{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"[](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/r2.4.10/tutorials/zh_cn/beginner/mindspore_train.ipynb) [](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/r2.4.10/tutorials/zh_cn/beginner/mindspore_train.py) [](https://gitee.com/mindspore/docs/blob/r2.4.10/tutorials/source_zh_cn/beginner/train.ipynb)\n",
"\n",
"[基本介绍](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/introduction.html) || [快速入门](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/quick_start.html) || [张量 Tensor](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/tensor.html) || [数据加载与处理](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/dataset.html) || [网络构建](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/model.html) || [函数式自动微分](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/autograd.html) || **模型训练** || [保存与加载](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/save_load.html) || [使用静态图加速](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/accelerate_with_static_graph.html) || [自动混合精度](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/mixed_precision.html) ||"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"# 模型训练\n",
"\n",
"模型训练一般分为四个步骤：\n",
"\n",
"1. 构建数据集。\n",
"2. 定义神经网络模型。\n",
"3. 定义超参、损失函数及优化器。\n",
"4. 输入数据集进行训练与评估。\n",
"\n",
"现在我们有了数据集和模型后，可以进行模型的训练与评估。"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"## 构建数据集\n",
"\n",
"首先从[数据加载与处理](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/dataset.html)加载代码，构建数据集。"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading data from https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/MNIST_Data.zip (10.3 MB)\n",
"\n",
"file_sizes: 100%|██████████████████████████| 10.8M/10.8M [00:05<00:00, 2.07MB/s]\n",
"Extracting zip file...\n",
"Successfully downloaded / unzipped to ./\n"
]
}
],
"source": [
"import mindspore\n",
"from mindspore import nn\n",
"from mindspore.dataset import vision, transforms\n",
"from mindspore.dataset import MnistDataset\n",
"\n",
"# Download data from open datasets\n",
"from download import download\n",
"\n",
"url = \"https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/\" \\\n",
" \"notebook/datasets/MNIST_Data.zip\"\n",
"path = download(url, \"./\", kind=\"zip\", replace=True)\n",
"\n",
"\n",
"def datapipe(path, batch_size):\n",
" image_transforms = [\n",
" vision.Rescale(1.0 / 255.0, 0),\n",
" vision.Normalize(mean=(0.1307,), std=(0.3081,)),\n",
" vision.HWC2CHW()\n",
" ]\n",
" label_transform = transforms.TypeCast(mindspore.int32)\n",
"\n",
" dataset = MnistDataset(path)\n",
" dataset = dataset.map(image_transforms, 'image')\n",
" dataset = dataset.map(label_transform, 'label')\n",
" dataset = dataset.batch(batch_size)\n",
" return dataset\n",
"\n",
"train_dataset = datapipe('MNIST_Data/train', batch_size=64)\n",
"test_dataset = datapipe('MNIST_Data/test', batch_size=64)"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"## 定义神经网络模型\n",
"\n",
"从[网络构建](https://www.mindspore.cn/tutorials/zh-CN/r2.4.10/beginner/model.html)中加载代码，构建一个神经网络模型。"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"class Network(nn.Cell):\n",
" def __init__(self):\n",
" super().__init__()\n",
" self.flatten = nn.Flatten()\n",
