Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Instructions to use andakm/swin-tiny-patch4-window7-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use andakm/swin-tiny-patch4-window7-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="andakm/swin-tiny-patch4-window7-224") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("andakm/swin-tiny-patch4-window7-224") model = AutoModelForImageClassification.from_pretrained("andakm/swin-tiny-patch4-window7-224", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from andakm/swin-tiny-patch4-window7-224: direct link, hf CLI and curl.
- Browser
- Download file 1.43 kB
-
https://huggingface.co/andakm/swin-tiny-patch4-window7-224/resolve/main/trainer_state.json
- Command line
-
hf download hf://andakm/swin-tiny-patch4-window7-224/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/andakm/swin-tiny-patch4-window7-224/resolve/main/trainer_state.json
1.43 kB
| { | |
| "best_metric": 0.29411764705882354, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224/checkpoint-9", | |
| "epoch": 2.4, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.2549019607843137, | |
| "eval_loss": 2.069157123565674, | |
| "eval_runtime": 23.5336, | |
| "eval_samples_per_second": 2.167, | |
| "eval_steps_per_second": 0.085, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.27450980392156865, | |
| "eval_loss": 1.849087119102478, | |
| "eval_runtime": 0.4147, | |
| "eval_samples_per_second": 122.973, | |
| "eval_steps_per_second": 4.822, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.29411764705882354, | |
| "eval_loss": 1.821778655052185, | |
| "eval_runtime": 0.4233, | |
| "eval_samples_per_second": 120.489, | |
| "eval_steps_per_second": 4.725, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "step": 9, | |
| "total_flos": 2.759631525568512e+16, | |
| "train_loss": 2.123395072089301, | |
| "train_runtime": 273.545, | |
| "train_samples_per_second": 5.034, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.759631525568512e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |