an error when I run the TSN experiments on Charades

[icyzhang0923]

When I run the TSN experiments on Charades, I meet a problem:

Traceback (most recent call last):
File "/media/icyzhang/SSD/PyVideoResearch-master/baseline_exp/temporal_segment_networks_charades.py", line 54, in
main()
File "/media/icyzhang/SSD/PyVideoResearch-master/main.py", line 106, in main
scores.update(trainer.train(train_loader, model, criterion, optimizer, epoch, metrics, args))
File "/media/icyzhang/SSD/PyVideoResearch-master/train.py", line 61, in train
output = model(input, meta)
File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 143, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 153, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 83, in parallel_apply
raise output
File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 59, in _worker
output = module(*input, **kwargs)
TypeError: TSNBase2 object argument after ** must be a mapping, not tuple

[gsig]

The error is complaining that a passed keyword argument to TSN base is somehow a tuple, not a dict. I have not tested the TSN baseline recently, so there is likely some code drift, either in this codebase, or relative to PyTorch etc. You could pull the repo at the got hash given in the baseline to figure out if it's this codebase or not. If it's a drift relative to PyTorch my guess is that it might have to do with our extension of the collate function to support arbitrary meta inputs: https://github.com/gsig/PyVideoResearch/blob/master/datasets/get.py otherwise it's likely some function signature somewhere. If you do figure it out, consider submitting a pull request to help others. Best, Gunnar

…

On Wed, Sep 11, 2019, 8:38 AM icyzhang ***@***.***> wrote: When I run the TSN experiments on Charades, I meet a problem: Traceback (most recent call last): File "/media/icyzhang/SSD/PyVideoResearch-master/baseline_exp/temporal_segment_networks_charades.py", line 54, in main() File "/media/icyzhang/SSD/PyVideoResearch-master/main.py", line 106, in main scores.update(trainer.train(train_loader, model, criterion, optimizer, epoch, metrics, args)) File "/media/icyzhang/SSD/PyVideoResearch-master/train.py", line 61, in train output = model(input, meta) File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in *call* result = self.forward(*input, **kwargs) File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 143, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 153, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 83, in parallel_apply raise output File "/home/icyzhang/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 59, in _worker output = module(*input, **kwargs) TypeError: TSNBase2 object argument after ** must be a mapping, not tuple — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#25?email_source=notifications&email_token=AA3OMNNBLVKFRQZ2C2C7CMLQJCN7TA5CNFSM4IVQMAYKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HKUMDXA>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AA3OMNNNZCHYP3BDLHR2DP3QJCN7TANCNFSM4IVQMAYA> .