C4W1L06 Convolutions Over Volumes

Показать описание

DeepLearningAI

Рекомендации по теме

Комментарии

Found this gem after wasting my time on several 'fancy' deeplearning video tutorials.
"If you can’t explain something in simple terms, you don’t understand it."
- Feynman

purpleturtledotcom

THANK YOU for ending my 4 days 9 hours search on understating CNN first layer input data structure/computation.... Moving on to the next step

ericksonramos

The way Andrew deconstructed the 3D convolution into a simple series of steps just goes in to say how great teachers can accelerate learning by manifolds.

muneshchauhan

Best explanation I've found about convolutions over multiple channels. Thanks.

JoaoPedro-piee

He explains this so well that I want to binge the entire playlist.

__dekana__

Blessed are the people who are passionate about nn and just made it into stanford to attend lecture given by this legend

the_random_noob

Such a calm, clear and graphically nice represented explaination. Thanks.

cypherecon

Finally, someone who can clearly explain the material!

tomWil

Thank you so much! This video helped me to understand CNN very much!

majinfu

thankyou sir for having great people like you in this life

mitakshra

The most effective way of explaining depth(no of channels) of CNN

harshdevmurari

Dude I really was searching this for 2 days but there was no clear explanation on volumes thanks a lot

redash

By far the best explanation I have ever seen. Such simple and crisp!

I had one doubt though professor, can we use CNN with data apart from images? If so, what does the filter size represent then? And how do we interpret the features of the data in terms of number of input channels?

sammyj

Excellent. Convolution over volumes was bugging me for a long time.

sau

The formula in the summary is wrong, it should be (n x n x c) input, (f x f x c x z) filter, and (n-f+1 x n-f+1 x z) output dimensions - for z output filters and c input channels. So the convolution is a 4d tensor.

ketilmalde

thanks for clarifying that the filter is channel deep

cem_kaya

Can we use different filter sizes in the multiple filter case? And what will be the output shape then?

nikhilbadveli

Great! So a conv64 basically applies 64 different filters on segments of the input.

DrN

Deep learning k one and only Jeetu bhaiya :)

mohitpandey

@3:11 : So do we add the 3 convolution to output the value of the 4x4 feature map ?

GagarineYuri

C4W1L06 Convolutions Over Volumes

C4W1L06 Convolutions Over Volumes

CNN #5: Convolution over Volume | Convolutional Neural Networks

Convolution over volume

convolutional neural network lecture | data science

All Convolution Animations Are Wrong (Neural Networks)

Convolution - II

L21- Convolutional Neural Network (Convolve over Volume)

Convolutional neural network (part 2): Convolution layer, pooling layer, and simple ConvNet Model

Convolutional neural network (part 1): Conv & pooling layers, complete ConvNet examples

How to Convolutional operation works in CNN | Deep Learning Animation

Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved Mobil...

Calculate Convolutional Layer Volume in ConvNet

Dynamic Convolution: Attention Over Convolution Kernels

From fully connected layers to convolutional layers

Deep Neural Networks - Video 17 CNN Convolution on RGB Images

Convolutional Neural Networks in Deep Learning with Keras and TensorFlow

How convolution works

Development of features in second convolutional layer

CS 152 NN—14: Convolutions: stride

MLT CNN Architectures: MobileNet - theory

Convolutional Neural Networks: convolution, padding, stride, softmax 🧠 ⚙️

Convolutional layers

Stride and Image Size After Convolution || Lesson 30 || Deep Learning || Learning Monkey ||

Convolution Padding - Neural Networks