Comments (8)
How much do they differ? Is this on CPU or GPU? Do you use cuDNN?
from recipes.
I use GPU and cuDNN for both caffe and lasagne. Also I have just installed Theano and Lasagne from master today.
The l2 norm of their difference for an example image is 0.14590697. (the example image the is cat image used in the caffe tutorial)
plt.plot(lasagne_out - caffe_out)
Here is a plot of the difference, as I said they are very similar.
from recipes.
Well this was not a good example (since some might think the preprocessing is not the same for caffe and lasagne).
For the input np.zeros((1, 3, 224, 224), dtype=np.float32)
the l2 norm of the difference is 0.096159138.
Also here is the plot for plt.plot(lasagne_out - caffe_out)
.
from recipes.
Hi @yassersouri, thanks for your report.
It looks like several of the pooling layers should use ignore_border=False
but are not. My guess is that when I wrote this I was using an older version of Lasagne (before Lasagne/Lasagne#374).
With this change I get an l2 norm of the difference for zero input of 9.7e-8, I will push an updated version shortly.
from recipes.
@ebenolson Thanks.
from recipes.
Oh, good catch! Sadly, this also means it won't be able to use cuDNN for pooling any more (it always ignores the border).
from recipes.
Do other models in the model zoo need similar updates?
from recipes.
I don't think so - I seem to remember this being a peculiarity of googlenet (I think this is why I was using both Pool2DLayer
and Pool2DLayerDNN
).
However, it would be good to verify that, and add some numerical tests to catch any future problems. PR's welcome 😄
from recipes.
Related Issues (20)
- 3D UNet implementation HOT 7
- reason behind low value of parameters in VGG19 HOT 1
- error when set values for vgg-19 HOT 2
- modelzoo resnet50.py incompatible to Python 3 HOT 3
- Implementation of Convolutional Spatial Transformer and Siamese network HOT 3
- no sandbox.cuda
- Bad argument to Theano: No. of dimensions changes in the error after reshaping
- Question not an Issue: fliping the arrays HOT 1
- cifar100 with resnet HOT 1
- pretrained network for small images HOT 1
- https://s3.amazonaws.com/lasagne/recipes/pretrained/imagenet/vgg16.pkl HOT 6
- vgg16.pkl without aws cli
- Need help with S3 Browser based downloads HOT 1
- Dice coeff is not changing since the first epoch and binary accuracy changes and is increased to 1?
- Problem with op.grad in OpFromGraph - Guided Backpropagation
- Wrong order of stride and pad arguments in build_simple_block HOT 3
- Broken links in Video features with C3D.ipynb example HOT 5
- Training C3D
- Wrong pretrained weights for UNet example HOT 1
- DICE coefficient loss function HOT 23
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 recipes.