ShiningRain

Grad_cam++的实现和原文的计算公式不一致，请问怎么理解

3

norm_factor = np.sum(gradient, axis=(1, 2)) # [C]归一化 for i in range(len(norm_factor)): norm_factor[i] = 1. / norm_factor[i] if norm_factor[i] > 0. else 0. # 避免除零 alpha = indicate * norm_factor[:, np.newaxis,...

I always meet the following error when training. Anyone know what's going on here? ?

4

Traceback (most recent call last): File "train_previous_mask.py", line 384, in trainIters(args) File "train_previous_mask.py", line 252, in trainIters loaders = init_dataloaders(args) File "train_previous_mask.py", line 50, in init_dataloaders use_prev_mask = False) #use_prev_mask...

About QUICK_START.md.

2

There's nothing in QUICK_START.md.

Can you give the reference of channel_unet? I want to cite it. Thank you very much !!!

About resluts

1

Why did I get such a bad result? Objects cannot be segmented.