medivhna / tf_face_toolbox Goto Github PK

Hi,
I'm really grateful that you share the TF code.
In the file parallel.py, the fully_connected layer is used before the loss layer, then the softmax loss and regularization_loss are calculated in the loss_function. I don't find where the margin_fully_connected be used.
But when I use margin_fully_connected instead of fully_connected, it doesn't work.

Thanks in advance!

I want to see softmax_loss but I can't find it. Can I access softmax loss code?

when I excuate command “CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --num_gpus=4 --model_name=ResNeXt --net_name=face --data_list_path=/home/chengcheng/make_data/buffer_TXT/cls/cls_training.npy”，the result showed

File "/home/xuchao/TF_Face_Toolbox/data.py", line 32, in get_image_paths_and_labels
label_index = part_line[1]
IndexError: list index out of range
why?