" self.dense_relu_sequential = nn.SequentialCell(\n",
" nn.Dense(28*28, 512),\n",
" nn.ReLU(),\n",
" nn.Dense(512, 512),\n",
" nn.ReLU(),\n",
" nn.Dense(512, 10)\n",
" )\n",
"\n",
" def construct(self, x):\n",
" x = self.flatten(x)\n",
" logits = self.dense_relu_sequential(x)\n",
" return logits\n",
"\n",
"model = Network()"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"## 定义超参、损失函数和优化器\n",
"\n",
"### 超参\n",
"\n",
"超参（Hyperparameters）是可以调整的参数，可以控制模型训练优化的过程，不同的超参数值可能会影响模型训练和收敛速度。目前深度学习模型多采用批量随机梯度下降算法进行优化，随机梯度下降算法的原理如下：\n",
"\n",
"$$w_{t+1}=w_{t}-\\eta \\frac{1}{n} \\sum_{x \\in \\mathcal{B}} \\nabla l\\left(x, w_{t}\\right)$$\n",
"\n",
"公式中，$n$是批量大小（batch size），$η$是学习率（learning rate）。另外，$w_{t}$为训练轮次$t$中的权重参数，$\\nabla l$为损失函数的导数。除了梯度本身，这两个因子直接决定了模型的权重更新，从优化本身来看，它们是影响模型性能收敛最重要的参数。一般会定义以下超参用于训练：\n",
"\n",
"- **训练轮次（epoch）**：训练时遍历数据集的次数。\n",
"\n",
"- **批次大小（batch size）**：数据集进行分批读取训练，设定每个批次数据的大小。batch size过小，花费时间多，同时梯度震荡严重，不利于收敛；batch size过大，不同batch的梯度方向没有任何变化，容易陷入局部极小值，因此需要选择合适的batch size，可以有效提高模型精度、全局收敛。\n",
"\n",
"- **学习率（learning rate）**：如果学习率偏小，会导致收敛的速度变慢，如果学习率偏大，则可能会导致训练不收敛等不可预测的结果。梯度下降法被广泛应用在最小化模型误差的参数优化算法上。梯度下降法通过多次迭代，并在每一步中最小化损失函数来预估模型的参数。学习率就是在迭代过程中，会控制模型的学习进度。"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"epochs = 3\n",
"batch_size = 64\n",
"learning_rate = 1e-2"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"### 损失函数\n",
"\n",
"损失函数（loss function）用于评估模型的预测值（logits）和目标值（targets）之间的误差。训练模型时，随机初始化的神经网络模型开始时会预测出错误的结果。损失函数会评估预测结果与目标值的相异程度，模型训练的目标即为降低损失函数求得的误差。\n",
"\n",
"常见的损失函数包括用于回归任务的`nn.MSELoss`（均方误差）和用于分类的`nn.NLLLoss`（负对数似然）等。 `nn.CrossEntropyLoss` 结合了`nn.LogSoftmax`和`nn.NLLLoss`，可以对logits 进行归一化并计算预测误差。"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"loss_fn = nn.CrossEntropyLoss()"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"### 优化器\n",
"\n",
"模型优化（Optimization）是在每个训练步骤中调整模型参数以减少模型误差的过程。MindSpore提供多种优化算法的实现，称之为优化器（Optimizer）。优化器内部定义了模型的参数优化过程（即梯度如何更新至模型参数），所有优化逻辑都封装在优化器对象中。在这里，我们使用SGD（Stochastic Gradient Descent）优化器。\n",
"\n",
"我们通过`model.trainable_params()`方法获得模型的可训练参数，并传入学习率超参来初始化优化器。"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"optimizer = nn.SGD(model.trainable_params(), learning_rate=learning_rate)"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"> 在训练过程中，通过微分函数可计算获得参数对应的梯度，将其传入优化器中即可实现参数优化，具体形态如下：\n",
">\n",
"> grads = grad_fn(inputs)\n",
">\n",
"> optimizer(grads)\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"## 训练与评估\n",
"\n",
"设置了超参、损失函数和优化器后，我们就可以循环输入数据来训练模型。一次数据集的完整迭代循环称为一轮（epoch）。每轮执行训练时包括两个步骤：\n",
"\n",
"1. 训练：迭代训练数据集，并尝试收敛到最佳参数。\n",
"2. 验证/测试：迭代测试数据集，以检查模型性能是否提升。\n",
"\n",
"接下来我们定义用于训练的`train_loop`函数和用于测试的`test_loop`函数。"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"使用函数式自动微分，需先定义正向函数`forward_fn`，使用[value_and_grad](https://www.mindspore.cn/docs/zh-CN/r2.4.10/api_python/mindspore/mindspore.value_and_grad.html)获得微分函数`grad_fn`。然后，我们将微分函数和优化器的执行封装为`train_step`函数，接下来循环迭代数据集进行训练即可。"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"# Define forward function\n",
"def forward_fn(data, label):\n",
" logits = model(data)\n",
" loss = loss_fn(logits, label)\n",
" return loss, logits\n",
"\n",
"# Get gradient function\n",
"grad_fn = mindspore.value_and_grad(forward_fn, None, optimizer.parameters, has_aux=True)\n",
"\n",
