Question

为什么Matplotlib不起作用？我有NN，想绘制一个图，但没有用！

# Train the network 
num_epochs = 200
loss_X = []
loss_Y = []
loss_Y_test = []
for epoch in range(num_epochs):
    for inputs,labels in train_loader:
        inputs = inputs.float()
        labels = labels.float()
        # Feed Forward
        output = net(inputs)
        # Loss Calculation
        loss = criterion(output, labels)
        # Clear the gradient buffer (we don't want to accumulate gradients)
        optimizer.zero_grad()
        # Backpropagation 
        loss.backward()
        # Weight Update: w <-- w - lr * gradient
        optimizer.step()
        loss_X.append(epoch)
        loss_Y.append(loss)

        # Test the the network 
        for inputs_T,labels_T in test_loader:
            inputs_T = inputs_T.float()
            labels_T = labels_T.float()
            # Feed Forward
            output_T = net(inputs_T)
            # Loss Calculation
            loss_T = criterion(output_T, labels_T)
            # Clear the gradient buffer (we don't want to accumulate gradients)
            optimizer.zero_grad()
            # Backpropagation 
            loss_T.backward()
            # Weight Update: w <-- w - lr * gradient
            optimizer.step()
            loss_Y_test.append(loss_T)

    #Accuracy
    # Since we are using a sigmoid, we will need to perform some thresholding
    output = (output>0.5).float()
    output_T = (output_T>0.5).float()
    # Accuracy: (output == labels).float().sum() / output.shape[0]
    accuracy = (output == labels).float().mean()
    accuracy_T = (output_T == labels_T).float().mean()
    # Print statistics 
    #print("Epoch {}/{}, Loss: {:.3f},Loss_T: {:.3f}, Accuracy: {:.3f}, Accuracy_T: {:.3f}".format(epoch+1,num_epochs, loss,loss_T, accuracy, accuracy_T))
    print("Epoch {}, Loss: {:.3f},Loss_T: {:.3f}".format(epoch+1, loss,loss_T))

这是绘制火车和测试图的飞行员代码

import matplotlib.pyplot as plt
plt.plot(loss_X, loss_Y, label="train")
plt.plot(loss_X, loss_Y_test, label="test")
plt.ylim([0, 2000])
plt.legend()
plt.savefig("chech.png")
plt.show()

这是错误消息“只能将一个元素张量转换为Python标量”

ValueError                                Traceback (most recent call last)
<ipython-input-1196-8a4ea3f00ea2> in <module>
----> 1 plt.plot(loss_X, loss_Y, label="train")
      2 plt.plot(loss_X, loss_Y_test, label="test")
      3 plt.ylim([0, 2000])
      4 plt.legend()
      5 plt.savefig("chech.png")

ValueError: only one element tensors can be converted to Python scalars

如何使用x = epoch，y = train，z = test进行绘图？

为什么Matplotlib绘图功能不起作用

0 个答案: