
||
"L 2284 0 \n",
|
||
"L 1503 0 \n",
|
||
"L 191 3500 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\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",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-76\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"59.179688\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6c\" x=\"120.458984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-69\" x=\"148.242188\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-64\" x=\"176.025391\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"239.501953\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6c\" x=\"271.289062\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"299.072266\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"360.253906\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"412.353516\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"p481b93a6a0\">\n",
|
||
" <rect x=\"20.5625\" y=\"8.711643\" width=\"195.3\" 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": [
|
||
"devices, num_epochs, lr, wd = d2l.try_all_gpus(), 10, 1e-4, 1e-4\n",
|
||
"lr_period, lr_decay, net = 2, 0.9, get_net(devices)\n",
|
||
"train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,\n",
|
||
" lr_decay)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b7055ca9",
|
||
"metadata": {
|
||
"origin_pos": 40
|
||
},
|
||
"source": [
|
||
"## [**对测试集分类**]并在Kaggle提交结果\n",
|
||
"\n",
|
||
"与 :numref:`sec_kaggle_cifar10`中的最后一步类似,最终所有标记的数据(包括验证集)都用于训练模型和对测试集进行分类。\n",
|
||
"我们将使用训练好的自定义输出网络进行分类。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"id": "747e6641",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:00:28.083877Z",
|
||
"iopub.status.busy": "2023-08-18T07:00:28.083216Z",
|
||
"iopub.status.idle": "2023-08-18T07:02:07.445306Z",
|
||
"shell.execute_reply": "2023-08-18T07:02:07.444197Z"
|
||
},
|
||
"origin_pos": 42,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"train loss 1.273\n",
|
||
"710.0 examples/sec on [device(type='cuda', index=0), device(type='cuda', index=1)]\n"
|
||
]
|
||
},
|
||
{
|
||
"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=\"229.425pt\" height=\"183.120283pt\" viewBox=\"0 0 229.425 183.120283\" 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>2023-08-18T07:02:07.394559</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 0 183.120283 \n",
|
||
"L 229.425 183.120283 \n",
|
||
"L 229.425 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 183.120283 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 20.5625 145.564033 \n",
|
||
"L 215.8625 145.564033 \n",
|
||
"L 215.8625 9.664033 \n",
|
||
"L 20.5625 9.664033 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <path d=\"M 42.2625 145.564033 \n",
|
||
"L 42.2625 9.664033 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m359173fe30\" 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=\"#m359173fe30\" x=\"42.2625\" y=\"145.564033\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 2 -->\n",
|
||
" <g transform=\"translate(39.08125 160.16247)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <path d=\"M 85.6625 145.564033 \n",
|
||
"L 85.6625 9.664033 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m359173fe30\" x=\"85.6625\" y=\"145.564033\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 4 -->\n",
|
||
" <g transform=\"translate(82.48125 160.16247)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <path d=\"M 129.0625 145.564033 \n",
|
||
"L 129.0625 9.664033 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m359173fe30\" x=\"129.0625\" y=\"145.564033\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 6 -->\n",
|
||
