Comments (3)
also another question when i extracted features of end layer using vgg19 it took more than 6 hours to reach a convergence, while when using alexnet end layer it gave more accurate results in almost 20 mins?
vgg19 suppose to give error rate less than that of alexnet, shouldn't that mean a better features representation?
sorry if i had soo many questions but yr work is really interesting
from deep-goggle.
Did you truncate the network in the same way
net.layers = net.layers(1:end-3)
?
As for VGG-19 being very slow, it is because of the network is massive and each forward pass takes much longer than for alexnet. Also, the hyperparameters were tuned for Alexnet. If you want to play with VGG-19 it might be better to use the code here - https://github.com/aravindhm/nnpreimage.
from deep-goggle.
yes it worked, thanks alot for your help and support
will check the link you provide, i understand the process much better now
from deep-goggle.
Related Issues (15)
- How to reconstruct from sift? HOT 4
- running my own vgg19 network HOT 15
- Wrong Net object HOT 4
- GOT Inf when traing HOT 2
- in invert_nn.m about backpropagation HOT 4
- how to get x0_sigma.mat, if I use other dataset rather than ImageNet HOT 3
- Question about two subsets of feature channels mentioned in your paper
- What about a specific subset of features from a layer?
- matlabpool removed
- filnames of images inverted in the paper HOT 2
- how to run my own networks HOT 6
- Can't find imagenet-caffe-ref.mat HOT 1
- Reference to non-existent field 'weights'. HOT 2
- can this tool visualize the learned weights/filters of CNN? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deep-goggle.