Inception v3 - AshokBhat/ml GitHub Wiki

About

  • A widely-used image recognition model
  • Greater than 78.1% accuracy on the ImageNet dataset

Model components

The model has a mixture of symmetric and asymmetric building blocks, including:

  • convolutions
  • average pooling
  • max pooling
  • concats
  • dropouts
  • fully connected layers Loss is computed via Softmax.

More information

  • Based on paper "Rethinking the Inception Architecture for Computer Vision" by Szegedy, et. al.

See also