zhanghang1989 / zhanghang1989/PyTorch-Encoding

My own trained model does not match the downloaded one.

Open
#193 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
448
PR merge metrics
No merged PRs in 30d

Description

Hi Dr. Zhang,

First of all I appreciate your excellent work. I am new at using this repo and currently I have some issues while training my own model. When I tried to use the following command (CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py --dataset minc --model deepten_resnet50_minc --batch-size 512 --lr 0.004 --epochs 80 --lr-step 60 --lr-scheduler step --weight-decay 5e-4) to train my own deep-TEN model, a model file 'model_best.pth.tar' was generated.The file size does not seem to be right to me (about 200MB, whereas your pre-trained model.pth is about 100MB). Do you have any idea how may I resolve this? Thank you for your time in advance!

Shuo

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with main.py and reproduce the reported minc training command, then compare the generated model_best.pth.tar with the downloaded model.pth. Check how each checkpoint is produced and loaded, and use the differing file sizes to establish whether the training result is expected or indicates a reproducible problem.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.