Replace AlexNet example with smaller model
- Dominant language
- Rust
- Stars
- 134
- Forks
- 34
- PR merge metrics
- No merged PRs in 30d
Description
The [AlexNet model weight file](https://github.com/intel/openvino-rs/blob/main/crates/openvino/tests/fixtures/alexnet/alexnet.bin) used for classification is large--233MB. This is too large for GitHub to handle, which forces us to use Git LFS for these test files (the [other weight file](https://github.com/intel/openvino-rs/blob/main/crates/openvino/tests/fixtures/inception/inception-ssd.bin)--95MB--is also stored in Git LFS). Switching to a smaller model, such as SqueezeNet, would allow us to avoid using Git LFS in the repository.
Contributor guide
Research direction
Start with crates/openvino/tests/fixtures/alexnet/alexnet.bin and inspect the classification test that references it, along with the inception fixture. Replace the AlexNet fixture with a smaller classification model such as SqueezeNet, update the test references, and run the relevant tests while verifying the large Git LFS files are no longer required.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- git, rust
- Domain
- machine-learning, testing-qa
- Issue type
- Refactor
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100