Image Classification
Transformers
PyTorch
TensorBoard
English
vit
Generated from Trainer
Eval Results (legacy)
Instructions to use DunnBC22/vit-base-patch16-224-in21k_Human_Activity_Recognition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DunnBC22/vit-base-patch16-224-in21k_Human_Activity_Recognition with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="DunnBC22/vit-base-patch16-224-in21k_Human_Activity_Recognition") 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("DunnBC22/vit-base-patch16-224-in21k_Human_Activity_Recognition") model = AutoModelForImageClassification.from_pretrained("DunnBC22/vit-base-patch16-224-in21k_Human_Activity_Recognition") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 5.0, | |
| "eval_Macro F1": 0.8394073191246441, | |
| "eval_Macro Precision": 0.842423886079004, | |
| "eval_Macro Recall": 0.8389614636720059, | |
| "eval_Micro F1": 0.8380952380952381, | |
| "eval_Micro Precision": 0.8380952380952381, | |
| "eval_Micro Recall": 0.8380952380952381, | |
| "eval_Weighted F1": 0.8388264444322653, | |
| "eval_Weighted Precision": 0.8421267923064243, | |
| "eval_Weighted Recall": 0.8380952380952381, | |
| "eval_accuracy": 0.8380952380952381, | |
| "eval_loss": 0.74034184217453, | |
| "eval_runtime": 2179.8388, | |
| "eval_samples_per_second": 1.156, | |
| "eval_steps_per_second": 0.145 | |
| } |