zhanghang1989 / zhanghang1989/PyTorch-Encoding
A problem "--Ir-step 60" occur at runing train_dist.py
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Pytorch vision: 1.4.0;
torchvision:0.5.0;
cuda vison:10.2
I run the train_dist.py follow the tutorial of https://hangzhang.org//PyTorch-Encoding/tutorials/texture.html.
I met a problem "train_dist.py: error: unrecognized arguments: --lr-step 60".
I delete ''--Ir-step 60" and add 'lr_step=60' at
scheduler = LR_Scheduler(args.lr_scheduler,
base_lr=args.lr,
lr_step=60, # added to solve lr_step problem
num_epochs=args.epochs,
iters_per_epoch=len(train_loader),
warmup_epochs=args.warmup_epochs)
Hope author could fix this small problem.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with train_dist.py and inspect its argument definitions, then compare them with the tutorial's --lr-step option and the LR_Scheduler call shown in the issue. Confirm the intended option name and verify that the tutorial command runs without an unrecognized-argument error and applies the requested learning-rate step.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- cli, machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100