" <g transform=\"translate(125.88125 160.16247)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <path d=\"M 172.4625 145.564033 \n",
|
||
"L 172.4625 9.664033 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m359173fe30\" x=\"172.4625\" y=\"145.564033\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 8 -->\n",
|
||
" <g transform=\"translate(169.28125 160.16247)scale(0.1 -0.1)\">\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-38\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <path d=\"M 215.8625 145.564033 \n",
|
||
"L 215.8625 9.664033 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m359173fe30\" x=\"215.8625\" y=\"145.564033\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- 10 -->\n",
|
||
" <g transform=\"translate(209.5 160.16247)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",
|
||
" <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-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- epoch -->\n",
|
||
" <g transform=\"translate(102.984375 173.840595)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-65\" d=\"M 3597 1894 \n",
|
||
"L 3597 1613 \n",
|
||
"L 953 1613 \n",
|
||
"Q 991 1019 1311 708 \n",
|
||
"Q 1631 397 2203 397 \n",
|
||
"Q 2534 397 2845 478 \n",
|
||
"Q 3156 559 3463 722 \n",
|
||
"L 3463 178 \n",
|
||
"Q 3153 47 2828 -22 \n",
|
||
"Q 2503 -91 2169 -91 \n",
|
||
"Q 1331 -91 842 396 \n",
|
||
"Q 353 884 353 1716 \n",
|
||
"Q 353 2575 817 3079 \n",
|
||
"Q 1281 3584 2069 3584 \n",
|
||
"Q 2775 3584 3186 3129 \n",
|
||
"Q 3597 2675 3597 1894 \n",
|
||
"z\n",
|
||
"M 3022 2063 \n",
|
||
"Q 3016 2534 2758 2815 \n",
|
||
"Q 2500 3097 2075 3097 \n",
|
||
"Q 1594 3097 1305 2825 \n",
|
||
"Q 1016 2553 972 2059 \n",
|
||
"L 3022 2063 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-70\" d=\"M 1159 525 \n",
|
||
"L 1159 -1331 \n",
|
||
"L 581 -1331 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2969 \n",
|
||
"Q 1341 3281 1617 3432 \n",
|
||
"Q 1894 3584 2278 3584 \n",
|
||
"Q 2916 3584 3314 3078 \n",
|
||
"Q 3713 2572 3713 1747 \n",
|
||
"Q 3713 922 3314 415 \n",
|
||
"Q 2916 -91 2278 -91 \n",
|
||
"Q 1894 -91 1617 61 \n",
|
||
"Q 1341 213 1159 525 \n",
|
||
"z\n",
|
||
"M 3116 1747 \n",
|
||
"Q 3116 2381 2855 2742 \n",
|
||
"Q 2594 3103 2138 3103 \n",
|
||
"Q 1681 3103 1420 2742 \n",
|
||
"Q 1159 2381 1159 1747 \n",
|
||
"Q 1159 1113 1420 752 \n",
|
||
"Q 1681 391 2138 391 \n",
|
||
"Q 2594 391 2855 752 \n",
|
||
"Q 3116 1113 3116 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-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-68\" d=\"M 3513 2113 \n",
|
||
"L 3513 0 \n",
|
||
"L 2938 0 \n",
|
||
"L 2938 2094 \n",
|
||
"Q 2938 2591 2744 2837 \n",
|
||
"Q 2550 3084 2163 3084 \n",
|
||
"Q 1697 3084 1428 2787 \n",
|
||
"Q 1159 2491 1159 1978 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 4863 \n",
|
||
"L 1159 4863 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1366 3272 1645 3428 \n",
|
||
"Q 1925 3584 2291 3584 \n",
|
||
"Q 2894 3584 3203 3211 \n",
|
||
"Q 3513 2838 3513 2113 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-70\" x=\"61.523438\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"125\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\" x=\"186.181641\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-68\" x=\"241.162109\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_11\">\n",
|
||
" <path d=\"M 20.5625 143.185179 \n",
|
||
"L 215.8625 143.185179 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_12\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"ma2eaac5e35\" 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=\"#ma2eaac5e35\" x=\"20.5625\" y=\"143.185179\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 1 -->\n",
