pytorch / pytorch/vision

Documentation enhancement: Specifying detailed shape requirements for pretrained models

Open
#3,921 7 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: documentation module: models
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

📚 Documentation

In the documentation of PyTorch Model Zoo, it is suggested that:

H and W are expected to be at least 224.

Technically, for H/W < 224 it is also workable, but there might be some lower bound.

For example, the AlexNet model is able to consume a tensor of [3, 200, 200] but not applicable for that of [3, 62, 62].

Similar cases also apply to vgg* and densenet*. Therefore, I am wondering if it is necessary to specify the undefined behaviours of models in the documentation to help users better leverage the models. Thanks.

Contributor guide

Open the contributing guide

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 reviewing the PyTorch Model Zoo documentation at https://pytorch.org/vision/stable/models.html and compare its H/W guidance with the stated AlexNet, vgg*, and densenet* examples. Document model-specific lower bounds or undefined behavior for smaller inputs, with the finished documentation making clear which tensor shapes are supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.