Deep Learning(CS7015): Lec 11.5 Image Classification continued (GoogLeNet and ResNet)

preview_player
Показать описание
lec11mod05
  1. NPTEL-NOC IITM
  2. deep learning
  3. prof.mitesh khapra
  4. iitmadras
  5. nptel deep learning
Рекомендации по теме
Deep Learning(CS7015): Lec 0:22:50

Deep Learning(CS7015): Lec 11.5 Image Classification continued (GoogLeNet and ResNet)

Deep Learning(CS7015): Lec 0:11:19

Deep Learning(CS7015): Lec 12.8 Deep Dream

Deep Learning(CS7015): Lec 0:11:31

Deep Learning(CS7015): Lec 15.4 Attention over images

Deep Learning(CS7015): Lec 0:18:29

Deep Learning(CS7015): Lec 11.1 The convolution operation

Deep Learning(CS7015): Lec 0:06:36

Deep Learning(CS7015): Lec 1.6 The Curious Case of Sequences

Deep Learning(CS7015): Lec 0:06:12

Deep Learning(CS7015): Lec 12.4 Finding influence of input pixels using backpropagation

Deep Learning(CS7015): Lec 0:36:36

Deep Learning(CS7015): Lec 10.4 Continuous bag of words model

Deep Learning(CS7015): Lec 0:16:58

Deep Learning(CS7015): Lec 11.3 Convolutional Neural Networks

Deep Learning(CS7015): Lec 0:06:23

Deep Learning(CS7015): Lec 8.5 Dataset augmentation

Deep Learning(CS7015): Lec 0:20:49

Deep Learning(CS7015): Lec 11.4 CNNs (success stories on ImageNet)

Deep Learning(CS7015): Lec 0:02:57

Deep Learning(CS7015): Lec 11.4 (Par-2) CNNs (success stories on ImageNet) (Contd.)

Deep Learning(CS7015): Lec 0:09:11

Deep Learning(CS7015): Lec 5.1 & Lec 5.2 Recap: Learning Parameters: Guess Work, Gradient Descen...

Deep Learning(CS7015): Lec 0:12:27

Deep Learning(CS7015): Lec 11.2 Relation between input size, output size and filter size

Deep Learning(CS7015): Lec 0:08:11

Deep Learning(CS7015): Lec 14.3 How LSTMs avoid the problem of vanishing gradients

Deep Learning(CS7015): Lec 0:06:31

Deep Learning(CS7015): Lec 12.2 Visualizing filters of a CNN

Deep Learning(CS7015): Lec 0:12:45

Deep Learning(CS7015): Lec 4.7 Backpropagation: Computing Gradients w.r.t. Parameters

Deep Learning(CS7015): Lec 0:16:37

Deep Learning(CS7015): Lec 8.11 Dropout

Generative Adversarial Networks 0:06:04

Generative Adversarial Networks

Deep Learning Part 0:14:01

Deep Learning Part - II (CS7015): Lec 18.7 Motivation for Sampling

Deep Learning(CS7015): Lec 0:13:39

Deep Learning(CS7015): Lec 2.2 McCulloch Pitts Neuron, Thresholding Logic

Lec 37 : 1:10:33

Lec 37 : Introduction to Deep Learning

Deep Learning Part 0:27:59

Deep Learning Part - II (CS7015): Lec 18.1 Joint Distributions

Deep Learning(CS7015): Lec 0:24:57

Deep Learning(CS7015): Lec 9.2 Unsupervised pre-training

Deep Learning(CS7015): Lec 0:17:39

Deep Learning(CS7015): Lec 11.3 (Part-2) Convolutional Neural Networks (Contd.)

Комментарии
Автор

16:35 If we have a trained model with less layers, why not use the weights and identity function from that model as initialization for the weights in the deeper network? That way when you go through gradient descent, we should get at least as good a solution.

mainakghosh
Автор

@11:58 How does using avg-pool instead of max pool make a change?
doesn't adjusting the size of the kernel make the difference.

mlofficial
Автор

at the avg pooling layer in google net, if a 1024x1x1 pool filter is used on 1024x7x7, wont the output be 7x7 instead of 1024?

vaibhavthalanki
Автор

D1<D, in this D is depth right? that means D =3 generally for rgb? if yes then how D1<D because as we move depth increases(as after input image D is the number of filters)

rituchoudhary