DeepLearningOnFlowersDataSet

Improving the image classification using CNN, Data Augmentation, Transfer Learning and Ensemble Techniques

The notebooks are divided into three sections as follows.

  • Part A:      Explores the application of convolutional networks on multiple architectures.
  • Part A - ii: Improve the accuracy using data augmentation and ensemble techniques.

  • Part B: Focuses on transfer learning (specifically the use of CNNs as feature extractors and the application of fine tuning with pre-trained CNNs).

The report discusses in detail, the performance of various architectures stated above.

  • Part C: Research component explores capsule networks.