project 12

ResNet50 & VGG19 Model Comparison

An analytical study training classic convolutional architectures on a custom dataset through transfer learning, then benchmarking their accuracy and inference speed.

Category
AI

technologies used

  • Python
  • TensorFlow
  • Keras
  • CUDA
  • Matplotlib
  • Seaborn

key features

  • 01Fine-tuning strategies with layer-wise weight freezing and custom classification heads.
  • 02Architecture performance comparison across precision, recall and F1-score metrics.
  • 03Training loops optimised with CUDA acceleration.

Thinking about a similar project?