PaddlePaddle笔记2-手写数字识别

睿洛医疗​​​​​​​

1，构造数据集

def structure_dataset():
    train_dataset = MNIST(mode='train', transform=ToTensor())
    test_dataset = MNIST(mode='test', transform=ToTensor())
    return train_dataset,test_dataset

查看数据集中的图像，看前64张

plt.figure()
for r in range(0,8):
    for c in range(0, 8):
        image = np.array(test_dataset.images[r*8+c]).reshape(28, 28)
        plt.subplot(8, 8, r*8+c+1)
        plt.axis('off')
        plt.imshow(image)

plt.show()

2，构造模型

class MyModel(Layer):
    def __init__(self):
        super(MyModel, self).__init__()
        self.conv1 = paddle.nn.Conv2D(in_channels=1, out_channels=6, kernel_size=5, stride=1, padding=2)
        self.max_pool1 = MaxPool2D(kernel_size=2, stride=2)
        self.conv2 = Conv2D(in_channels=6, out_channels=16, kernel_size=5, stride=1)
        self.max_pool2 = MaxPool2D(kernel_size=2, stride=2)
        self.linear1 = Linear(in_features=16*5*5, out_features=120)
        self.linear2 = Linear(in_features=120, out_features=84)
        self.linear3 = 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 = F.relu(x)
        x = self.conv2(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

3，训练模型

def train(epochs,modelname = "None"):
    train_dataset, test_dataset = structure_dataset()

    inputs = InputSpec([None, 784], 'float32', 'x')
    labels = InputSpec([None, 10], 'float32', 'x')
    model = paddle.Model(MyModel(), inputs, labels)
    optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())

    if modelname is not "None":
        model.load(modelname)

    model.prepare(
        optim,
        # paddle.nn.CrossEntropyLoss(),
        paddle.nn.loss.CrossEntropyLoss(),
        Accuracy()
    )

    model.fit(train_dataset,
              test_dataset,
              epochs=epochs,
              batch_size=64,
              save_dir='mnist_checkpoint',
              verbose=1)

    # 模型评估
    model.evaluate(test_dataset, verbose=1)

    # 保存模型和优化器参数信息
    model.save('./model/recognition_numeral')

4，加载模型预测

def predict(test_dataset):
    inputs = InputSpec([None, 784], 'float32', 'x')
    labels = InputSpec([None, 10], 'float32', 'x')
    model = paddle.Model(MyModel(), inputs, labels)
    optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())
    # 高阶API加载模型
    model.load('./model/recognition_numeral')
    model.prepare(
        optim,
        paddle.nn.loss.CrossEntropyLoss(),
        Accuracy()
    )
    # 预测
    pred_result = model.predict(test_dataset)
    return pred_result