pengfei

Results 6 comments of pengfei

> For me the problem was solved by removing the cached .pkl files from ./data/cache/_train_gt.pkl I fix the problem by doing the same with you

Hi,I use pytorch1.7 and train on 2080. I think this code can be directirely run on the 3090, you can have a try. If there is any mistake, please let...

> ERROR: Invalid requirement: u'torch~=1.5.1+cu101' (from line 1 of requirements.txt) > ERROR: Invalid requirement: u'torchvision~=0.6.1+cu101' (from line 5 of requirements.txt) > What should I do? Hi I fix the bug,...

you need to change your python environment in root dir cd ~/pytorch-faster-rcnn python train.py

You need to download coco dataset and set root dir in config/train_config.py

I have the same problem as you , have you solved the problem?