pytorch / pytorch/vision

Imagenet Pre-trained model for other Depth Multiplier

Open
#2,951 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

On the mnasnet model under mnasnet.py file, the link provided for imagenet pretrained model is only for two depth multiplier, as shown in the code below:

_MODEL_URLS = {
"mnasnet0_5":
"https://download.pytorch.org/models/mnasnet0.5_top1_67.823-3ffadce67e.pth",
"mnasnet0_75": None,
"mnasnet1_0":
"https://download.pytorch.org/models/mnasnet1.0_top1_73.512-f206786ef8.pth",
"mnasnet1_3": None
}

Can you provide the link for Imagenet pre-trained model for mnasnet0_75 and mnasnet1_3?

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 in mnasnet.py at the _MODEL_URLS mapping and inspect how pretrained weights are selected for mnasnet0_75 and mnasnet1_3. Add valid ImageNet model links for those variants, then verify that the corresponding pretrained-model loading path resolves them successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.