zhanghang1989 / zhanghang1989/PyTorch-Encoding
PSP train can't find file
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Firstly, I cd /PyTorch-Encoding/experiments/segmentation/ and when I train PSPnet by
CUDA_VISIBLE_DEVICES=0,1 python train_ym.py --dataset pascal_aug --model psp --aux --se-loss --backbone resnet101 --lr 0.001
train_ym.py is same as train.py but I can' find the data.
Why does the code use /py3.5_pytorch1.0/lib/python3.5/site-packages/encoding/datasets/init.py instead of "PyTorch-Encoding/encoding/datasets/init.py" .I didn't download data using code but I give the right address of my data in "PyTorch-Encoding/encoding/datasets/pascal_aug.py" but the code don't use the file because it use the file "py3.5_pytorch1.0/lib/python3.5/site-packages/encoding/datasets/pascal_aug.py" so it can't find the "train.txt".
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 experiments/segmentation/train_ym.py and trace its import of encoding.datasets.pascal_aug. Compare the repository file with the installed file under py3.5_pytorch1.0/lib/python3.5/site-packages/encoding/datasets/, and verify which package Python resolves when the training command runs. Done when the command uses the intended dataset definition and can locate train.txt.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100