"# Define function of one-step training\n",
"def train_step(data, label):\n",
" (loss, _), grads = grad_fn(data, label)\n",
" optimizer(grads)\n",
" return loss\n",
"\n",
"def train_loop(model, dataset):\n",
" size = dataset.get_dataset_size()\n",
" model.set_train()\n",
" for batch, (data, label) in enumerate(dataset.create_tuple_iterator()):\n",
" loss = train_step(data, label)\n",
"\n",
" if batch % 100 == 0:\n",
" loss, current = loss.asnumpy(), batch\n",
" print(f\"loss: {loss:>7f} [{current:>3d}/{size:>3d}]\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"`test_loop`函数同样需循环遍历数据集，调用模型计算loss和Accuray并返回最终结果。"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"def test_loop(model, dataset, loss_fn):\n",
" num_batches = dataset.get_dataset_size()\n",
" model.set_train(False)\n",
" total, test_loss, correct = 0, 0, 0\n",
" for data, label in dataset.create_tuple_iterator():\n",
" pred = model(data)\n",
" total += len(data)\n",
" test_loss += loss_fn(pred, label).asnumpy()\n",
" correct += (pred.argmax(1) == label).asnumpy().sum()\n",
" test_loss /= num_batches\n",
" correct /= total\n",
" print(f\"Test: \\n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"我们将实例化的损失函数和优化器传入`train_loop`和`test_loop`中。训练3轮并输出loss和Accuracy，查看性能变化。"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1\n",
"-------------------------------\n",
"loss: 2.302806 [ 0/938]\n",
"loss: 2.285086 [100/938]\n",
"loss: 2.264712 [200/938]\n",
"loss: 2.174010 [300/938]\n",
"loss: 1.931853 [400/938]\n",
"loss: 1.340721 [500/938]\n",
"loss: 0.953515 [600/938]\n",
"loss: 0.756860 [700/938]\n",
"loss: 0.756263 [800/938]\n",
"loss: 0.463846 [900/938]\n",
"Test: \n",
" Accuracy: 84.7%, Avg loss: 0.527155 \n",
"\n",
"Epoch 2\n",
"-------------------------------\n",
"loss: 0.479126 [ 0/938]\n",
"loss: 0.437443 [100/938]\n",
"loss: 0.685504 [200/938]\n",
"loss: 0.395121 [300/938]\n",
"loss: 0.550566 [400/938]\n",
"loss: 0.459457 [500/938]\n",
"loss: 0.293049 [600/938]\n",
"loss: 0.422102 [700/938]\n",
"loss: 0.333153 [800/938]\n",
"loss: 0.412182 [900/938]\n",
"Test: \n",
" Accuracy: 90.5%, Avg loss: 0.335083 \n",
"\n",
"Epoch 3\n",
"-------------------------------\n",
"loss: 0.207366 [ 0/938]\n",
"loss: 0.343559 [100/938]\n",
"loss: 0.391145 [200/938]\n",
"loss: 0.317566 [300/938]\n",
"loss: 0.200746 [400/938]\n",
"loss: 0.445798 [500/938]\n",
"loss: 0.603720 [600/938]\n",
"loss: 0.170811 [700/938]\n",
"loss: 0.411954 [800/938]\n",
"loss: 0.315902 [900/938]\n",
"Test: \n",
" Accuracy: 91.9%, Avg loss: 0.279034 \n",
"\n",
"Done!\n"
]
}
],
"source": [
"loss_fn = nn.CrossEntropyLoss()\n",
"optimizer = nn.SGD(model.trainable_params(), learning_rate=learning_rate)\n",
"\n",
"for t in range(epochs):\n",
" print(f\"Epoch {t+1}\\n-------------------------------\")\n",
" train_loop(model, train_dataset)\n",
" test_loop(model, test_dataset, loss_fn)\n",
"print(\"Done!\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "MindSpore",
"language": "python",
"name": "mindspore"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5 (default, Oct 25 2019, 15:51:11) \n[GCC 7.3.0]"
},
"vscode": {
"interpreter": {
"hash": "8c9da313289c39257cb28b126d2dadd33153d4da4d524f730c81a4aaccbd2ca7"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}