Skip to content
This repository has been archived by the owner on Jan 24, 2024. It is now read-only.

Commit

Permalink
update save_model to 2.0rc (#924)
Browse files Browse the repository at this point in the history 
* update save_model to 2.0rc

* update save_model to 2.0rc
  • Loading branch information
@dingjiaweiww
dingjiaweiww authored Oct 28, 2020
1 parent b98a567 commit 7a4952a
Showing 1 changed file with 40 additions and 59 deletions.
99 changes: 40 additions & 59 deletions paddle2.0_docs/save_model/save_model.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"metadata": {},
"source": [
"# 模型保存及加载\n",
"本教程将基于Paddle高阶API对模型参数的保存和加载进行讲解。在日常训练模型过程中我们会遇到一些突发情况，导致训练过程主动或被动的中断，因此在模型没有完全训练好的情况下，我们需要高频的保存下模型参数，在发生意外时可以快速载入保存的参数继续训练。抑或是模型已经训练好了，我们需要使用训练好的参数进行预测或部署模型上线。面对上述情况，Paddle中提供了保存模型和提取模型的方法，支持从上一次保存状态开始训练，只要我们随时保存训练过程中的模型状态，就不用从初始状态重新训练。\n",
"本教程将基于Paddle高阶API对模型参数的保存和加载进行讲解。在日常训练模型过程中我们会遇到一些突发情况，导致训练过程主动或被动的中断，因此在模型没有完全训练好的情况下，我们需要高频的保存下模型参数，在发生意外时可以快速载入保存的参数继续训练；抑或是模型已经训练好了，我们需要使用训练好的参数进行预测或部署模型上线。面对上述情况，Paddle中提供了保存模型和提取模型的方法，支持从上一次保存状态开始训练，只要我们随时保存训练过程中的模型状态，就不用从初始状态重新训练。\n",
"下面将基于手写数字识别的模型讲解paddle如何保存及加载模型，并恢复训练，网络结构部分的讲解省略。"
]
},
Expand All @@ -14,19 +14,19 @@
"metadata": {},
"source": [
"## 环境\n",
"本教程基于paddle-2.0Beta编写，如果您的环境不是此版本，请先安装paddle-2.0Beta版本，使用命令：pip3 install paddlepaddle==2.0Beta。"
"本教程基于paddle-2.0rc版编写，如果您的环境不是此版本，请先安装paddle-2.0rc版本，使用命令：pip3 install paddlepaddle==2.0.0-rc0"
]
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.0.0-beta0\n"
"2.0.0-rc0\n"
]
}
],
Expand All @@ -36,11 +36,10 @@
"from paddle.nn import Layer\n",
"from paddle.vision.datasets import MNIST\n",
"from paddle.metric import Accuracy\n",
"from paddle.nn import Conv2d,MaxPool2d,Linear\n",
"from paddle.nn import Conv2D,MaxPool2D,Linear\n",
"from paddle.static import InputSpec\n",
"\n",
"print(paddle.__version__)\n",
"paddle.disable_static()"
"print(paddle.__version__)"
]
},
{
Expand All @@ -54,7 +53,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -71,17 +70,17 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"class MyModel(Layer):\n",
" def __init__(self):\n",
" super(MyModel, self).__init__()\n",
" self.conv1 = paddle.nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5, stride=1, padding=2)\n",
" self.max_pool1 = MaxPool2d(kernel_size=2, stride=2)\n",
" self.conv2 = Conv2d(in_channels=6, out_channels=16, kernel_size=5, stride=1)\n",
" self.max_pool2 = MaxPool2d(kernel_size=2, stride=2)\n",
" self.conv1 = paddle.nn.Conv2D(in_channels=1, out_channels=6, kernel_size=5, stride=1, padding=2)\n",
" self.max_pool1 = MaxPool2D(kernel_size=2, stride=2)\n",
" self.conv2 = Conv2D(in_channels=6, out_channels=16, kernel_size=5, stride=1)\n",
" self.max_pool2 = MaxPool2D(kernel_size=2, stride=2)\n",
" self.linear1 = Linear(in_features=16*5*5, out_features=120)\n",
" self.linear2 = Linear(in_features=120, out_features=84)\n",
" self.linear3 = Linear(in_features=84, out_features=10)\n",
Expand All @@ -99,7 +98,6 @@
" x = self.linear2(x)\n",
" x = F.relu(x)\n",
" x = self.linear3(x)\n",
" x = F.softmax(x)\n",
" return x"
]
},
Expand All @@ -113,28 +111,30 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/1\n",
"step 100/938 - loss: 1.6177 - acc_top1: 0.6119 - acc_top2: 0.6813 - 15ms/step\n",
"step 200/938 - loss: 1.7720 - acc_top1: 0.7230 - acc_top2: 0.7788 - 15ms/step\n",
"step 300/938 - loss: 1.6114 - acc_top1: 0.7666 - acc_top2: 0.8164 - 15ms/step\n",
"step 400/938 - loss: 1.6537 - acc_top1: 0.7890 - acc_top2: 0.8350 - 15ms/step\n",
"step 500/938 - loss: 1.5229 - acc_top1: 0.8170 - acc_top2: 0.8619 - 15ms/step\n",
"step 600/938 - loss: 1.5269 - acc_top1: 0.8391 - acc_top2: 0.8821 - 15ms/step\n",
"step 700/938 - loss: 1.4821 - acc_top1: 0.8561 - acc_top2: 0.8970 - 15ms/step\n",
"step 800/938 - loss: 1.4860 - acc_top1: 0.8689 - acc_top2: 0.9081 - 15ms/step\n",
"step 900/938 - loss: 1.5032 - acc_top1: 0.8799 - acc_top2: 0.9174 - 15ms/step\n",
"step 938/938 - loss: 1.4617 - acc_top1: 0.8835 - acc_top2: 0.9203 - 15ms/step\n",
"Epoch 1/3\n",
"step 938/938 [==============================] - loss: 0.1555 - acc_top1: 0.8947 - acc_top2: 0.9496 - 16ms/step \n",
"save checkpoint at /Users/dingjiawei/online_repo/book/paddle2.0_docs/save_model/mnist_checkpoint/0\n",
"Eval begin...\n",
"step 100/157 - loss: 1.4765 - acc_top1: 0.9636 - acc_top2: 0.9891 - 6ms/step\n",
"step 157/157 - loss: 1.4612 - acc_top1: 0.9705 - acc_top2: 0.9910 - 6ms/step\n",
"step 157/157 [==============================] - loss: 0.0105 - acc_top1: 0.9535 - acc_top2: 0.9807 - 6ms/step \n",
"Eval samples: 10000\n",
"Epoch 2/3\n",
"step 938/938 [==============================] - loss: 0.0143 - acc_top1: 0.9689 - acc_top2: 0.9909 - 16ms/step \n",
"save checkpoint at /Users/dingjiawei/online_repo/book/paddle2.0_docs/save_model/mnist_checkpoint/1\n",
"Eval begin...\n",
"step 157/157 [==============================] - loss: 0.0101 - acc_top1: 0.9733 - acc_top2: 0.9934 - 6ms/step \n",
"Eval samples: 10000\n",
"Epoch 3/3\n",
"step 938/938 [==============================] - loss: 0.0083 - acc_top1: 0.9796 - acc_top2: 0.9951 - 16ms/step \n",
"save checkpoint at /Users/dingjiawei/online_repo/book/paddle2.0_docs/save_model/mnist_checkpoint/2\n",
"Eval begin...\n",
"step 157/157 [==============================] - loss: 0.0276 - acc_top1: 0.9761 - acc_top2: 0.9934 - 6ms/step \n",
"Eval samples: 10000\n",
"save checkpoint at /Users/dingjiawei/online_repo/book/paddle2.0_docs/save_model/mnist_checkpoint/final\n"
]
Expand All @@ -149,15 +149,16 @@
"\n",
"model.prepare(\n",
" optim,\n",
" paddle.nn.loss.CrossEntropyLoss(),\n",
" paddle.nn.CrossEntropyLoss(),\n",
" Accuracy(topk=(1, 2))\n",
" )\n",
"model.fit(train_dataset,\n",
" test_dataset,\n",
" epochs=1,\n",
" log_freq=100,\n",
" epochs=3,\n",
" batch_size=64,\n",
" save_dir='mnist_checkpoint')\n"
" save_dir='mnist_checkpoint',\n",
" verbose=1\n",
" )"
]
},
{
