运行GradCAM可视化时出错

Question

我使用开源Pytorch Grad CAM代码来可视化我的模型，如下所示：

classifier = cnn.CNN(in_shape=(1,28,28), n_classes=10).cuda()

Grad-CAM实现来自这里：https://github.com/jacobgil/pytorch-grad-cam/

然而，当我跑的时候

def preprocess_image(img):
    means = [0.485, 0.456, 0.406]
    stds = [0.229, 0.224, 0.225]

    preprocessed_img = img.copy()[:, :, ::-1]
    for i in range(3):
        preprocessed_img[:, :, i] = preprocessed_img[:, :, i] - means[i]
        preprocessed_img[:, :, i] = preprocessed_img[:, :, i] / stds[i]
    preprocessed_img = \
        np.ascontiguousarray(np.transpose(preprocessed_img, (2, 0, 1)))
    preprocessed_img = torch.from_numpy(preprocessed_img)
    preprocessed_img.unsqueeze_(0)
    input = preprocessed_img.requires_grad_(True)
    return input

model = classifier
grad_cam = GradCam(model=model, feature_module=model.features, target_layer_names=["2"], use_cuda=True)

img = cv2.imread('/content/drive/My Drive/pic.png', 1)
img = np.float32(cv2.resize(img, (224, 224))) / 255
input = preprocess_image(img)
input = input[:, 0:1, :, :]

target_index = None
mask = grad_cam(input, target_index)
show_cam_on_image(img, mask)

我得到这个错误：

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-30-fe930a4e6b09> in <module>()
    155 # Otherwise, targets the requested index.
    156 target_index = None
--> 157 mask = grad_cam(input, target_index)
    158 show_cam_on_image(img, mask)

6 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in linear(input, weight, bias)
   1674         ret = torch.addmm(bias, input, weight.t())
   1675     else:
-> 1676         output = input.matmul(weight.t())
   1677         if bias is not None:
   1678             output += bias

RuntimeError: mat1 dim 1 must match mat2 dim 0

如果这有帮助，下面是print(model.features)的输出：

Sequential(
  (0): Conv2d(1, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
  (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (2): ReLU(inplace=True)
  (3): Conv2d(16, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (5): ReLU(inplace=True)
  (6): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (7): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (9): ReLU(inplace=True)
  (10): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (11): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (12): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (13): ReLU(inplace=True)
  (14): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)

如何修复此错误并使渐变凸轮按预期运行