Pretrained models in CNN | ImageNET Dataset | ILSVRC | Keras Code

A pre-trained model is a model created and trained by someone else to solve a problem that is similar to ours. In practice, someone is almost always a tech giant or a group of star researchers. They usually choose a very large dataset as their base datasets such as ImageNet or the Wikipedia Corpus. Then, they create a large neural network (e.g., VGG19 has 143,667,240 parameters) to solve a particular problem (e.g., this problem is image classification for VGG19). Of course, this pre-trained model must be made public so that we can take these models and repurpose them.

============================
Do you want to learn from me?
Check my affordable mentorship program at : https://learnwith.campusx.in
============================

📱 Grow with us:
CampusX' LinkedIn: LinkedIn: campusx-official
CampusX on Instagram for daily tips: Instagram: campusx.official
My LinkedIn: LinkedIn: nitish-singh-03412789
Discord: Discord: discord

👍If you find this video helpful, consider giving it a thumbs up and subscribing for more educational videos on data science!

💭Share your thoughts, experiences, or questions in the comments below. I love hearing from you!

⌚Time Stamps⌚

00:00 - Intro
01:11 - Why use pre-trained models?
04:19 - ImageNET Dataset
09:16 - ILSVRC
13:24 - Architecture of AlexNET
15:05 - Famous Architectures
17:45 - Idea of pre-trained models
21:20 - Code Example