Instructions to use OpenGVLab/pvt_v2_b0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/pvt_v2_b0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="OpenGVLab/pvt_v2_b0") 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("OpenGVLab/pvt_v2_b0") model = AutoModelForImageClassification.from_pretrained("OpenGVLab/pvt_v2_b0") - Inference
- Notebooks
- Google Colab
- Kaggle
Update "out_indices" and "out_features" fields in config for compatibility with new code
#1
by FoamoftheSea - opened
These fields were previously being stored incorrectly to the JSON with the underscore prefix (e.g. "_out_indices"). This was an error, and they should be saved here without the underscore prefix as "out_indices" for correct loading.
czczup changed pull request status to merged