search

dipakkr / 3d-cnn-action-recognition

Implementation of Action Recognition using 3D Convnet on UCF-101 dataset.
73 stars 32 forks source link

inputting videos #1

Open Golnoush123 opened 5 years ago

Golnoush123 commented 5 years ago

When I input my dataset and I print X in line 102 I get arrays of zeros. it seems that what VideoCapture returns in line 101 is arrays of zero. Why this happens? Does the code able to read my videos or not when arrays are zero?How can I see the input video frames to make sure? I am running 3dcnn.py

dipakkr commented 5 years ago

@Golnoush123 you can't directly input video in the model.

First I have converted the video in frames then the frames are taken to model in chunks.

we can find the detailed code and explanation to run in 3dCNN-v2 folder

MuhammadAsadJaved commented 5 years ago

Hi, Can this code run on video from webcam or IP camera? is there pre-trained network or I should train network then it can be run on video from webcam?

if yes then what will be the sequence of files ? Why you did not show any output of test images? ##

hemanthkumar3111 commented 5 years ago

i just want to try the same on webcam, so please give me some suggestions regarding that