Instructions to use AmitMidday/Dogs-Breed-Classification-Using-Vision-Transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AmitMidday/Dogs-Breed-Classification-Using-Vision-Transformers with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="AmitMidday/Dogs-Breed-Classification-Using-Vision-Transformers") 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("AmitMidday/Dogs-Breed-Classification-Using-Vision-Transformers") model = AutoModelForImageClassification.from_pretrained("AmitMidday/Dogs-Breed-Classification-Using-Vision-Transformers", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 3.74515962600708, | |
| "best_model_checkpoint": "./results\\checkpoint-317", | |
| "epoch": 1.0, | |
| "global_step": 317, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7662779397473275, | |
| "eval_f1": 0.737623875891686, | |
| "eval_loss": 3.74515962600708, | |
| "eval_runtime": 442.185, | |
| "eval_samples_per_second": 4.654, | |
| "eval_steps_per_second": 0.09, | |
| "eval_top3_accuracy": 0.9382896015549077, | |
| "eval_top5_accuracy": 0.966958211856171, | |
| "step": 317 | |
| } | |
| ], | |
| "max_steps": 317, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.2770998546458378e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |