Instructions to use OpenGVLab/pvt_v2_b4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/pvt_v2_b4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="OpenGVLab/pvt_v2_b4") 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_b4") model = AutoModelForImageClassification.from_pretrained("OpenGVLab/pvt_v2_b4") - Notebooks
- Google Colab
- Kaggle
Fixed "out_indices" and "out_features" fields in config
#1
by FoamoftheSea - opened
These fields were being incorrectly stored with underscore prefixes as "_out_indices" and "_out_features". They should be stored as "out_features" and "out_indices" without the prefix for proper loading of PVTv2 as a backbone.
czczup changed pull request status to merged