This project implements an image classification model using the ResNet50 architecture, a 50-layer deep convolutional neural network designed to classify images into various categories. The model was trained on a dataset from ImageNet and achieved an impressive accuracy of 99.34%.
ResNet50 is widely known for its effectiveness in image classification tasks by employing residual learning techniques to tackle the problem of vanishing gradients in deep networks. The model is capable of recognizing complex patterns and features, making it an excellent choice for image classification challenges.
- Architecture: ResNet50, a 50-layer convolutional neural network
- Dataset: ImageNet
- Training: The model was trained using transfer learning techniques, which leverage pre-trained weights.
- Accuracy: The model achieved a 99.34% accuracy on the validation set.
Before running the project, install the required dependencies:
pip install -r requirements.txt