Presentation is loading. Please wait.

Presentation is loading. Please wait.

Logan Lebanoff Mentor: Haroon Idrees

Similar presentations


Presentation on theme: "Logan Lebanoff Mentor: Haroon Idrees"— Presentation transcript:

1 Logan Lebanoff Mentor: Haroon Idrees
Jun 1 - 5

2 Research paper ImageNet Classification with Deep Convolutional Neural Networks Motivations/results of certain approaches Terms ReLU vs sigmoid, GPUs, overlapping pooling, input image size, data augmentation, dropout MatConvNet Manual Necessary to understand how to make changes in the code

3 ImageNet Downloaded training/validation/test image dataset
Understanding the code Modifying

4 ImageNet Load a pretrained network
Retrain the pretrained network to just change the last layer’s weights

5 pretrained = load('E:\Logan\matconvnet-1. 0-beta12\matconvnet-1
pretrained = load('E:\Logan\matconvnet-1.0-beta12\matconvnet-1.0-beta12\examples\data\imagenet12-dropout\pretrained.mat'); pretrained.layers{end} = struct('type', 'softmaxloss', 'name', 'loss') ; [net,info] = cnn_train(pretrained, imdb, fn, opts.train, 'conserveMemory', true) ; % changed net to pretrained

6 ImageNet Change last layer to output a different size vector instead of the default 1000 Find where back propagation happens in the code Change back propagation depth from +inf to 1 Still quite slow Found where the number of epochs was set, and changed it from 20 to 1, for testing

7 % Block 7 %net = add_block(net, opts, 7, 1, 1, 4096, 4096, 1, 0) ; Changed removed net.layers{end+1} = struct('type', 'dropout', 'name', 'dropout7', 'rate', 0.5) ; % Block 8 net = add_block(net, opts, 8, 1, 1, 4096, 5, 1, 0) ; % I changed this to 5 from 1000 net.layers(end) = [] ;

8 ImageNet Error while running test image on my retrained network
Assertion failed in nnsoftmaxloss if nargin <= 2 t = Xmax + log(sum(ex,3)) - reshape(X(c_), [sz(1:2) 1 sz(4)]) ; Y = sum(t(:)) / n ;

9 MNIST Error while running on test image on MNIST
Image depth does not match Changed to grayscale Also had to resize the image to 224x224x3 for ImageNet

10 Next week Retrain network with crowd training images
Using pretrained network Still only training last layer Classification problem Find the count by classifying into groups , , , etc.


Download ppt "Logan Lebanoff Mentor: Haroon Idrees"

Similar presentations


Ads by Google