|
||
" <g transform=\"translate(7.2 146.984397)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_13\">\n",
|
||
" <path d=\"M 20.5625 110.138689 \n",
|
||
"L 215.8625 110.138689 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_14\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#ma2eaac5e35\" x=\"20.5625\" y=\"110.138689\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 2 -->\n",
|
||
" <g transform=\"translate(7.2 113.937907)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_15\">\n",
|
||
" <path d=\"M 20.5625 77.092199 \n",
|
||
"L 215.8625 77.092199 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_16\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#ma2eaac5e35\" x=\"20.5625\" y=\"77.092199\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 3 -->\n",
|
||
" <g transform=\"translate(7.2 80.891417)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_17\">\n",
|
||
" <path d=\"M 20.5625 44.045709 \n",
|
||
"L 215.8625 44.045709 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_18\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#ma2eaac5e35\" x=\"20.5625\" y=\"44.045709\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 4 -->\n",
|
||
" <g transform=\"translate(7.2 47.844927)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_5\">\n",
|
||
" <g id=\"line2d_19\">\n",
|
||
" <path d=\"M 20.5625 10.999219 \n",
|
||
"L 215.8625 10.999219 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #b0b0b0; stroke-width: 0.8; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_20\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#ma2eaac5e35\" x=\"20.5625\" y=\"10.999219\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <!-- 5 -->\n",
|
||
" <g transform=\"translate(7.2 14.798437)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",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_21\">\n",
|
||
" <path d=\"M 3.0625 15.841305 \n",
|
||
"L 7.2625 17.934256 \n",
|
||
"L 11.4625 19.708035 \n",
|
||
"L 15.6625 20.891391 \n",
|
||
"L 19.8625 22.317189 \n",
|
||
"L 20.5625 22.830098 \n",
|
||
"L 24.7625 42.214788 \n",
|
||
"L 28.9625 43.938759 \n",
|
||
"L 33.1625 46.907568 \n",
|
||
"L 37.3625 50.606321 \n",
|
||
"L 41.5625 53.343841 \n",
|
||
"L 42.2625 53.659541 \n",
|
||
"L 46.4625 76.747299 \n",
|
||
"L 50.6625 78.65222 \n",
|
||
"L 54.8625 80.917824 \n",
|
||
"L 59.0625 82.124096 \n",
|
||
"L 63.2625 82.986791 \n",
|
||
"L 63.9625 83.099884 \n",
|
||
"L 68.1625 99.092501 \n",
|
||
"L 72.3625 101.766916 \n",
|
||
"L 76.5625 102.192122 \n",
|
||
"L 80.7625 104.249592 \n",
|
||
"L 84.9625 103.938202 \n",
|
||
"L 85.6625 103.833648 \n",
|
||
"L 89.8625 114.892886 \n",
|
||
"L 94.0625 112.075692 \n",
|
||
"L 98.2625 114.680878 \n",
|
||
"L 102.4625 115.179996 \n",
|
||
"L 106.6625 115.106443 \n",
|
||
"L 107.3625 115.835702 \n",
|
||
"L 111.5625 123.001206 \n",
|
||
"L 115.7625 124.601748 \n",
|
||
"L 119.9625 124.541051 \n",
|
||
"L 124.1625 123.939081 \n",
|
||
"L 128.3625 123.899116 \n",
|
||
"L 129.0625 123.241024 \n",
|
||
"L 133.2625 129.555298 \n",
|
||
"L 137.4625 129.124065 \n",
|
||
"L 141.6625 127.719394 \n",
|
||
"L 145.8625 126.362181 \n",
|
||
"L 150.0625 125.191705 \n",
|
||
"L 150.7625 124.914939 \n",
|
||
"L 154.9625 133.014319 \n",
|
||
"L 159.1625 134.600212 \n",
|
||
"L 163.3625 131.947343 \n",
|
||
"L 167.5625 129.935907 \n",
|
||
"L 171.7625 130.544932 \n",
|
||
"L 172.4625 130.789168 \n",
|
||
"L 176.6625 132.1321 \n",
|
||
"L 180.8625 131.096089 \n",
|
||
"L 185.0625 132.689098 \n",
|
||
"L 189.2625 134.242739 \n",
|
||
"L 193.4625 133.907868 \n",
|
||
