Hi,thank you for your work! i have 2 questions here:
1.When i want to continue training from the "checkpoint_epoch_39.pth"(i trained 40 epochs),here is the error:
robeon@robeon-MS:~/pytorch-GCCPM$ python train.py --dataset-folder /home/robeon/pytorch-GCCPM/LIP --checkpoint-path /home/robeon/pytorch-GCCPM/default_checkpoints/checkpoint_epoch_39.pth.tar
Traceback (most recent call last):
File "train.py", line 171, in
checkpoints_folder, args.log_after, args.checkpoint_after)
File "train.py", line 62, in train
checkpoint = torch.load(checkpoint_path)
File "/home/robeon/anaconda3/lib/python3.6/site-packages/torch/serialization.py", line 386, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File "/home/robeon/anaconda3/lib/python3.6/site-packages/torch/serialization.py", line 555, in _load
return legacy_load(f)
File "/home/robeon/anaconda3/lib/python3.6/site-packages/torch/serialization.py", line 469, in legacy_load
tar.extract('storages', path=tmpdir)
File "/home/robeon/anaconda3/lib/python3.6/tarfile.py", line 2041, in extract
tarinfo = self.getmember(member)
File "/home/robeon/anaconda3/lib/python3.6/tarfile.py", line 1752, in getmember
raise KeyError("filename %r not found" % name)
KeyError: "filename 'storages' not found"
i dont't know how to solve this
2.How to drop the learning-rate?Does the code drops itself or i need to modify the base_lr by myself and continue training?
thanks again!