Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Instructions to use Angy309/swinv2-tiny-patch4-window8-256-prueba2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Angy309/swinv2-tiny-patch4-window8-256-prueba2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Angy309/swinv2-tiny-patch4-window8-256-prueba2") 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("Angy309/swinv2-tiny-patch4-window8-256-prueba2") model = AutoModelForImageClassification.from_pretrained("Angy309/swinv2-tiny-patch4-window8-256-prueba2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 2.7272727272727275, | |
| "eval_accuracy": 0.7948717948717948, | |
| "eval_loss": 0.4983014762401581, | |
| "eval_runtime": 1.1952, | |
| "eval_samples_per_second": 65.261, | |
| "eval_steps_per_second": 2.51, | |
| "total_flos": 4.767600833578598e+16, | |
| "train_loss": 0.6202580610911052, | |
| "train_runtime": 32.385, | |
| "train_samples_per_second": 64.937, | |
| "train_steps_per_second": 0.463 | |
| } |