Closed lifuguan closed 2 years ago
You should not save kernels, but the masks. The paper says "... the average of mask activations of the 100 instance kernels over the 5000 images in the val split. " Thus, the mask predictions after sigmoid are saved and averaged, rather than the kernels.
Hello, Sorry to disturb you. I'm trying to visualize the kernels (called
object_feats
in your code). It've been illustrated in your paper. Here is my code, which aims to save and add them onkernels.npy
during the inference phrase.However, the result is completely different from your figures:
It will be appreciated if anyone can show me the way to visualize kernel correctly.