"L 194.1625 133.575794 \n",
|
||
"L 198.3625 137.891812 \n",
|
||
"L 202.5625 139.38676 \n",
|
||
"L 206.7625 138.455778 \n",
|
||
"L 210.9625 136.129469 \n",
|
||
"L 215.1625 134.495273 \n",
|
||
"L 215.8625 134.162813 \n",
|
||
"\" clip-path=\"url(#p93ec2f92b2)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_22\"/>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 20.5625 145.564033 \n",
|
||
"L 20.5625 9.664033 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 215.8625 145.564033 \n",
|
||
"L 215.8625 9.664033 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 20.5625 145.564033 \n",
|
||
"L 215.8625 145.564033 \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 20.5625 9.664033 \n",
|
||
"L 215.8625 9.664033 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"legend_1\">\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 131.09375 32.342158 \n",
|
||
"L 208.8625 32.342158 \n",
|
||
"Q 210.8625 32.342158 210.8625 30.342158 \n",
|
||
"L 210.8625 16.664033 \n",
|
||
"Q 210.8625 14.664033 208.8625 14.664033 \n",
|
||
"L 131.09375 14.664033 \n",
|
||
"Q 129.09375 14.664033 129.09375 16.664033 \n",
|
||
"L 129.09375 30.342158 \n",
|
||
"Q 129.09375 32.342158 131.09375 32.342158 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff; opacity: 0.8; stroke: #cccccc; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"line2d_23\">\n",
|
||
" <path d=\"M 133.09375 22.76247 \n",
|
||
"L 143.09375 22.76247 \n",
|
||
"L 153.09375 22.76247 \n",
|
||
"\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <!-- train loss -->\n",
|
||
" <g transform=\"translate(161.09375 26.26247)scale(0.1 -0.1)\">\n",
|
||
" <defs>\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",
|
||
" <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",
|
||
" <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-69\" d=\"M 603 3500 \n",
|
||
"L 1178 3500 \n",
|
||
"L 1178 0 \n",
|
||
"L 603 0 \n",
|
||
"L 603 3500 \n",
|
||
"z\n",
|
||
"M 603 4863 \n",
|
||
"L 1178 4863 \n",
|
||
"L 1178 4134 \n",
|
||
"L 603 4134 \n",
|
||
"L 603 4863 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6e\" d=\"M 3513 2113 \n",
|
||
"L 3513 0 \n",
|
||
"L 2938 0 \n",
|
||
"L 2938 2094 \n",
|
||
"Q 2938 2591 2744 2837 \n",
|
||
"Q 2550 3084 2163 3084 \n",
|
||
"Q 1697 3084 1428 2787 \n",
|
||
"Q 1159 2491 1159 1978 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1366 3272 1645 3428 \n",
|
||
"Q 1925 3584 2291 3584 \n",
|
||
"Q 2894 3584 3203 3211 \n",
|
||
"Q 3513 2838 3513 2113 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6c\" d=\"M 603 4863 \n",
|
||
"L 1178 4863 \n",
|
||
"L 1178 0 \n",
|
||
"L 603 0 \n",
|
||
"L 603 4863 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\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",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"39.208984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"80.322266\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-69\" x=\"141.601562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6e\" x=\"169.384766\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"232.763672\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6c\" x=\"264.550781\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"292.333984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"353.515625\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"405.615234\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"p93ec2f92b2\">\n",
|
||
" <rect x=\"20.5625\" y=\"9.664033\" width=\"195.3\" 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": [
|
||
"net = get_net(devices)\n",
|
||
"train(net, train_valid_iter, None, num_epochs, lr, wd, devices, lr_period,\n",
