LeNet实现MNIST手写数字识别任务

import paddle
print("本教程基于Paddle的版本号为："+paddle.__version__)
transform = Compose([Normalize(mean=[127.5], std=[127.5], data_format='CHW')])
print("下载并加载训练数据")
train_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
test_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
print("加载完成")

LeNet1 = paddle.nn.Sequential(paddle.nn.Conv2D(in_channels=1, out_channels=6, kernel_size=3, stride=1, padding=1),
                              paddle.nn.ReLU(),
                              paddle.nn.MaxPool2D(kernel_size=2, stride=2),
                              paddle.nn.Conv2D(in_channels=6, out_channels=16, kernel_size=5, stride=1, padding=0),
                              paddle.nn.ReLU(),
                              paddle.nn.MaxPool2D(kernel_size=2, stride=2),
                              paddle.nn.Flatten(),
                              paddle.nn.Linear(in_features=400, out_features=120),
                              paddle.nn.Linear(in_features=120, out_features=84),
                              paddle.nn.Linear(in_features=84, out_features=10))
paddle.summary(LeNet1, (1, 1, 28, 28))
model = paddle.Model(LeNet1)
model.prepare(paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters()), paddle.nn.CrossEntropyLoss(),
              paddle.metric.Accuracy())
visualdl = paddle.callbacks.VisualDL(log_dir='visualdl_log')

model.fit(train_dataset,
          epochs=5,
          batch_size=64,
          verbose=1,
          save_dir='F:/PyCharm/PyCharm文件/卷积神经网络实现手写数字识别')
result = model.evaluate(test_dataset, verbose=1)
print(result)