Recurrent Neural Networks for Video Understanding
This article compares how various recurrent neural network (RNN) models in PyTorch perform when identifying the genre of YouTube videos.
Created on January 8|Last edited on October 19
Comment
This report is a saved snapshot of Roberto's research. He has published this example so you can see how to use W&B to visualize training and keep track of your work. Feel free to add a visualization, click on graphs and data, and play with features. Your edits will not overwrite his work
Project Description
Roberto developed a deep learning model that can identify the genre of a YouTube video. Using PyTorch & Keras models to aggregate spatial strings (pixels) and sequential strings (audio). Later, he concatenates the model onto a fully connected network to output the video label genre: Games, Art & Entertainment, etc. He wrote a more thorough description of his work in his thesis paper, and the code for this project is available on GitHub.
Run set 1
16
Comparing Models and Frameworks
I coded eight deep learning models: 4 in Keras and the same models in PyTorch. I chose to compare not only models but frameworks as well based on research I did on algorithms crashing in production.
Tensorflow (Keras) has the most extensive user base and most traction currently. I want to compare it with PyTorch, an imperative framework that performs computation as you type it. Tensorflow (Keras) uses symbolic programming: only computing your code at the end of each graph session. Tensorflow is evolving to become more “PyTorch” like with eager execution; however, that is still in alpha and did not exist when my project started.
Google engineers also recognized the value of comparing frameworks as they worked along a similar path parallel to my work. More information about the difference between each framework and its performance is written in my paper. My experiments reveal surprising results.
Add a comment
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
<h1>HAcked</h1> •
nice
Reply
Tags: Intermediate, Computer Vision, Video, Object Detection, Keras, PyTorch, Experiment, Research, RNN, Plots
Iterate on AI agents and models faster. Try Weights & Biases today.