-
I am trying to convert the U-NET model from caffe to keras.
The model was downloaded from [U-NET webpage](http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/) - here is the [direct link](http…
-
Hi,
Thanks for making this code available. I wanted to give this a quick look. I am on Mac OS, installed latest Keras and Tensorflow. Tried on python 3.5 after 2to3 for mostly the print statements.
…
-
This packet tokenizer unknown switch FCA6 issue appear for idRO new Chaos after the se…
-
While debugging huge memory consumption issues, I stumbled that using any RNN with `return_sequences=False` (eg. SimpleRNN, GRU) results in an upcast to `float64`. Consequently everything that follows…
-
It would be useful to support maxout. This should be pretty trivial, but there's some room for bugs storing the weights so it will have to be tested carefully.
-
When I tried to run `python run_demo.py` I got the following error (even though I have installed Flask)
```
Traceback (most recent call last):
File "run_demo.py", line 7, in
from betago.model …
-
Hello everyone,
I try to use pythonnet with some other compiled libraries like numpy, scipy, theano, and overall keras. Pythonnet allows me too get the data I want, to treat them with keras.
The pro…
-
Hey guys,
I was wondering how are the initial internal states in a recurrent layer dealt with? So far it appears they are reset are every run. Is there any way to preserve them?
I'd like to be able …
-
Moved from https://github.com/benanne/Lasagne/issues/133
skaae updated
8 years ago
-
I want to implement the recurrent model explained in eqn 11,12,13 of [this](http://arxiv.org/abs/1509.06664) paper. As far as I understand, I need to subclass the recurrent layer from keras, but I do …