python手寫數字識別（PaddlePaddle框架、MNIST數據集）

import paddle
import paddle.nn.functional as F
from paddle.vision.transforms import Compose, Normalizetransform = Compose([Normalize(mean=[127.5],std=[127.5],data_format='CHW')])
# 使用transform對數據集做歸一化
print('download training data and load training data')
# 使用飛槳框架自帶的 paddle.vision.datasets.MNIST 完成mnist數據集的加載
train_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
test_dataset = paddle.vision.datasets.MNIST(mode='test', transform=transform)
print('load finished')# 用paddle.nn下的API，如Conv2D、MaxPool2D、Linear完成卷積神經網絡的構建
class CNN(paddle.nn.Layer):def __init__(self):super().__init__()self.conv1 = paddle.nn.Conv2D(in_channels=1, out_channels=6, kernel_size=5, stride=1, padding=2)self.max_pool1 = paddle.nn.MaxPool2D(kernel_size=2,  stride=2)self.conv2 = paddle.nn.Conv2D(in_channels=6, out_channels=16, kernel_size=5, stride=1)self.max_pool2 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)self.linear1 = paddle.nn.Linear(in_features=16*5*5, out_features=120)self.linear2 = paddle.nn.Linear(in_features=120, out_features=84)self.linear3 = paddle.nn.Linear(in_features=84, out_features=10)def forward(self, x):x = self.conv1(x)x = F.relu(x)x = self.max_pool1(x)x = self.conv2(x)x = F.relu(x)x = self.max_pool2(x)x = paddle.flatten(x, start_axis=1,stop_axis=-1)x = self.linear1(x)x = F.relu(x)x = self.linear2(x)x = F.relu(x)x = self.linear3(x)return x# 開始對模型進行訓練，先構建train_loader，加載訓練數據，然后定義train函數，設置好損失函數后，按batch加載數據，完成模型的訓練
train_loader = paddle.io.DataLoader(train_dataset, batch_size=128, shuffle=True)
# 加載訓練集 batch_size 設為 128
def train(model):model.train()epochs = 3optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())# 用Adam作為優化函數print("Training:")for epoch in range(epochs):for batch_id, data in enumerate(train_loader()):x_data = data[0]y_data = data[1]predicts = model(x_data)loss = F.cross_entropy(predicts, y_data)# 計算損失acc = paddle.metric.accuracy(predicts, y_data)loss.backward()if batch_id % 300 == 0:print("epoch: {}, batch_id: {}, loss is: {}, acc is: {}".format(epoch, batch_id, loss.numpy(), acc.numpy()))optim.step()optim.clear_grad()
model = CNN()
train(model)# 訓練完成后，需要驗證模型的效果，此時，加載測試數據集，然后用訓練好的模對測試集進行預測，計算損失與精度。
test_loader = paddle.io.DataLoader(test_dataset, places=paddle.CPUPlace(), batch_size=128)
# 加載測試數據集
def test(model):model.eval()print("Testing:")for batch_id, data in enumerate(test_loader()):x_data = data[0]y_data = data[1]predicts = model(x_data)# 獲取預測結果loss = F.cross_entropy(predicts, y_data)acc = paddle.metric.accuracy(predicts, y_data)if batch_id % 50 == 0:print("batch_id: {}, loss is: {}, acc is: {}".format(batch_id, loss.numpy(), acc.numpy()))
test(model)