diff --git a/.gitignore b/.gitignore index e7f8501f2c04d0ddb9a27202b3e91d33c47d9de8..8b1e433c11f8ea644b935f60c0ced50cfa5d31a2 100644 --- a/.gitignore +++ b/.gitignore @@ -6,3 +6,4 @@ pandoc.template py_env* *.ipynb build +.vscode diff --git a/paddle2.0_docs/getting_started/getting_started.ipynb b/paddle2.0_docs/getting_started/getting_started.ipynb index 33b2afdc358a11006a32e47766c3341d94894920..6e59d468fa76e0dccf0b585258d6f250b9c2fdf4 100644 --- a/paddle2.0_docs/getting_started/getting_started.ipynb +++ b/paddle2.0_docs/getting_started/getting_started.ipynb @@ -31,24 +31,22 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 8, "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "'2.0.0-beta0'" - ] - }, - "execution_count": 1, - "metadata": {}, - "output_type": "execute_result" + "name": "stdout", + "output_type": "stream", + "text": [ + "2.0.0-beta0\n" + ] } ], "source": [ "import paddle\n", "\n", - "paddle.__version__" + "print(paddle.__version__)\n", + "paddle.disable_static()" ] }, { @@ -71,7 +69,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -90,7 +88,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ @@ -113,7 +111,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 11, "metadata": { "scrolled": true }, @@ -123,15 +121,15 @@ "output_type": "stream", "text": [ "Epoch 1/5\n", - "step 1875/1875 [==============================] - loss: 0.2571 - acc: 0.9037 - 10ms/step \n", + "step 1875/1875 [==============================] - loss: 0.2250 - acc: 0.9025 - 9ms/step \n", "Epoch 2/5\n", - "step 1875/1875 [==============================] - loss: 0.1880 - acc: 0.9458 - 14ms/step \n", + "step 1875/1875 [==============================] - loss: 0.0969 - acc: 0.9462 - 13ms/step \n", "Epoch 3/5\n", - "step 1875/1875 [==============================] - loss: 0.0279 - acc: 0.9549 - 11ms/step \n", + "step 1875/1875 [==============================] - loss: 0.1035 - acc: 0.9550 - 12ms/step \n", "Epoch 4/5\n", - "step 1875/1875 [==============================] - loss: 0.0505 - acc: 0.9608 - 13ms/step \n", + "step 1875/1875 [==============================] - loss: 0.0316 - acc: 0.9603 - 12ms/step \n", "Epoch 5/5\n", - "step 1875/1875 [==============================] - loss: 0.2253 - acc: 0.9646 - 12ms/step \n" + "step 1875/1875 [==============================] - loss: 0.1771 - acc: 0.9637 - 12ms/step \n" ] } ], diff --git a/paddle2.0_docs/high_level_api/high_level_api.ipynb b/paddle2.0_docs/high_level_api/high_level_api.ipynb index feeb7068ee718b97632546f2e6af1dcfe5b6878b..a71c4a4984a2535f7c02f3217e403d6feec4514e 100644 --- a/paddle2.0_docs/high_level_api/high_level_api.ipynb +++ b/paddle2.0_docs/high_level_api/high_level_api.ipynb @@ -36,7 +36,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -45,7 +45,7 @@ "'2.0.0-beta0'" ] }, - "execution_count": 1, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -55,6 +55,9 @@ "import paddle.vision as vision\n", "import paddle.text as text\n", "\n", + "# 启动动态图训练模式\n", + "paddle.disable_static()\n", + "\n", "paddle.