Mitra Tajrobehkar comments

Results 5 comments of


                                            Mitra Tajrobehkar

Nan loss in RCAN model

hi, i use torch version 0.3.1. and just I modified optimizer = optim.Adam(params, weight_decay=conf.l2, lr=lr, eps=1e-3) to optimizer = adabound.AdaBound(params, weight_decay=conf.l2, lr=lr, final_lr=0.1, eps=1e-3) when I ran it I faced...

Train on different dataset

Hi, I have another error when I use another dataset. my data is 32x32x3. consists of train.tar.gz and test.tar.gz only. error: cannot reshape array of size 651786224 into shape(73257,32,32,3)

training rel classification/detection using multi gpus

Fine. Thanks!

CUDA error 'out of memory' in func 'cuda_neoscrypt::init' line 1258

I use Lab server, 8 GPUs. For running faster RCNN I have this problem. In this case, what can I do. Thank you!

CUDA error 'out of memory' in func 'cuda_neoscrypt::init' line 1258

samywee: Thank you for your help. Sorry I am new in DL and using GPU. So, I should ask admin to allocate me more space of GPU, correct? Since each...