|
||
" lr_decay)\n",
|
||
"\n",
|
||
"preds = []\n",
|
||
"for data, label in test_iter:\n",
|
||
" output = torch.nn.functional.softmax(net(data.to(devices[0])), dim=1)\n",
|
||
" preds.extend(output.cpu().detach().numpy())\n",
|
||
"ids = sorted(os.listdir(\n",
|
||
" os.path.join(data_dir, 'train_valid_test', 'test', 'unknown')))\n",
|
||
"with open('submission.csv', 'w') as f:\n",
|
||
" f.write('id,' + ','.join(train_valid_ds.classes) + '\\n')\n",
|
||
" for i, output in zip(ids, preds):\n",
|
||
" f.write(i.split('.')[0] + ',' + ','.join(\n",
|
||
" [str(num) for num in output]) + '\\n')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1ee7ec4f",
|
||
"metadata": {
|
||
"origin_pos": 44
|
||
},
|
||
"source": [
|
||
"上面的代码将生成一个`submission.csv`文件,以 :numref:`sec_kaggle_house`中描述的方式提在Kaggle上提交。\n",
|
||
"\n",
|
||
"## 小结\n",
|
||
"\n",
|
||
"* ImageNet数据集中的图像比CIFAR-10图像尺寸大,我们可能会修改不同数据集上任务的图像增广操作。\n",
|
||
"* 要对ImageNet数据集的子集进行分类,我们可以利用完整ImageNet数据集上的预训练模型来提取特征并仅训练小型自定义输出网络,这将减少计算时间和节省内存空间。\n",
|
||
"\n",
|
||
"## 练习\n",
|
||
"\n",
|
||
"1. 试试使用完整Kaggle比赛数据集,增加`batch_size`(批量大小)和`num_epochs`(迭代轮数),或者设计其它超参数为`lr = 0.01`,`lr_period = 10`,和`lr_decay = 0.1`时,能取得什么结果?\n",
|
||
"1. 如果使用更深的预训练模型,会得到更好的结果吗?如何调整超参数?能进一步改善结果吗?\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "2cf6e42a",
|
||
"metadata": {
|
||
"origin_pos": 46,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"source": [
|
||
"[Discussions](https://discuss.d2l.ai/t/2833)\n"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"language_info": {
|
||
"name": "python"
|
||
},
|
||
"required_libs": [],
|
||
"widgets": {
|
||
"application/vnd.jupyter.widget-state+json": {
|
||
"state": {
|
||
"05d481bdab484ccfb68104e67a56f0da": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "HTMLStyleModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "HTMLStyleModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "StyleView",
|
||
"background": null,
|
||
"description_width": "",
|
||
"font_size": null,
|
||
"text_color": null
|
||
}
|
||
},
|
||
"07e8ce70ebdd4559861a53d673e2ab0c": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "HTMLModel",
|
||
"state": {
|
||
"_dom_classes": [],
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "HTMLModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/controls",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "HTMLView",
|
||
"description": "",
|
||
"description_allow_html": false,
|
||
"layout": "IPY_MODEL_426e00de12584ffaa3d44a3e93eea652",
|
||
"placeholder": "",
|
||
"style": "IPY_MODEL_0fc52730af0b4d46981292e17b21881b",
|
||
"tabbable": null,
|
||
"tooltip": null,
|
||
"value": " 83.3M/83.3M [00:00<00:00, 178MB/s]"
|
||
}
|
||
},
|
||
"0fc52730af0b4d46981292e17b21881b": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "HTMLStyleModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "HTMLStyleModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "StyleView",
|
||
"background": null,
|
||
"description_width": "",
|
||
"font_size": null,
|
||
"text_color": null
|
||
}
|
||
},
|
||
"426e00de12584ffaa3d44a3e93eea652": {
|
||
"model_module": "@jupyter-widgets/base",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "LayoutModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/base",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "LayoutModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "LayoutView",
|
||
"align_content": null,
|
||
"align_items": null,
|
||
"align_self": null,
|
||
"border_bottom": null,
|
||
"border_left": null,
|
||
"border_right": null,
|
||
"border_top": null,
|
||
"bottom": null,
|
||
"display": null,
|
||
"flex": null,
