手写字体识别

class MNIST(paddle.nn.Layer):
    def __init__(self):
        super(MNIST, self).__init__()
        
        # 定义一层全连接层，输出维度是1
        self.fc = paddle.nn.Linear(in_features=784, out_features=1)
        
    # 定义网络结构的前向计算过程
    def forward(self, inputs):
        outputs = self.fc(inputs)
        return outputs

model = MNIST()

def train(model):
    # 启动训练模式
    model.train()
    # 加载训练集 batch_size 设为 16
    train_loader = paddle.io.DataLoader(paddle.vision.datasets.MNIST(mode='train'), 
                                        batch_size=16, 
                                        shuffle=True)
    # 定义优化器，使用随机梯度下降SGD优化器，学习率设置为0.001
    opt = paddle.optimizer.SGD(learning_rate=0.001, parameters=model.parameters())


def norm_img(img):
    # 验证传入数据格式是否正确，img的shape为[batch_size, 28, 28]
    assert len(img.shape) == 3
    batch_size, img_h, img_w = img.shape[0], img.shape[1], img.shape[2]
    # 归一化图像数据
    img = img / 255
    # 将图像形式reshape为[batch_size, 784]
    img = paddle.reshape(img, [batch_size, img_h*img_w])
    
    return img

import paddle
# 确保从paddle.vision.datasets.MNIST中加载的图像数据是np.ndarray类型
paddle.vision.set_image_backend('cv2')

# 声明网络结构
model = MNIST()

def train(model):
    # 启动训练模式
    model.train()
    # 加载训练集 batch_size 设为 16
    train_loader = paddle.io.DataLoader(paddle.vision.datasets.MNIST(mode='train'), 
                                        batch_size=16, 
                                        shuffle=True)
    # 定义优化器，使用随机梯度下降SGD优化器，学习率设置为0.001
    opt = paddle.optimizer.SGD(learning_rate=0.001, parameters=model.parameters())
    EPOCH_NUM = 10
    for epoch in range(EPOCH_NUM):
        for batch_id, data in enumerate(train_loader()):
            images = norm_img(data[0]).astype('float32')
            labels = data[1].astype('float32')
            
            #前向计算的过程
            predicts = model(images)
            
            # 计算损失
            loss = F.square_error_cost(predicts, labels)
            avg_loss = paddle.mean(loss)
            
            #每训练了1000批次的数据，打印下当前Loss的情况
            if batch_id % 1000 == 0:
                print("epoch_id: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, avg_loss.numpy()))
            
            #后向传播，更新参数的过程
            avg_loss.backward()
            opt.step()
            opt.clear_grad()
            
train(model)
paddle.save(model.state_dict(), './mnist.pdparams')

import matplotlib.pyplot as plt
import numpy as np
from PIL import Image

img_path = './work/example_0.jpg'
# 读取原始图像并显示
im = Image.open('./work/example_0.jpg')
plt.imshow(im)
plt.show()
# 将原始图像转为灰度图
im = im.convert('L')
print('原始图像shape: ', np.array(im).shape)
# 使用Image.ANTIALIAS方式采样原始图片
im = im.resize((28, 28), Image.ANTIALIAS)
plt.imshow(im)
plt.show()
print("采样后图片shape: ", np.array(im).shape)

def load_image(img_path):
    # 从img_path中读取图像，并转为灰度图
    im = Image.open(img_path).convert('L')
    # print(np.array(im))
    im = im.resize((28, 28), Image.ANTIALIAS)
    im = np.array(im).reshape(1, -1).astype(np.float32)
    # 图像归一化，保持和数据集的数据范围一致
    im = 1 - im / 255
    return im

# 定义预测过程
model = MNIST()
params_file_path = 'mnist.pdparams'
img_path = './work/example_0.jpg'
# 加载模型参数
param_dict = paddle.load(params_file_path)
model.load_dict(param_dict)
# 灌入数据
model.eval()
tensor_img = load_image(img_path)
result = model(paddle.to_tensor(tensor_img))
print('result',result)
#  预测输出取整，即为预测的数字，打印结果
print("本次预测的数字是", result.numpy().astype('int32'))

正确识别手写字体2：