/Applied-AI-Study-Group-2020-June

This is the repository for the content of inzva 2020-June Applied AI Study Group, guided by Ahmet Melek and Onur Boyar.

Primary LanguageJupyter NotebookMIT LicenseMIT

Applied-AI-Study-Group

This is the repository for the content of inzva 2020-June Applied AI Study Group, guided by Ahmet Melek and Onur Boyar.

In the group we have worked on these subjects:

  • Frameworks: Tensorflow, Keras Functional API, Keras Sequential API, Pytorch

  • Topics: Image Classification, Image Localisation, Image Segmentation

  • Architectures - Methods: Artificial Neural Networks (Fully-Connected Neural Networks), Convolutional Neural Networks (CNN)

  • Environments: Google Colab, Jupyter Notebook (Local)

Weekly Summaries

Week1 - Computer Vision

We have worked on six problems:

  • Image Classification with MNIST dataset on tensorflow, using Fully-Connected Neural Networks.

  • Image Classification with MNIST dataset on keras functional API, using Convolutional Neural Networks.

  • Image Classification with CIFAR-10 dataset on keras sequential API, using Convolutional Neural Networks.

  • Image Localisation with Kaggle Facial Keypoint Detection dataset on keras sequential API, using Convolutional Neural Networks.

  • Image Localisation with Kaggle Facial Keypoint Detection dataset on Pytorch, using Convolutional Neural Networks.

  • Image Segmentation with testing on random images from internet on Pytorch, using pretrained resnet101 model.

For all examples in Week1, we have worked on Google Colab.

Homework 1

In homework one, participants take an aligned hand image dataset with keypoint labels, and try to preprocess the dataset and make regression on the keypoint coordinates.