zhanghang1989 / zhanghang1989/PyTorch-Encoding

decompression bomb DOS attack Warning

Open
#377 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

When i try train the model with 1500 images i am getting this warning and after that training stopped
model = encnet
backbone = resnest101
learning rate = 0.0125 (changed)
base size = 480 (changed)
crop size = 440 (changed)
batch size = 2

Error:
/home/****/miniconda3/envs/seg-pe/lib/python3.7/site-packages/PIL/Image.py:2850: DecompressionBombWarning: Image size (133036628 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
DecompressionBombWarning,

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 by reproducing training with the listed model, backbone, and image settings, then inspect the reported PIL Image.py warning and the dimensions of the input images. The issue does not identify a project file, test, expected behavior, or a defined completion condition, so first determine why training stops after the warning.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.