Video classification in TensorFlow using Mask R-CNN. This project is built upon https://github.com/matterport/Mask_RCNN. The dataset used to train Mask R-CNN has been built with LabelBox, the video classification has been done with an LSTM that classifies activities taken from a subset of ActivityNet dataset (Gymnastics activities). This repository has been used for the final project of the module Vision and Perception (Spring 2018) at Sapienza University of Rome.
dharshan-manjunath opened this issue · comments
Getting the below error when own video file is used for training
ValueError: Layer #389 (named "mrcnn_bbox_fc"), weight <tf.Variable 'mrcnn_bbox_fc/kernel:0' shape=(1024, 136) dtype=float32_ref> has shape (1024, 136), but the saved weight has shape (1024, 324)