YOLOv1 Model (based on)
This repository contains an object detection network in the spirit of YOLOv1 for dog/cat head detection.
Model Details
- Architecture: 5 Convolutional Layers, 2 Fully Connected Layers.
- Activations: ReLU activation after each convolutional and fully connected layer, with Sigmoid activation at the output layer.
- Weight Initialization: Default PyTorch initialization (Kaiming Uniform for convolutional and linear layers).
- Optimizer: Adam (lr=0.001).
- Loss Function: Mean Squared Error (MSE) Loss.
- Dataset: https://www.kaggle.com/datasets/andrewmvd/dog-and-cat-detection
Usage
Load this model in PyTorch.
Feel free to update this model card with further training details, benchmarks, or usage examples.