lixiang

@yzhang123 i have already changed the configuration you specified before i met the above problem. I'm wondering the “PVA9.1_ImgNet_COCO_VOC0712.caffemodel” doesn't have a layer named "conv1_1/conv". But how?

just like the way of installing py-faster-rcnn on windows

127.5 is half of 255, but why?

@fighting-liu In train_faster_rcnn_alt_opt.py/train_fast_rcnn, there already exist this configuration: cfg.TRAIN.HAS_RPN = False. But i don't know why it doesn't work. It seems that the cfg reloaded in layer.py and neglects the...

Hi, Can you provide the code for plotting the geodesic error maps (Fig. 7)? Thanks.

@iSaran have you solved this problem yet?

Same question. I'm using a server with 4 TITAN XP GPUs. When I ran the code, only 1 GPU was used. It took around 7s to run for one step....

@bittnt i'm training with my own data, how to initialize the convolution weights?

same problem

collect2.exe: error: ld returned 1 exit status error: command 'C:\\Anaconda\\MinGW\\bin\\g++.exe' failed with exit status 1