利用pytorch实现Visualising Image Classification Models and Saliency Maps

def compute_saliency_maps(X, y, model):
    """
    使用模型图像(image)X和标记(label)y计算正确类的saliency map.

    输入:
    - X: 输入图像; Tensor of shape (N, 3, H, W)
    - y: 对应X的标记; LongTensor of shape (N,)
    - model: 一个预先训练好的神经网络模型用于计算X.

    返回值:
    - saliency: A Tensor of shape (N, H, W) giving the saliency maps for the input
    images.
    """
    # Make sure the model is in "test" mode
    model.eval()

    # Wrap the input tensors in Variables
    X_var = Variable(X, requires_grad=True)
    y_var = Variable(y)
    saliency = None
    ##############################################################################
    #
    # 首先进行前向操作，将输入图像pass through已经训练好的model，再进行反向操作，
    # 从而得到对应图像,正确分类分数的梯度
    # 
    ##############################################################################

    # 前向操作
    scores = model(X_var)

    # 得到正确类的分数，scores为[5]的Tensor
    scores = scores.gather(1, y_var.view(-1, 1)).squeeze() 

    #反向计算，从输出的分数到输入的图像进行一系列梯度计算
    scores.backward(torch.FloatTensor([1.0,1.0,1.0,1.0,1.0])) # 参数为对应长度的梯度初始化
#     scores.backward() 必须有参数，因为此时的scores为非标量，为5个元素的向量

    # 得到正确分数对应输入图像像素点的梯度
    saliency = X_var.grad.data

    saliency = saliency.abs() # 取绝对值
    saliency, i = torch.max(saliency,dim=1)  # 从3个颜色通道中取绝对值最大的那个通道的数值
    saliency = saliency.squeeze() # 去除1维
#     print(saliency)

    return saliency

def show_saliency_maps(X, y):
    # Convert X and y from numpy arrays to Torch Tensors
    X_tensor = torch.cat([preprocess(Image.fromarray(x)) for x in X], dim=0)
    y_tensor = torch.LongTensor(y)

    # Compute saliency maps for images in X
    saliency = compute_saliency_maps(X_tensor, y_tensor, model)

    # Convert the saliency map from Torch Tensor to numpy array and show images
    # and saliency maps together.
    saliency = saliency.numpy()
    N = X.shape[0]

    for i in range(N):
        plt.subplot(2, N, i + 1)
        plt.imshow(X[i])
        plt.axis('off')
        plt.title(class_names[y[i]])
        plt.subplot(2, N, N + i + 1)
        plt.imshow(saliency[i], cmap=plt.cm.hot)
        plt.axis('off')
        plt.gcf().set_size_inches(12, 5)
    plt.show()

show_saliency_maps(X, y)

    out = model( X_var )  
    loss_func = torch.nn.CrossEntropyLoss()
    loss = loss_func( out, y_var ) 
    loss.backward()
    grads = X_var.grad
    grads = grads.abs()
    mx, index_mx = torch.max( grads, 1 )
#     print(mx, index_mx)
    saliency = mx.data
#     print(saliency)