Instructions to use microsoft/resnet-26 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/resnet-26 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="microsoft/resnet-26") 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("microsoft/resnet-26") model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-26") - 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=1.547e-04; Maximum converted output difference=1.547e-04.
All crossload differences
logits: 1.025e-05
hidden_states[0]: 9.060e-06
hidden_states[1]: 7.853e-05
hidden_states[2]: 1.547e-04
hidden_states[3]: 8.881e-05
hidden_states[4]: 1.428e-04
amyeroberts changed pull request status to merged