Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Instructions to use djbp/swin-base-patch4-window7-224-in22k-cons_Classification_base_V10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use djbp/swin-base-patch4-window7-224-in22k-cons_Classification_base_V10 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="djbp/swin-base-patch4-window7-224-in22k-cons_Classification_base_V10") 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("djbp/swin-base-patch4-window7-224-in22k-cons_Classification_base_V10") model = AutoModelForImageClassification.from_pretrained("djbp/swin-base-patch4-window7-224-in22k-cons_Classification_base_V10") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 6.885245901639344, | |
| "eval_accuracy": 0.8819264629725531, | |
| "eval_auc_class_0": 0.9495999423161078, | |
| "eval_auc_class_1": 0.9589146175353072, | |
| "eval_auc_class_2": 0.9645625643801177, | |
| "eval_auc_overall": 0.9576923747438442, | |
| "eval_loss": 0.3063272535800934, | |
| "eval_runtime": 213.6843, | |
| "eval_samples_per_second": 9.037, | |
| "eval_steps_per_second": 0.075, | |
| "total_flos": 4.1785312376666235e+18, | |
| "train_accuracy": 0.8871655680496316, | |
| "train_auc_class_0": 0.9601424899214485, | |
| "train_auc_class_1": 0.968345723853034, | |
| "train_auc_class_2": 0.9621813081120092, | |
| "train_auc_overall": 0.9635565072954971, | |
| "train_loss": 0.4226800623394194, | |
| "train_runtime": 11867.0985, | |
| "train_samples_per_second": 4.564, | |
| "train_steps_per_second": 0.009 | |
| } |