OLive/examples/vgg/requirements.txt

onnxruntime
pillow
torchvision
Add RawDataContainer, SNPE eval and pass accept common dataloader, Migrate snpe examples to workflow jsons (#333) ## Describe your changes This PR introduces a new data container called `RawDataContainer` where the data is saved in directory as numpy binary files. See the doc for `RawDataset` for more details. SNPE quantization and evaluation converts the generic dataloader to snpe dataloader so they are not limited snpe data loaders anymore. In the future, we can expand the dataset to support diferent types of data (.npy, .npz, pickle, etc), The snpe examples have been changed to workflow config jsons that use the raw data config. ## Checklist before requesting a review - [x] Add unit tests for this change. - [x] Make sure all tests can pass. - [ ] Update documents if necessary. - [ ] Format your code by running `pre-commit run --all-files` - [x] Is this a user-facing change? If yes, give a description of this change to be included in the release notes. SNPE evaluation and quantization now accept generic dataloaders such as torch dataloader. They no longer require users to provide SNPE dataloaders. ## (Optional) Issue link 2023-06-13 18:02:08 +03:00			`onnxruntime`
Welcome to new version of Olive (#127) * clean repo * olive code first commit * add security.md 2023-03-24 03:27:01 +03:00			`pillow`
			`torchvision`