|
||
"flex_flow": null,
|
||
"grid_area": null,
|
||
"grid_auto_columns": null,
|
||
"grid_auto_flow": null,
|
||
"grid_auto_rows": null,
|
||
"grid_column": null,
|
||
"grid_gap": null,
|
||
"grid_row": null,
|
||
"grid_template_areas": null,
|
||
"grid_template_columns": null,
|
||
"grid_template_rows": null,
|
||
"height": null,
|
||
"justify_content": null,
|
||
"justify_items": null,
|
||
"left": null,
|
||
"margin": null,
|
||
"max_height": null,
|
||
"max_width": null,
|
||
"min_height": null,
|
||
"min_width": null,
|
||
"object_fit": null,
|
||
"object_position": null,
|
||
"order": null,
|
||
"overflow": null,
|
||
"padding": null,
|
||
"right": null,
|
||
"top": null,
|
||
"visibility": null,
|
||
"width": null
|
||
}
|
||
},
|
||
"62f56dcf4a5143feb9096688694380bd": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "HBoxModel",
|
||
"state": {
|
||
"_dom_classes": [],
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "HBoxModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/controls",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "HBoxView",
|
||
"box_style": "",
|
||
"children": [
|
||
"IPY_MODEL_c71d6d9028d74e1ab55487a6028970a5",
|
||
"IPY_MODEL_6aa8082311944890a8b240d3a40133d6",
|
||
"IPY_MODEL_07e8ce70ebdd4559861a53d673e2ab0c"
|
||
],
|
||
"layout": "IPY_MODEL_9b1361574f2b4f1dae8ae76858d73d89",
|
||
"tabbable": null,
|
||
"tooltip": null
|
||
}
|
||
},
|
||
"6aa8082311944890a8b240d3a40133d6": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "FloatProgressModel",
|
||
"state": {
|
||
"_dom_classes": [],
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "FloatProgressModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/controls",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "ProgressView",
|
||
"bar_style": "success",
|
||
"description": "",
|
||
"description_allow_html": false,
|
||
"layout": "IPY_MODEL_955d26cae5294b2ea621e20082681646",
|
||
"max": 87319819.0,
|
||
"min": 0.0,
|
||
"orientation": "horizontal",
|
||
"style": "IPY_MODEL_7bfcb307c3fd4d4c9a3c70d7eeca097d",
|
||
"tabbable": null,
|
||
"tooltip": null,
|
||
"value": 87319819.0
|
||
}
|
||
},
|
||
"7bfcb307c3fd4d4c9a3c70d7eeca097d": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "ProgressStyleModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "ProgressStyleModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "StyleView",
|
||
"bar_color": null,
|
||
"description_width": ""
|
||
}
|
||
},
|
||
"955d26cae5294b2ea621e20082681646": {
|
||
"model_module": "@jupyter-widgets/base",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "LayoutModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/base",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "LayoutModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "LayoutView",
|
||
"align_content": null,
|
||
"align_items": null,
|
||
"align_self": null,
|
||
"border_bottom": null,
|
||
"border_left": null,
|
||
"border_right": null,
|
||
"border_top": null,
|
||
"bottom": null,
|
||
"display": null,
|
||
"flex": null,
|
||
"flex_flow": null,
|
||
"grid_area": null,
|
||
"grid_auto_columns": null,
|
||
"grid_auto_flow": null,
|
||
"grid_auto_rows": null,
|
||
"grid_column": null,
|
||
"grid_gap": null,
|
||
"grid_row": null,
|
||
"grid_template_areas": null,
|
||
"grid_template_columns": null,
|
||
"grid_template_rows": null,
|
||
"height": null,
|
||
"justify_content": null,
|
||
"justify_items": null,
|
||
"left": null,
|
||
"margin": null,
|
||
"max_height": null,
|
||
"max_width": null,
|
||
"min_height": null,
|
||
"min_width": null,
|
||
"object_fit": null,
|
||
"object_position": null,
|
||
"order": null,
|
||
