YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Cats vs Dogs classifier (MobileNetV2, Keras)
Binary image classifier (cats vs dogs) trained in Google Colab Pro on the Kaggle Dogs vs Cats competition dataset using transfer learning with MobileNetV2.
Model details
- Framework: TensorFlow / Keras
- Base model:
tf.keras.applications.MobileNetV2(ImageNet weights, frozen) - Custom head:
- GlobalAveragePooling2D
- Dropout(0.2)
- Dense(1, sigmoid)
- Input size: 160 x 160 x 3
- Loss: binary cross-entropy
- Optimizer: Adam (lr = 1e-4)
- Data augmentation (train only):
- rotation, width/height shift, shear, zoom, horizontal flip
- Training:
- Epochs: 10
- Best validation accuracy: ≈96%
See model_info.json for meta information (class indices, number of samples, last validation accuracy, etc.).
Full training notebook & training details are available on Kaggle:
👉 Cats vs Dogs classifier (MobileNetV2, Keras)
license: apache-2.0
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support