Anonymous
Anonymous
@chihyaoma @liuhualin333 Have you been able to reproduce the result with pytorch 1.2.0, cuda 10.1? I have the same problem here. My configurations are as follows. ``` # Name Version...
Even with `pytorch 0.4.1`, the performance gap still exists. ``` R2RBatch loaded with 2349 instructions, using splits: val_unseen Evaluating on val_seen env ... Epoch: [90][1/16] Time 1.582 (1.582) Loss inf...
> I am facing the same problem here yielding almost same perforance with you. Have you found any clue? I still do not have any clue. If you find the...
> Same here If you find the answer, can you share with us here ? This is really wired.
> ok i have trained DFF on cityscapes if you have any probelm i can send to you the trained model DFF.pth @achreff Have you reproduced the result in cityscapes...
@dragonfly90 Have you figured out why spread loss is increasing ? I have encountered the same issue.