/Custom-VGG-and-ResNet-models-for-Human-Pose-classification

Implementation of VGG (Visual Geometry Group) and ResNet (residual network) architectures in human pose classification.

Primary LanguageJupyter Notebook

Human pose classification ML project

Model 1

  • Name: Customed Visual Geometry Group (VGG)
  • Description: Visual Geometry Group (VGG) is a leading research team in computer vision. Their work has significantly advanced image recognition, object detection.

Model 2

  • Name: Residual Network (ResNet)
  • Description: Residual Network (ResNet) is a groundbreaking deep learning architecture. Introduced to address vanishing gradient issues, ResNet features skip connections that enable efficient training of extremely deep neural networks. This innovation has become a cornerstone in image recognition.