__version__" ] }, @@ -90,7 +93,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "metadata": { "tags": [] }, @@ -118,7 +121,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 18, "metadata": {}, "outputs": [], "source": [ @@ -140,7 +143,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 5, "metadata": { "tags": [] }, @@ -207,8 +210,8 @@ " return len(self.data)\n", "\n", "# 测试定义的数据集\n", - "train_dataset = MyDataset(mode='train')\n", - "val_dataset = MyDataset(mode='test')\n", + "train_dataset_2 = MyDataset(mode='train')\n", + "val_dataset_2 = MyDataset(mode='test')\n", "\n", "print('=============train dataset=============')\n", "for data, label in train_dataset:\n", @@ -232,7 +235,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -243,7 +246,7 @@ "transform = Compose([ColorJitter(), Resize(size=100)])\n", "\n", "# 通过transform参数传递定义好的数据增项方法即可完成对自带数据集的应用\n", - "train_dataset = vision.datasets.MNIST(mode='train', transform=transform)" + "train_dataset_3 = vision.datasets.MNIST(mode='train', transform=transform)" ] }, { @@ -257,7 +260,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -316,7 +319,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 12, "metadata": {}, "outputs": [], "source": [ @@ -340,7 +343,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": {}, "outputs": [], "source": [ @@ -364,7 +367,7 @@ "\n", " return y\n", "\n", - "mnist = Mnist()" + "mnist_2 = Mnist()" ] }, { @@ -380,14 +383,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, "outputs": [], "source": [ "# 场景1：动态图模式\n", "\n", - "# 启动动态图训练模式\n", - "paddle.disable_static()\n", "# 使用GPU训练\n", "paddle.set_device('gpu')\n", "# 模型封装\n", @@ -412,9 +413,45 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "--------------------------------------------------------------------------------\n", + " Layer (type) Input Shape Output Shape Param #\n", + "================================================================================\n", + " Flatten-57509 [-1, 1, 28, 28] [-1, 784] 0\n", + " Linear-7 [-1, 784] [-1, 512] 401,920\n", + " ReLU-4 [-1, 512] [-1, 512] 0\n", + " Dropout-4 [-1, 512] [-1, 512] 0\n", + " Linear-8 [-1, 512] [-1, 10] 5,130\n", + "================================================================================\n", + "Total params: 407,050\n", + "Trainable params: 407,050\n", + "Non-trainable params: 0\n", + "--------------------------------------------------------------------------------\n", + "Input size (MB): 0.00\n", + "Forward/backward pass size (MB): 0.02\n", + "Params size (MB): 1.55\n", + "Estimated Total Size (MB): 1.57\n", + "--------------------------------------------------------------------------------\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "{'total_params': 407050, 'trainable_params': 407050}" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "model.summary((1, 28, 28))" ] @@ -428,9 +465,45 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "--------------------------------------------------------------------------------\n", + " Layer (type) Input Shape Output Shape Param #\n", + "================================================================================\n", + " Flatten-57508 [-1, 1, 28, 28] [-1, 784] 0\n", + " Linear-5 [-1, 784] [-1, 512] 401,920\n", + " ReLU-3 [-1, 512] [-1, 512] 0\n", + " Dropout-3 [-1, 512] [-1, 512] 0\n", + " Linear-6 [-1, 512] [-1, 10] 5,130\n", + "================================================================================\n", + "Total params: 407,050\n", + "Trainable params: 407,050\n", + "Non-trainable params: 0\n", + "--------------------------------------------------------------------------------\n", + "Input size (MB): 0.00\n", + "Forward/backward pass size (MB): 0.02\n", + "Params size (MB): 1.55\n", + "Estimated Total Size (MB): 1.57\n", + "--------------------------------------------------------------------------------\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "{'total_params': 407050, 'trainable_params': 407050}" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "paddle.summary(mnist, (1, 28, 