Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Instructions to use djbp/swin-tiny-patch4-window7-224-MM_Classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use djbp/swin-tiny-patch4-window7-224-MM_Classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="djbp/swin-tiny-patch4-window7-224-MM_Classification") 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-tiny-patch4-window7-224-MM_Classification") model = AutoModelForImageClassification.from_pretrained("djbp/swin-tiny-patch4-window7-224-MM_Classification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 393 Bytes
847b644 426f541 847b644 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | {
"epoch": 20.0,
"eval_accuracy": 0.8693982074263764,
"eval_loss": 0.34680071473121643,
"eval_runtime": 75.6434,
"eval_samples_per_second": 10.325,
"eval_steps_per_second": 0.093,
"total_flos": 4.783917310653358e+18,
"train_loss": 0.3464228366550646,
"train_runtime": 17694.0061,
"train_samples_per_second": 10.877,
"train_steps_per_second": 0.021
} |