Instructions to use nvidia/mit-b2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/mit-b2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="nvidia/mit-b2") 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("nvidia/mit-b2") model = AutoModelForImageClassification.from_pretrained("nvidia/mit-b2") - Inference
- Notebooks
- Google Colab
- Kaggle
Add TF weights
#1
by amyeroberts - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its Pytorch counterpart.
Maximum crossload output difference=5.007e-06; Maximum crossload hidden layer difference=9.346e-05;
Maximum conversion output difference=5.007e-06; Maximum conversion hidden layer difference=9.346e-05;
amyeroberts changed pull request status to merged