本章主要介绍模型的训练、保存和加载，在第一章中已经学习过，主要是熟悉新的写法，没有其他特殊的处理，核心内容是实现随机梯度下降算法：

模型训练：

        模型训练一般分为四个步骤：

1. 构建数据集。
2. 定义神经网络模型。
3. 定义超参、损失函数及优化器。
4. 输入数据集进行训练与评估。

构建数据集：

import mindspore
from mindspore import nn
from mindspore.dataset import vision, transforms
from mindspore.dataset import MnistDataset

# Download data from open datasets
from download import download

url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/" \
      "notebook/datasets/MNIST_Data.zip"
path = download(url, "./", kind="zip", replace=True)


def datapipe(path, batch_size):
    image_transforms = [
        vision.Rescale(1.0 / 255.0, 0),
        vision.Normalize(mean=(0.1307,), std=(0.3081,)),
        vision.HWC2CHW()
    ]
    label_transform = transforms.TypeCast(mindspore.int32)

    dataset = MnistDataset(path)
    dataset = dataset.map(image_transforms, 'image')
    dataset = dataset.map(label_transform, 'label')
    dataset = dataset.batch(batch_size)
    return dataset

train_dataset = datapipe('MNIST_Data/train', batch_size=64)
test_dataset = datapipe('MNIST_Data/test', batch_size=64)

定义神经网络模型：

class Network(nn.Cell):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.dense_relu_sequential = nn.SequentialCell(
            nn.Dense(28*28, 512),
            nn.ReLU(),
            nn.Dense(512, 512),
            nn.ReLU(),
            nn.Dense(512, 10)
        )

    def construct(self, x):
        x = self.flatten(x)
        logits = self.dense_relu_sequential(x)
        return logits

model = Network()

定义超参、损失函数和优化器： 

## 超参
epochs = 3 # 训练轮次
batch_size = 64 # 批次大小
learning_rate = 1e-2 # 学习率
## 损失函数
loss_fn = nn.CrossEntropyLoss()
## 优化器
optimizer = nn.SGD(model.trainable_params(), learning_rate=learning_rate)

训练与评估：

## 定义前向传播
def forward_fn(data, label):
    logits = model(data)
    loss = loss_fn(logits, label)
    return loss, logits

## 自微分函数
grad_fn = mindspore.value_and_grad(forward_fn, None, optimizer.parameters, has_aux=True)

## 定义一步训练
def train_step(data, label):
    (loss, _), grads = grad_fn(data, label)
    optimizer(grads)
    return loss

## 训练轮训
def train_loop(model, dataset):
    size = dataset.get_dataset_size()
    model.set_train()
    for batch, (data, label) in enumerate(dataset.create_tuple_iterator()):
        loss = train_step(data, label)

        if batch % 100 == 0:
            loss, current = loss.asnumpy(), batch
            print(f"loss: {loss:>7f}  [{current:>3d}/{size:>3d}]")

## 测试轮训
def test_loop(model, dataset, loss_fn):
    num_batches = dataset.get_dataset_size()
    model.set_train(False)
    total, test_loss, correct = 0, 0, 0
    for data, label in dataset.create_tuple_iterator():
        pred = model(data)
        total += len(data)
        test_loss += loss_fn(pred, label).asnumpy()
        correct += (pred.argmax(1) == label).asnumpy().sum()
    test_loss /= num_batches
    correct /= total
    print(f"Test: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
    
loss_fn = nn.CrossEntropyLoss()
optimizer = nn.SGD(model.trainable_params(), learning_rate=learning_rate)

for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train_loop(model, train_dataset)
    test_loop(model, test_dataset, loss_fn)
print("Done!")

保存与加载：

        同样，保存与加载在第一章中也介绍过，熟悉下新的写法。

import numpy as np
import mindspore
from mindspore import nn
from mindspore import Tensor
def network():
    model = nn.SequentialCell(
                nn.Flatten(),
                nn.Dense(28*28, 512),
                nn.ReLU(),
                nn.Dense(512, 512),
                nn.ReLU(),
                nn.Dense(512, 10))
    return model

## 保存模型
model = network()
mindspore.save_checkpoint(model, "model.ckpt")

## 实例化和加载模型
model = network()
param_dict = mindspore.load_checkpoint("model.ckpt")
param_not_load, _ = mindspore.load_param_into_net(model, param_dict)
print(param_not_load)

保存和加载MindIR：

        可使用export接口直接将模型保存为MindIR，同时保存了Checkpoint和模型结构，因此需要定义输入Tensor来获取输入shape。

model = network()
inputs = Tensor(np.ones([1, 1, 28, 28]).astype(np.float32))
mindspore.export(model, inputs, file_name="model", file_format="MINDIR")

mindspore.set_context(mode=mindspore.GRAPH_MODE)

graph = mindspore.load("model.mindir")
model = nn.GraphCell(graph) # 仅支持图模式
outputs = model(inputs)
print(outputs.shape)