影象分類通用測試程式碼

損失函式

損失函式 nn.CrossEntropyLoss。nn.CrossEntropyLoss()是nn.logSoftmax()和nn.NLLLoss()的整合,可以直接使用它來替換網路中的這兩個操作，這個函式可以用於多分類問題。函式的引數：weight(Tensor, optional)：如果輸入這個引數的話必須是一個1維的tensor，長度為類別數C，每個值對應每一類的權重。reduction (string, optional) ：指定最終的輸出型別，預設為‘mean’。

優化器

pytorch中常用的四種優化器。SGD、Momentum、RMSProp、Adam。

opt_SGD = torch.optim.SGD(net_SGD.parameters(),lr=LR)
opt_Momentum = torch.optim.SGD(net_Momentum.parameters(),lr=LR,momentum=0.8)
opt_RMSprop = torch.optim.RMSprop(net_RMSprop.parameters(),lr=LR,alpha=0.9)
opt_Adam = torch.optim.Adam(net_Adam.parameters(),lr=LR,betas=(0.9,0.99))

SGD 是最普通的優化器, 也可以說沒有加速效果, 而 Momentum 是 SGD 的改良版, 它加入了動量原則。後面的 RMSprop 又是 Momentum 的升級版。而 Adam 又是 RMSprop 的升級版。不過，並不是越先進的優化器, 結果越佳。
這裡用的優化器optim.Adam

網路訓練

每一個epoch進行一次訓練和測試。對於訓練，將訓練引數傳入網路net.train()，定義執行時的損失以及開始時間初始化。

net.train()
running_loss = 0.0
t1 = time.perf_counter()
for step, data in enumerate(train_loader, start=0):
	images,labels = data
	optimizer.zero_grad()
	outputs = net(images.to(device))
	loss = loss_function(outputs,labels.to(device))
	loss.backward()
	optimizer.step()
	running_loss += loss.item()
	rate = (step + 1) / len(train_loader)
	a ="*" * int(rate * 50)
	b ="." * int((1-rate) * 50)
	print("\rtrain loss: {:^3.0f}%[{}->{}]{:.f}".format(int(rate * 100), a, b, loss), end="")
print()
print(time.perf_counter()-t1)
 

總程式碼下

    net = AlexNet(num_classes=5,init_weights=True)
    net.to(device)
    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.0002)
    save_path = './AlexNet.pth'
    best_acc = 0.0
    for epoch in range(10):
        net.train()
        running_loss = 0.0
        t1 = time.perf_counter()
        for step, data in enumerate(train_loader, start=0):
            images,labels = data
            optimizer.zero_grad()
            outputs = net(images.to(device))
            loss = loss_function(outputs,labels.to(device))
            loss.backward()
            optimizer.step()
            running_loss += loss.item()
            rate = (step + 1) / len(train_loader)
            a ="*" * int(rate * 50)
            b ="." * int((1-rate) * 50)
            print("\rtrain loss: {:^3.0f}%[{}->{}]{:.f}".format(int(rate * 100), a, b, loss), end="")
        print()
        print(time.perf_counter()-t1)
        net.eval()
        acc = 0.0
        with torch.no_grad():
            for val_data in validate_loader:
                val_images,val_labels = val_data
                outputs = net(val_images.to(device))
                predict_y = torch.max(outputs, dim=1)[1]
                acc += (predict_y == val_labels.to(device)).sum().item()
            val_accurate = acc / val_num
            if val_accurate > best_acc:
                best_acc = val_accurate
                torch.save(net.state_dict(), save_path)
            print('[epoch %d] train_loss: %.3f test_accuracy；%.3f' % (epoch + 1, running_loss / step, val_accurate))
    print('Finished Training')