1. Dimension of weight_softmax[idx] and features channel 2. Upsampling (directly resize)?

[qsunyuan]

Meet this interesting work so late.

Here is my little doubt.

CAM/pytorch_CAM.py

Line 48 in c63f285

cam = weight_softmax[idx].dot(feature_conv.reshape((nc, h*w)))

1. The dimension of weight_softmax[idx] should be 512. However, for layer4's nc, it should be 256. Is there a mistake here? In other words, I suspect that CAM can only be used for the last layer, so as to match the dimension of 512.
2. Is there a better process for upsampling the final class activation map? I feel the resize is a bit rough.

[qsunyuan]

The resize code link:

CAM/pytorch_CAM.py

Line 94 in c63f285

heatmap = cv2.applyColorMap(cv2.resize(CAMs[0],(width, height)), cv2.COLORMAP_JET)