Instructions to use dima806/yoga_pose_image_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dima806/yoga_pose_image_classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/yoga_pose_image_classification") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("dima806/yoga_pose_image_classification") model = AutoModelForImageClassification.from_pretrained("dima806/yoga_pose_image_classification") - Notebooks
- Google Colab
- Kaggle
Returns yoga pose given an image with 97% accuracy.
See https://www.kaggle.com/code/dima806/yoga-pose-classification-vit for more details.
Classification report:
precision recall f1-score support
Bridge 0.9776 0.9776 0.9776 134
Child 0.9701 0.9701 0.9701 134
Cobra 0.9774 0.9701 0.9738 134
Downward-Dog 0.9924 0.9701 0.9811 134
Pigeon 1.0000 0.9851 0.9925 134
Standing-Mountain 0.9214 0.9699 0.9451 133
Tree 0.9767 0.9474 0.9618 133
Triangle 0.9270 0.9549 0.9407 133
Warrior 0.9699 0.9627 0.9663 134
accuracy 0.9676 1203
macro avg 0.9681 0.9676 0.9677 1203
weighted avg 0.9681 0.9676 0.9677 1203
- Downloads last month
- 15
Model tree for dima806/yoga_pose_image_classification
Base model
google/vit-base-patch16-224-in21k