28))" ] @@ -456,7 +529,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "metadata": {}, "outputs": [], "source": [ @@ -475,9 +548,36 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "step 1875/1875 [==============================] - loss: 0.1600 - acc: 0.9022 - 10ms/step \n", + "Epoch 2/10\n", + "step 1875/1875 [==============================] - loss: 0.0455 - acc: 0.9461 - 12ms/step \n", + "Epoch 3/10\n", + "step 1875/1875 [==============================] - loss: 0.1429 - acc: 0.9544 - 19ms/step \n", + "Epoch 4/10\n", + "step 1875/1875 [==============================] - loss: 0.0197 - acc: 0.9601 - 22ms/step \n", + "Epoch 5/10\n", + "step 1875/1875 [==============================] - loss: 0.1762 - acc: 0.9644 - 25ms/step \n", + "Epoch 6/10\n", + "step 1875/1875 [==============================] - loss: 0.1304 - acc: 0.9667 - 22ms/step \n", + "Epoch 7/10\n", + "step 1875/1875 [==============================] - loss: 0.0133 - acc: 0.9682 - 22ms/step \n", + "Epoch 8/10\n", + "step 1875/1875 [==============================] - loss: 0.0097 - acc: 0.9705 - 19ms/step \n", + "Epoch 9/10\n", + "step 1875/1875 [==============================] - loss: 3.1264e-04 - acc: 0.9716 - 23ms/step \n", + "Epoch 10/10\n", + "step 1875/1875 [==============================] - loss: 0.0767 - acc: 0.9729 - 13ms/step \n" + ] + } + ], "source": [ "# 启动模型训练，指定训练数据集，设置训练轮次，设置每次数据集计算的批次大小，设置日志格式\n", "model.fit(train_dataset, \n", @@ -497,14 +597,39 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 20, "metadata": { "tags": [] }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10\n", + "step 1875/1875 [==============================] - loss: 0.0490 - acc: 0.9741 - 6ms/step \n", + "Epoch 2/10\n", + "step 1875/1875 [==============================] - loss: 0.1384 - acc: 0.9760 - 7ms/step \n", + "Epoch 3/10\n", + "step 1875/1875 [==============================] - loss: 0.0929 - acc: 0.9767 - 7ms/step \n", + "Epoch 4/10\n", + "step 1875/1875 [==============================] - loss: 0.0190 - acc: 0.9772 - 6ms/step \n", + "Epoch 5/10\n", + "step 1875/1875 [==============================] - loss: 0.0862 - acc: 0.9774 - 7ms/step \n", + "Epoch 6/10\n", + "step 1875/1875 [==============================] - loss: 0.0748 - acc: 0.9785 - 8ms/step \n", + "Epoch 7/10\n", + "step 1875/1875 [==============================] - loss: 0.0039 - acc: 0.9798 - 17ms/step \n", + "Epoch 8/10\n", + "step 1875/1875 [==============================] - loss: 0.0037 - acc: 0.9808 - 11ms/step \n", + "Epoch 9/10\n", + "step 1875/1875 [==============================] - loss: 0.0013 - acc: 0.9800 - 8ms/step \n", + "Epoch 10/10\n", + "step 1875/1875 [==============================] - loss: 0.0376 - acc: 0.9810 - 8ms/step \n" + ] + } + ], "source": [ - "# 启动动态图训练模式\n", - "paddle.disable_static()\n", "\n", "# 使用GPU训练\n", "paddle.set_device('gpu')\n", @@ -530,17 +655,13 @@ "source": [ "### 5.2 单机多卡\n", "\n", - "对于高层API来实现单机多卡非常简单，整个训练代码和单机单卡没有差异。直接使用`paddle.distributed.launch`启动单机单卡的程序即可。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# train.py里面包含的就是单机单卡代码\n", - "python -m paddle.distributed.launch train.py" + "对于高层API来实现单机多卡非常简单，整个训练代码和单机单卡没有差异。直接使用`paddle.distributed.launch`启动单机单卡的程序即可。\n", + "\n", + "```bash\n", + "$ python -m paddle.distributed.launch train.py\n", + "```\n", + "\n", + "train.py里面包含的就是单机单卡代码" ] }, { @@ -810,9 +931,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Eval begin...