Instructions to use OpenGVLab/pvt_v2_b5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/pvt_v2_b5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="OpenGVLab/pvt_v2_b5") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("OpenGVLab/pvt_v2_b5") model = AutoModelForImageClassification.from_pretrained("OpenGVLab/pvt_v2_b5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Fixed "out_indices" and "out_features" fields in config (#1)
Verified signature- Fixed "out_indices" and "out_features" fields in config (dab84ad4ba0c556bb41ddcc3324c8cee442ad719) - Added first encoder layer to "out_indices" and "out_features" (f1dfc46dfeef1dfd4106c27f0c6a9cc543fdcf25) - Fixed model name/path (ea62a8cb3ba97e8bb16d58957b614fa72b9374ea) Co-authored-by: Nate <FoamoftheSea@users.noreply.huggingface.co>85ccf16
-
Update README.md
Verified signature1351f8f -
Upload folder using huggingface_hub
Verified signatureab50a82 -
initial commit
Verified signaturee85f67e