• Epoch: 10
  • Optimizer: Adam
  • Learning Rate: 10e-3
  • Augmentation: Random Horizontal and Vertical Flip

Result:

Metric Train Validation Test
Loss 0.29818 0.34164 0.3223
Accuracy (Macro) 0.89413 0.87473 0.86351
Accuracy (Micro) 0.90601 0.88515 0.88538
Accuracy (Weighted) 0.90601 0.88515 0.88538
F1 (Macro) 0.89576 0.87189 0.8632
F1 (Micro) 0.90601 0.88515 0.88538
F1 (Weighted) 0.90581 0.88571 0.88556
Precision (Macro) 0.89771 0.87115 0.86314
Precision (Micro) 0.90601 0.88515 0.88538
Precision (Weighted) 0.9059 0.88785 0.88599
Recall (Macro) 0.89413 0.87473 0.86351
Recall (Micro) 0.90601 0.88515 0.88538
Recall (Weighted) 0.90601 0.88515 0.88538

This model has been pushed to the Hub using the PytorchModelHubMixin integration:

  • Library: [More Information Needed]
  • Docs: [More Information Needed]
Downloads last month
20
Safetensors
Model size
4.23M params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train pradanaadn/trash-clasification

Space using pradanaadn/trash-clasification 1