## 將圖像數據轉換成圖像張量
transform = transforms.Compose([
    transforms.ToTensor(),
    # 標準化,均值和標準差
    transforms.Normalize((0.1307,), (0.3081,))
    ])

# -*- coding: utf-8 -*-
"""
Created on Wed Aug  4 09:08:32 2021

@author: motoh
"""

import torch
## 對圖像數據進行處理的包
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
 
# prepare dataset
 
batch_size = 64
## 將圖像數據轉換成圖像張量
# 標準化,均值和標準差
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) 
 
train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)
 

# design model using class
 
 
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)
 
    def forward(self, x):
        #變成矩陣 -1其實就是自動獲取mini_batch，784是1*28*28，圖片的像素數量
        x = x.view(-1, 784) 
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        # 最后一層不做激活，不進行非線性變換
        return self.l5(x)  
 
 
model = Net()
 
# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
 
# training cycle forward, backward, update
 
 
def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        # 獲得一個批次的數據和標簽
        inputs, target = data
        optimizer.zero_grad()
        # 獲得模型預測結果(64, 10)
        outputs = model(inputs)
        # 交叉熵代價函數outputs(64,10),target（64）
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
 
        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))
            running_loss = 0.0
 
 
def test():
    correct = 0
    total = 0
    ## 不計算梯度
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            # dim = 1 列是第0個維度，行是第1個維度，## 每一行最大值的下標
            _, predicted = torch.max(outputs.data, dim=1) 
            total += labels.size(0)
            correct += (predicted == labels).sum().item() # 張量之間的比較運算
    print('accuracy on test set: %d %% ' % (100*correct/total))
 
 
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()