Nimish Jain
Results
3
comments of
Nimish Jain
This model is only trained for GRID dataset. If your video is saying "hello", it won't predict "hello". Instead it will predict some 6 word sentence based on command(4) +...
The video criteria is: - .mpg format - 360 x 288 - 25 frames - second length can be any number. Ex.(1, 2, 50, 100) No problem will occur if...
It can only run on Python 3.5 to Python 3.7 because TensorFlow only supports these versions of python as of October 2020.