"overflow": null,
|
||
"padding": null,
|
||
"right": null,
|
||
"top": null,
|
||
"visibility": null,
|
||
"width": null
|
||
}
|
||
},
|
||
"9b1361574f2b4f1dae8ae76858d73d89": {
|
||
"model_module": "@jupyter-widgets/base",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "LayoutModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/base",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "LayoutModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "LayoutView",
|
||
"align_content": null,
|
||
"align_items": null,
|
||
"align_self": null,
|
||
"border_bottom": null,
|
||
"border_left": null,
|
||
"border_right": null,
|
||
"border_top": null,
|
||
"bottom": null,
|
||
"display": null,
|
||
"flex": null,
|
||
"flex_flow": null,
|
||
"grid_area": null,
|
||
"grid_auto_columns": null,
|
||
"grid_auto_flow": null,
|
||
"grid_auto_rows": null,
|
||
"grid_column": null,
|
||
"grid_gap": null,
|
||
"grid_row": null,
|
||
"grid_template_areas": null,
|
||
"grid_template_columns": null,
|
||
"grid_template_rows": null,
|
||
"height": null,
|
||
"justify_content": null,
|
||
"justify_items": null,
|
||
"left": null,
|
||
"margin": null,
|
||
"max_height": null,
|
||
"max_width": null,
|
||
"min_height": null,
|
||
"min_width": null,
|
||
"object_fit": null,
|
||
"object_position": null,
|
||
"order": null,
|
||
"overflow": null,
|
||
"padding": null,
|
||
"right": null,
|
||
"top": null,
|
||
"visibility": null,
|
||
"width": null
|
||
}
|
||
},
|
||
"c71d6d9028d74e1ab55487a6028970a5": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "HTMLModel",
|
||
"state": {
|
||
"_dom_classes": [],
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "HTMLModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/controls",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "HTMLView",
|
||
"description": "",
|
||
"description_allow_html": false,
|
||
"layout": "IPY_MODEL_feb254b14115426a87721b8d7c742bd2",
|
||
"placeholder": "",
|
||
"style": "IPY_MODEL_05d481bdab484ccfb68104e67a56f0da",
|
||
"tabbable": null,
|
||
"tooltip": null,
|
||
"value": "100%"
|
||
}
|
||
},
|
||
"feb254b14115426a87721b8d7c742bd2": {
|
||
"model_module": "@jupyter-widgets/base",
|
||
"model_module_version": "2.0.0",
|
||
"model_name": "LayoutModel",
|
||
"state": {
|
||
"_model_module": "@jupyter-widgets/base",
|
||
"_model_module_version": "2.0.0",
|
||
"_model_name": "LayoutModel",
|
||
"_view_count": null,
|
||
"_view_module": "@jupyter-widgets/base",
|
||
"_view_module_version": "2.0.0",
|
||
"_view_name": "LayoutView",
|
||
"align_content": null,
|
||
"align_items": null,
|
||
"align_self": null,
|
||
"border_bottom": null,
|
||
"border_left": null,
|
||
"border_right": null,
|
||
"border_top": null,
|
||
"bottom": null,
|
||
"display": null,
|
||
"flex": null,
|
||
"flex_flow": null,
|
||
"grid_area": null,
|
||
"grid_auto_columns": null,
|
||
"grid_auto_flow": null,
|
||
"grid_auto_rows": null,
|
||
"grid_column": null,
|
||
"grid_gap": null,
|
||
"grid_row": null,
|
||
"grid_template_areas": null,
|
||
"grid_template_columns": null,
|
||
"grid_template_rows": null,
|
||
"height": null,
|
||
"justify_content": null,
|
||
"justify_items": null,
|
||
"left": null,
|
||
"margin": null,
|
||
"max_height": null,
|
||
"max_width": null,
|
||
"min_height": null,
|
||
"min_width": null,
|
||
"object_fit": null,
|
||
"object_position": null,
|
||
"order": null,
|
||
"overflow": null,
|
||
"padding": null,
|
||
"right": null,
|
||
"top": null,
|
||
"visibility": null,
|
||
"width": null
|
||
}
|
||
}
|
||
},
|
||
"version_major": 2,
|
||
"version_minor": 0
|
||
}
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
} |