CODEWITHSUNDEEP
computer-visiondeep-learningvideo-processingcaffenvidia-digits
Video Analysis Deep Learning
Video Analysis Deep Learning

Reputation: 348

How to use video for traning deep learning (caffe & digits)?

Based on a, b, c, d, Action Recognition with Deep Learning, Long-term Recurrent Convolutional Networks, e, Generic Features for Video Analysis,... there are several methods for analyses video by caffe but what is exactly the input for caffe. Can we put video in different folders like image for training?

Upvotes: 1

Views: 433

Answers (2)

Amin Ullah
Amin Ullah

Reputation: 77

As far as my experience, you can't directly do it with digits, because in digits no default settings for sequences of frame analysis. A very famous project in Caffe known as C3D for action recognition can be used for training a new model or fine-tune existing moded for action or activity recognition. C3D

Upvotes: 0

Luke Yeager
Luke Yeager

Reputation: 1430

DIGITS doesn't support video data yet. When we do we'll add some sort of video example here:

https://github.com/NVIDIA/DIGITS/tree/master/examples

Upvotes: 3

Related Questions