lameeus 64ee9acfdb 1) Extended layers to everything that has a ReLU activation ...

2) Added layer name to the warning
3) Corrected the dead neuron count (should work for both Theano and TF (tested for TF))
4) Added a print alongside the warning since for me the warning stopped showing after some epochs (might be a bug at my side).

2017-10-25 12:13:09 +02:00

..

activations

fix PEP8

2017-06-15 17:00:32 -07:00

applications

Fix bad argument name for require_flatten

2017-10-20 15:59:03 +02:00

backend

tensorflow_backend.py import dtype

2017-10-18 00:49:51 -04:00

callbacks

1) Extended layers to everything that has a ReLU activation

2017-10-25 12:13:09 +02:00

constraints

add clip alias to correct place

2017-06-15 17:36:12 -07:00

datasets

Fix for Python 3 in conll dataset loading

2017-09-07 15:19:48 +03:00

initializers

fix imports

2017-06-15 17:20:58 -07:00

layers

remove Deconvoluion3D because it is available in keras upstream

2017-10-17 16:45:55 -04:00

losses

Fix DSSIM definition (#99)

2017-06-09 08:19:41 -07:00

metrics

Move activations, metrics, optimizers and regularizers (#94)

2017-06-15 16:15:59 -07:00

optimizers

Update ftml for Keras changes to optimizers (#137)

2017-08-16 20:51:32 -07:00

preprocessing

Add activations, regularizers...

2017-01-25 10:26:45 +05:30

regularizers

fix PEP8

2017-06-15 17:00:32 -07:00

tests

add tests for ftml

2017-06-16 13:20:09 -07:00

utils

save_all_weights and load_all_weights (#90)

2017-06-07 20:59:48 -07:00

wrappers

Add activations, regularizers...

2017-01-25 10:26:45 +05:30

__init__.py

initializations->initializers

2017-03-19 07:28:31 +05:30