Comments (6)
@MarvinTeichmann that indeed looks really great! It would definitely be useful for our users. Do not hesitate to send us a pull request :) Just my suggestion is to move the 'semantic segmentation loss' to 'objectives.py' file instead of 'losses.py' file, and change 'logits'/'labels' arguments name to 'y_pred'/'y_true', for consistency with other objective functions.
@FreakTheMighty You can go ahead, thanks!
from tensorflow-fcn.
Thanks for the hint and good idea. I have implemented the upscore_layer and the semantic segmentation loss to tflearn. Can you have a short look at it? I have no experience with tflearn. Needed to do some changed to fit in to the framework but have cannot test whether it works now.
Thanks in advance! If you approve my code, I will open a pull request.
from tensorflow-fcn.
@MarvinTeichmann wow, that was fast :D. I can take a closer look tonight, but I think it makes sense to open a pull request sooner rather than later. The maintainer, @aymericdamien, of tflearn will be able to give the most substantive feedback.
I only get a few hours a day to work on these things, but I'd like to contribute an example that recreates the FCN using tflearn and your new layers and loss.
from tensorflow-fcn.
@aymericdamien I've started working on porting @MarvinTeichmann networks here. MarvinTeichmann/tflearn#1 I'm sure I will get stuck along the way, but I think it will be good experience.
One thing I noticed about the weak_cross_entropy_2d_loss
objective is that it takes more than two arguments where tflearn objectives are passed as strings into the solver. How would that interface work in tflearn?
from tensorflow-fcn.
Yes, because of the extra argument, it cannot directly be called as a string argument in regression
layer, however, loss argument can be a function, so it could be something like:
def my_loss(y_pred, y_true):
return tflearn.weak_cross_entropy_2d_loss(y_pred, y_true, num_classes=10)
net = ...
net = tflearn.regression(net, loss=my_loss)
Another approach would be to remove num_classes argument and calculate it automatically by checking dimension of y_true. So passing just
net = ...
net = tflearn.regression(net, loss='weak_cross_entropy_2d_loss')
will work
from tensorflow-fcn.
Merged in tflearn/tflearn#137.
from tensorflow-fcn.
Related Issues (20)
- AttributeError: type object 'GraphKeys' has no attribute 'REGULARIZATION_LOSSES' HOT 3
- test_fcn32 fails, but test_fcn8 and test_fcn16 complete
- Test loss diverges during training nyud-fcn32s-color
- Memory error
- A problem about fcn8_vgg.py HOT 2
- Extend your get_deconv_filter from 2D to 3D. How?
- I train datasets "ADEChallengeData2016",But loss is almost the same HOT 3
- A problem about the deconvolution HOT 3
- A problem with fcn8_vgg.py
- An example of images with shape [None, h, w, 3]
- ValueError: No gradients provided for any variable
- The problem about fcn8_vgg.py
- is the vgg16.npy random weights or trained weights....?
- Max Tensor Size in FCN-16 and FCN-32
- What does the "use_dilated" mean in "build" function? HOT 1
- the kernel–size of upscore–layer(deconvolution) in fcn32s
- convert the ckpt model to movidius graph HOT 1
- Hello, could you tell me how to modify to achieve the effect in the article, you can run but the result is very poor.
- The weight decay (the regularization loss) is not applied for the fc_layer and upscore_layer
- What the speed it can reach?
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 tensorflow-fcn.