Convolutional Neural Nets Explained and Implemented in Python (PyTorch)

preview_player
Показать описание
Convolutional Neural Networks (CNNs) have been the undisputed champions of Computer Vision (CV) for almost a decade. Their widespread adoption kickstarted the world of deep learning; without them, the field of AI would look very different today.

Rather than manual feature extraction, deep learning CNNs are capable of doing image classification, object detection, and much more automatically for a vast number of datasets and use cases. All they need is training data.

Deep CNNs are the de-facto standard in computer vision. New models using vision transformers (ViT) and multi-modality may change this in the future, but for now, CNNs still dominate state-of-the-art benchmarks in vision.

In this hands-on video, we will learn why this is, how to implement deep learning CNNs for computer vision tasks like image classification using Python and PyTorch, and everything you could need to know about well-known CNNs like LeNet, AlexNet, VGGNet, and ResNet.

🌲 Pinecone article:

🤖 AI Dev Studio:

🎉 Subscribe for Article and Video Updates!

👾 Discord:

00:00 Intro
01:59 What Makes a Convolutional Neural Network
03:24 Image preprocessing for CNNs
09:15 Common components of a CNN
11:01 Components: pooling layers
12:31 Building the CNN with PyTorch
14:14 Notable CNNs
17:52 Implementation of CNNs
18:52 Image Preprocessing for CNNs
22:46 How to normalize images for CNN input
23:53 Image preprocessing pipeline with pytorch
24:59 Pytorch data loading pipeline for CNNs
25:32 Building the CNN with PyTorch
28:08 CNN training parameters
28:49 CNN training loop
30:27 Using PyTorch CNN for inference
Рекомендации по теме
Комментарии
Автор

Thanks for the video. I can't find the link to the notebook in the video description, has it been removed?

aramhedayati
Автор

Still a pleasure to watch your explanations. It help learning fast and apprehend concepts quickly. Wish you merry Christmas.

blueaquilae
Автор

08:00-09:00: results are getting abstract ? I think classification results might get more specific (while features get more abstract) 😃

wernerzirkel
Автор

Very complete educational video. Thank you very much. I really enjoyed it

sm-pzer
Автор

Your explanation was very clear and helped me a lot, sir. Thank you!

cego
Автор

Oh I really am trying to understand this better. Thank you very much, it seems this video is clarifying a lot! Very good explanation thanks!

AlessandroOrlandi
Автор

I wanted to thank you--your series have helped out immensely--Please keep up such stellar work! Cheers!

PrimaryKenophobia
Автор

e.g if I want to take a reference image and retrieve all the information within the image I can do it with CNN correct if I am wrong, moving forward with the question which is now since I have the information like histogram color palette latitude etc now I want to superimpose that on an input image, what should I do in order to do that its a personal project I work on short films and I am looking to make an Ai to help me in my color grading

uffkeql
Автор

incredible visualization 💯
Thanks for creating this kind of informative videos
Appreciate your efforts @James Briggs

pavanreddy
Автор

clear explanation, thanks a lot, really helpful.

ashenafibelihu
Автор

thanks for the video, why you chose pytorch for the implementation, Keras seems much easier?

AI_ML_DL_LLM
Автор

awesome I get the stuff better here than in Cal lectures lmao

thomasmeta
Автор

FIRST YOUR CODE FOR 1D. AND 2D CONVOLUTION

jameshopkins
Автор

Even a high school student can understand what is CNN if student watch this.

meenakshichippa
welcome to shbcf.ru