conflict resize on imagenet preprocess
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 9.8k
- Forks
- 1.6k
- PR merge metrics
- No merged PRs in 30d
Description
the iamges resized in 224x24 on your example code for preprocess here https://github.com/onnx/models/blob/main/vision/classification/imagenet_preprocess.py
but，it resized into 256x256 in https://github.com/onnx/models/blob/main/vision/classification/imagenet_validation.ipynb
I thought the 224x224 is wrong，cause is meaningless to resize image to 224x224 then centerCrop to 224x224
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
Compare vision/classification/imagenet_preprocess.py with vision/classification/imagenet_validation.ipynb, focusing on the resize and center-crop steps described in the issue. Determine the intended ImageNet preprocessing sequence, then make the two references consistent and verify that the example code and validation notebook use the same dimensions.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100