sequence input layer - video classification
显示 更早的评论
Could anyone please elaborate on how to feed video frames to a sequence input layer? MATLAB documentation for sequence or time series data input to a network says: "Sequences or time series data, specified as a cell array of matrices. C is a N-by-1 cell array where N is the number of observations. Each entry of C is a time series represented by a matrix with rows corresponding to data points, and columns corresponding to time steps."
My question is, how to create a sequence input layer for video data of N videos, where each video is composed of L frames of colored nXmXc images?
回答（1 个）
Ameer Hamza
2020-9-22
0 个投票
What about this example: https://www.mathworks.com/help/deeplearning/ug/classify-videos-using-deep-learning.html. This shows how to feed video frames to lstm.
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
2020-9-22
2020-9-22
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
