visdial-rl
visdial-rl copied to clipboard
PyTorch code for Learning Cooperative Visual Dialog Agents using Deep Reinforcement Learning
Do we really need transpose?Because I got this error: beamTokensTable[:, :, 0] = topIdx.transpose(0, 1).data RuntimeError: The expanded size of the tensor (5) must match the existing size (10) at...
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?...
When I tried to run evaluate.py with “-evalMode dialog” like this `python evaluate.py -useGPU \ -startFrom checkpoints/abot_rl_ep20.vd \ -qstartFrom checkpoints/qbot_rl_ep20.vd \ -evalMode dialog \ -beamSize 5` , I had an...
https://github.com/batra-mlp-lab/visdial-rl/blob/1fb7e88a65013477b0eb8f14dec2fda74eb48d17/visdial/models/decoders/gen.py#L243 Following the paper, the above should be replaced by `loss += -1 * log_prob * (reward.detach() * (self.mask[:, t].float()))` Not having a `.detach()` on the reward here provides another...
If the score of ground truth would tie with another option, it always got assigned a higher rank. This caused evaluation metrics to be reported higher than their true values....
Thanks to your kindness, I managed to run your code. By the way, here is one more question. I ran ``` python evaluate.py -useGPU \ -startFrom checkpoints/abot_rl_ep20.vd \ -qstartFrom checkpoints/qbot_rl_ep20.vd...
Hi, Thank you providing this code. Could you explain your code for backtracking in beam search. In particular how do you handle the dropped sequences that have seen EOS earlier...