jhtao1860
jhtao1860
@atmika-honnalgere use torch==0.4.0 is OK, but other project use torch==1.1.0 ,how to cope with the coexistence problem of the 2 version.
@akshitac8 @Iamal1 if you change the NUM_GPUS in .yaml from 4 to 2, you should modify the code of "the train_net_step.py " like this: maskRCNN = mynn.DataParallel(maskRCNN, device_ids=[0, 1], cpu_keywords=['im_info',...
@xincoder the result is the 12th( index 0 is the first ) case of all 415 scenarios in "prediction_test.txt" . I did not change the source code so I did...