search

batra-mlp-lab / visdial-rl

PyTorch code for Learning Cooperative Visual Dialog Agents using Deep Reinforcement Learning
170 stars 39 forks source link

RuntimeError: CUDA error: out of memory #14

Open Sxx1995 opened 5 years ago

Sxx1995 commented 5 years ago

I ran the command "python train.py -useGPU -trainMode sl-abot". However, I got such error "RuntimeError: CUDA error: out of memory". How much GPU memory is needed when training the model? The memory of my GPU is 12212MiB. Thanks!

Jiaqiang-Ruan commented 5 years ago

Hi, I encountered the same problem. Is the problem solved?

sinhprous commented 3 years ago

please wrap the rankABot calling (https://github.com/batra-mlp-lab/visdial-rl/blob/master/train.py#L409) with with torch.no_grad():