通过极简方案快速构建手写数字识别模型

通过极简方案快速构建手写数字识别模型

import paddle
from paddle.nn import Linear
import paddle.nn.functional as F
import os
import numpy as np
import matplotlib.pyplot as plt

train_dataset = paddle.vision.datasets.MNIST(mode='train')

train_data0 = np.array(train_dataset[0][0])
train_label_0 = np.array(train_dataset[0][1])

import matplotlib.pyplot as plt
plt.figure("Image") 
plt.figure(figsize=(2,2))
plt.imshow(train_data0, cmap=plt.cm.binary)
plt.axis('on')
plt.title('image') 
plt.show()

print("图像数据形状和对应数据为:", train_data0.shape)
print("图像标签形状和对应数据为:", train_label_0.shape, train_label_0)
print("\n打印第一个batch的第一个图像，对应标签数字为{}".format(train_label_0))

class MNIST(paddle.nn.Layer):
    def __init__(self):
        super(MNIST, self).__init__()
        
        self.fc = paddle.nn.Linear(in_features=784, out_features=1)
        
    def forward(self, inputs):
        outputs = self.fc(inputs)
        return outputs

model = MNIST()

def train(model):
    model.train()
    train_loader = paddle.io.DataLoader(paddle.vision.datasets.MNIST(mode='train'), 
                                        batch_size=16, 
                                        shuffle=True)
    opt = paddle.optimizer.SGD(learning_rate=0.001, parameters=model.parameters())

def norm_img(img):
    assert len(img.shape) == 3
    batch_size, img_h, img_w = img.shape[0], img.shape[1], img.shape[2]
    img = img / 255
    img = paddle.reshape(img, [batch_size, img_h*img_w])
    
    return img

import paddle
paddle.vision.set_image_backend('cv2')

model = MNIST()

def train(model):
    model.train()
    train_loader = paddle.io.DataLoader(paddle.vision.datasets.MNIST(mode='train'), 
                                        batch_size=16, 
                                        shuffle=True)
    opt = paddle.optimizer.SGD(learning_rate=0.0000001, 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')
            
            predicts = model(images)
            
            loss = F.square_error_cost(predicts, labels)
            avg_loss = paddle.mean(loss)

            if batch_id % 1000 == 0:
                print("epoch_id: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, avg_loss.numpy()))
            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'
im = Image.open('./work/example_0.jpg')
plt.imshow(im)
plt.show()
im = im.convert('L')
print('原始图像shape: ', np.array(im).shape)
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):
    im = Image.open(img_path).convert('L')
    im = im.resize((28, 28), Image.ANTIALIAS)
    im = np.array(im).reshape(1, -1).astype(np.float32)
    im = 1 - im / 255
    return im

model = MNIST()
params_file_path = 'mnist.pdparams'
img_path = './work/example_0.jpg'
param_dict = paddle.load(params_file_path)
model.load_dict(param_dict)
model.eval()
tensor_img = load_image(img_path)
result = model(paddle.to_tensor(tensor_img))
print('result',result)
print("本次预测的数字是", result.numpy().astype('int32'))