Expand Down Expand Up @@ -272,42 +273,22 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/2\n",
"step 100/938 - loss: 1.4635 - acc_top1: 0.9650 - acc_top2: 0.9898 - 15ms/step\n",
"step 200/938 - loss: 1.5459 - acc_top1: 0.9659 - acc_top2: 0.9897 - 15ms/step\n",
"step 300/938 - loss: 1.5109 - acc_top1: 0.9658 - acc_top2: 0.9893 - 15ms/step\n",
"step 400/938 - loss: 1.4797 - acc_top1: 0.9664 - acc_top2: 0.9899 - 15ms/step\n",
"step 500/938 - loss: 1.4786 - acc_top1: 0.9673 - acc_top2: 0.9902 - 15ms/step\n",
"step 600/938 - loss: 1.5082 - acc_top1: 0.9679 - acc_top2: 0.9906 - 15ms/step\n",
"step 700/938 - loss: 1.4768 - acc_top1: 0.9687 - acc_top2: 0.9909 - 15ms/step\n",
"step 800/938 - loss: 1.4638 - acc_top1: 0.9696 - acc_top2: 0.9913 - 15ms/step\n",
"step 900/938 - loss: 1.5058 - acc_top1: 0.9704 - acc_top2: 0.9916 - 15ms/step\n",
"step 938/938 - loss: 1.4702 - acc_top1: 0.9708 - acc_top2: 0.9917 - 15ms/step\n",
"step 938/938 [==============================] - loss: 0.0046 - acc_top1: 0.9768 - acc_top2: 0.9943 - 18ms/step \n",
"Eval begin...\n",
"step 100/157 - loss: 1.4613 - acc_top1: 0.9755 - acc_top2: 0.9944 - 5ms/step\n",
"step 157/157 - loss: 1.4612 - acc_top1: 0.9805 - acc_top2: 0.9956 - 5ms/step\n",
"step 157/157 [==============================] - loss: 0.0012 - acc_top1: 0.9789 - acc_top2: 0.9934 - 6ms/step \n",
"Eval samples: 10000\n",
"Epoch 2/2\n",
"step 100/938 - loss: 1.4832 - acc_top1: 0.9789 - acc_top2: 0.9927 - 15ms/step\n",
"step 200/938 - loss: 1.4618 - acc_top1: 0.9779 - acc_top2: 0.9932 - 14ms/step\n",
"step 300/938 - loss: 1.4613 - acc_top1: 0.9779 - acc_top2: 0.9929 - 15ms/step\n",
"step 400/938 - loss: 1.4765 - acc_top1: 0.9772 - acc_top2: 0.9932 - 15ms/step\n",
"step 500/938 - loss: 1.4932 - acc_top1: 0.9775 - acc_top2: 0.9934 - 15ms/step\n",
"step 600/938 - loss: 1.4773 - acc_top1: 0.9773 - acc_top2: 0.9936 - 15ms/step\n",
"step 700/938 - loss: 1.4612 - acc_top1: 0.9783 - acc_top2: 0.9939 - 15ms/step\n",
"step 800/938 - loss: 1.4653 - acc_top1: 0.9779 - acc_top2: 0.9939 - 15ms/step\n",
"step 900/938 - loss: 1.4639 - acc_top1: 0.9780 - acc_top2: 0.9939 - 15ms/step\n",
"step 938/938 - loss: 1.4678 - acc_top1: 0.9779 - acc_top2: 0.9937 - 15ms/step\n",
"step 938/938 [==============================] - loss: 0.0063 - acc_top1: 0.9845 - acc_top2: 0.9965 - 18ms/step \n",
"Eval begin...\n",
"step 100/157 - loss: 1.4612 - acc_top1: 0.9733 - acc_top2: 0.9945 - 6ms/step\n",
"step 157/157 - loss: 1.4612 - acc_top1: 0.9778 - acc_top2: 0.9952 - 6ms/step\n",
"step 157/157 [==============================] - loss: 0.0014 - acc_top1: 0.9848 - acc_top2: 0.9964 - 6ms/step \n",
"Eval samples: 10000\n"
]
}
Expand Down Expand Up @@ -337,8 +318,8 @@
"model.fit(train_data=train_dataset,\n",
" eval_data=test_dataset,\n",
" batch_size=64,\n",
" log_freq=100,\n",
" epochs=2\n",
" epochs=2,\n",
" verbose=1\n",
" )"
]
},
Expand Down

0 comments on commit 7a4952a

Please sign in to comment.