Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Instructions to use djbp/NMM_Classification_base_V10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use djbp/NMM_Classification_base_V10 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="djbp/NMM_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/NMM_Classification_base_V10") model = AutoModelForImageClassification.from_pretrained("djbp/NMM_Classification_base_V10", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 6.892307692307693, | |
| "eval_accuracy": 0.8349146110056926, | |
| "eval_auc_class_0": 0.9613559582309583, | |
| "eval_auc_class_1": 0.9315019107361742, | |
| "eval_auc_class_2": 0.920726636279075, | |
| "eval_auc_overall": 0.9378615017487358, | |
| "eval_loss": 0.40655088424682617, | |
| "eval_runtime": 226.5129, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 0.075 | |
| } |