YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
EatFish Fish Classification
Image classification model for three fish classes: anchovy, emperor, sangara
Model
- Architecture: MobileNetV3Small
- Pretrained weights: ImageNet
- Input size: 224 x 224 RGB
- Output: Softmax probabilities across 3 classes
Evaluation
- Test accuracy: 100.00%
- Test loss: 0.0114
Files
- eatfish_mobilenetv3.keras: final saved model
- eatfish_mobilenetv3_best.keras: best validation-loss checkpoint
- class_names.json: class label order
- evaluation.json: test metrics and confusion matrix
Input
Provide an RGB image resized to 224 x 224 pixels. The model uses MobileNetV3 preprocessing internally.
- Downloads last month
- 17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support