This projects detect Anomalous Behavior through live CCTV camera feed to alert the police or local authority for faster response time. We are using Spatio Temporal AutoEncoder and more importantly three models from Keras ie; Convolutional 3D, Convolutional 2D LSTM and Convolutional 3D Transpose. 👮‍♂️👮‍♀️📹🔍🔫⚖

💾 🔥 The fastest and easiest to use TFRecords formatter

Notes about usage: This code is to create a custom video dataset to train deeplearning models using PyTorch on consecutive video frames extracted from a video. This code expects the extracted video frames in separate folders. For example, video1's frames will be in a folder named 'video1'. You can use OpenCV to extract video frames and save insi…