\n", + "step 10000/10000 [==============================] - loss: 0.0000e+00 - acc: 0.9801 - 2ms/step \n", + "Eval samples: 10000\n" + ] + } + ], "source": [ "result = model.evaluate(val_dataset, verbose=1)" ] @@ -834,9 +965,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Predict begin...\n", + "step 10000/10000 [==============================] - 4ms/step \n", + "Predict samples: 10000\n" + ] + } + ], "source": [ "pred_result = model.predict(val_dataset)" ] @@ -866,17 +1007,40 @@ "\n", "### 8.1 模型存储\n", "\n", - "模型训练和验证达到我们的预期后，可以使用`save`接口来将我们的模型保存下来，用于后续模型的Fine-tuning（接口参数training=True）或推理部署（接口参数training=False）。" + "模型训练和验证达到我们的预期后，可以使用`save`接口来将我们的模型保存下来，用于后续模型的Fine-tuning（接口参数training=True）或推理部署（接口参数training=False）。\n", + "\n", + "需要注意的是，在动态图模式训练时保存推理模型的参数文件和模型文件，需要在forward成员函数上添加@paddle.jit.to_static装饰器，参考下面的例子：\n", + "\n", + "```python\n", + "class Mnist(paddle.nn.Layer):\n", + " def __init__(self):\n", + " super(Mnist, self).__init__()\n", + "\n", + " self.flatten = paddle.nn.Flatten()\n", + " self.linear_1 = paddle.nn.Linear(784, 512)\n", + " self.linear_2 = paddle.nn.Linear(512, 10)\n", + " self.relu = paddle.nn.ReLU()\n", + " self.dropout = paddle.nn.Dropout(0.2)\n", + "\n", + " @paddle.jit.to_static\n", + " def forward(self, inputs):\n", + " y = self.flatten(inputs)\n", + " y = self.linear_1(y)\n", + " y = self.relu(y)\n", + " y = self.dropout(y)\n", + " y = self.linear_2(y)\n", + "\n", + " return y\n", + "```" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "metadata": {}, "outputs": [], "source": [ - "# 保存用于推理部署的模型（training=False）\n", - "model.save('~/model/mnist', training=False)" + "model.save('~/model/mnist')" ] }, { diff --git a/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb b/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb index bcb2466cd2adc0643ca9e0c2548271bcb339544a..e731144601952d278a305cb0597da2137b0fe5cc 100644 --- a/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb +++ b/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb @@ -58,6 +58,9 @@ "import paddle\n", "from paddle.nn import functional as F\n", "\n", + "device = paddle.set_device('gpu')\n", + "paddle.disable_static(device)\n", + "\n", "paddle.__version__" ] }, @@ -808,34 +811,6 @@ "## 5.模型训练" ] }, - { - "cell_type": "markdown", - "metadata": { - "colab_type": "text", - "id": "8Sskbyz58X4J" - }, - "source": [ - "### 5.1 配置信息\n", - "\n", - "定义训练BATCH_SIZE、训练轮次和计算设备等信息。" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": { - "colab": {}, - "colab_type": "code", - "id": "4fSkTiRB8OpP" - }, - "outputs": [], - "source": [ - "BATCH_SIZE = 32\n", - "EPOCHS = 15\n", - "device = paddle.set_device('gpu')\n", - "paddle.disable_static(device)" - ] - }, { "cell_type": "markdown", "metadata": { @@ -843,14 +818,14 @@ "id": "x_vaedRa8eoy" }, "source": [ - "### 5.3 自定义Loss\n", + "### 5.1 自定义Loss\n", "\n", "在这个任务中我们使用SoftmaxWithCrossEntropy损失函数来做计算，飞桨中有functional形式的API，这里我们做一个自定义操作，实现一个Class形式API放到模型训练中使用。没有直接使用CrossEntropyLoss的原因主要是对计算维度的自定义需求，本次需要进行softmax计算的维度是1，不是默认的最后一维，所以我们采用上面提到的损失函数，通过axis参数来指定softmax计算维度。" ] }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 10, "metadata": { "colab": {}, "colab_type": "code", @@ -877,7 +852,7 @@ "id": "rj6MPPMkJIdZ" }, "source": [ - "### 5.4 启动模型训练\n", + "### 5.2 启动模型训练\n", "\n", "使用模型代码进行Model实例生成，使用prepare接口定义优化器、损失函数和评价指标等信息，用于后续训练使用。在所有初步配置完成后，调用fit接口开启训练执行过程，调用fit时只需要将前面定义好的训练数据集、测试数据集、训练轮次（Epoch）和批次大小（batch_size）配置好即可。" ] @@ -907,8 +882,8 @@ "model.prepare(optim, SoftmaxWithCrossEntropy())\n", "model.fit(train_dataset, \n", " val_dataset, \n", - " epochs=EPOCHS, \n", - " batch_size=BATCH_SIZE)" + " epochs=15, \n", + " batch_size=32)" ] }, {