Add MobileViT-XS to MCT-model garden #1049
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Idan-BenAmi
approved these changes
Apr 30, 2024
| "!rm -f imagenet/val/ILSVRC2012_img_val.tar\n", | ||
| "# We follow https://github.com/pytorch/examples/blob/main/imagenet/extract_ILSVRC.sh here\n", | ||
| "# get script from soumith and run; this script creates all class directories and moves images into corresponding directories\n", | ||
| "!cd imagenet/val/ && wget -qO- https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh | bash\n", |
There was a problem hiding this comment.
consider to take the code from here, looks more elegant.. https://github.com/sony/model_optimization/blob/main/tutorials/notebooks/keras/ptq/example_keras_imagenet.ipynb
| "\n", | ||
| "### Download a Pre-Trained Model \n", | ||
| "\n", | ||
| "We begin by loading a pre-trained [MobileViT-XS](https://huggingface.co/SSI-DNN/pytorch_mobilevit_xs) model. This implementation is based on [Timm](https://github.com/huggingface/pytorch-image-models) and includes a slightly modified version of timm/Attention module that was adapted for model quantization. For further insights into the model's implementation details, please refer to [MCT Models Garden - yolov8](https://github.com/sony/model_optimization/tree/main/tutorials/mct_model_garden/models_pytorch/mobilevit_xs). " |
There was a problem hiding this comment.
Maybe add a few words what are the adjustments (batch issue..)
| " target_platform_version='v1')\n", | ||
| "\n", | ||
| "# Specify the necessary configuration for mixed precision quantization. To keep the tutorial brief, we'll use a small set of images and omit the hessian metric for mixed precision calculations. It's important to be aware that this choice may impact the resulting accuracy. \n", | ||
| "mp_config = mct.core.MixedPrecisionQuantizationConfig(num_of_images=5,\n", |
There was a problem hiding this comment.
check if compression is required..
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request Description:
Add MobileViT-XS to MCT-model garden
Add MobileViT-XS tutorial
Checklist before requesting a review: