litingfeng
litingfeng
Later today, I tried `script_test_object_detection_pipeline_PASCAL.m`. It works without any modification. So strange.
It seems that in demo, you did not `caffe.reset_all();` after each network.
> **1)** I already understand that logic behind not using torch.arange. My question is much simpler, i was just asking why was there a need for a custom CrossEntropyLoss for...
> Hi, thanks for the great work. I try to run the code following the command, but there is no specification on the conda environment pt1.8. Could you please provide...
Same issue, can't compile...