- 22 8月, 2019 4 次提交
-
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
- 26 7月, 2019 1 次提交
-
-
由 Fariz Rahman 提交于
* suppress serde warning * add test * pep8 * python2 * theano fix * theano fix * pop before call * few fixes * fix wrappers * mooore fix
-
- 24 7月, 2019 1 次提交
-
-
由 Neutron3529 提交于
move self.l1 and self.l2 outside K.sum may increase the performance of calculating the norm. In deep learning, the norm should not be very large (a large norm will make loss function useless), so move self.l1 and self.l2 outside K.sum will not cause overflow problem
-
- 11 7月, 2019 1 次提交
-
-
由 Fariz Rahman 提交于
* allow len1 * add test * pep8 * rem unusedvar * skip theano * typo * fix * pep8
-
- 10 7月, 2019 1 次提交
-
-
由 Abhijith Nair 提交于
-
- 07 7月, 2019 1 次提交
-
-
由 Abhinav Sagar 提交于
-
- 04 7月, 2019 1 次提交
-
-
由 HarikrishnanBalagopal 提交于
-
- 03 7月, 2019 6 次提交
-
-
由 Bjarne Thorsted 提交于
In certain use cases, load_weights() would cause OSError if called repeatedly on many different files. The proposed addition will now make sure the HDF5 files are closed before exiting.
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
由 Taehoon Lee 提交于
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
- 28 6月, 2019 1 次提交
-
-
由 苏剑林(Jianlin Su) 提交于
-
- 25 6月, 2019 2 次提交
-
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
- 24 6月, 2019 1 次提交
-
-
由 Liz Decolvenaere 提交于
* Added weighted metrics to save/load * Patch to enable backwards-compatability with versions that did NOT save weighted_metrics * Line wrap to fit PEP8 style
-
- 18 6月, 2019 1 次提交
-
-
由 adrianstaniec 提交于
-
- 08 6月, 2019 3 次提交
-
-
由 François Chollet 提交于
-
由 François Chollet 提交于
-
由 ghostplant 提交于
If building TF with XLA option enabled, an additional `xla_gpu:0` device will be exposed to users which is a domain for running graph in XLA mode. Should skip this device to avoid the number of multi_gpu improperly inferred.
-
- 05 6月, 2019 1 次提交
-
-
由 François Chollet 提交于
-
- 02 6月, 2019 1 次提交
-
-
由 HarikrishnanBalagopal 提交于
When we dilate a kernel of size N by D we take N - 1 steps of size D and finally sample 1 more pixel, hence (N - 1) * D + 1.
-
- 30 5月, 2019 1 次提交
-
-
由 Abhinav Sagar 提交于
-
- 29 5月, 2019 3 次提交
-
-
由 François Chollet 提交于
-
由 François Chollet 提交于
This reverts commit 08f6bdeb.
-
由 tanzhenyu 提交于
* Sync keras optimizers with tf.keras optimizers. Changes: 1) epsilon has been removed from argument list, using default instead for future support of mixed precision. passing epsilon is still supported. 2) decay has been removed from argument list, for future support of learning rate decay objects. passing decay is still supported. 3) all lr has been changed to learning_rate. passing lr is still supported. 4) add initial_accumulator_value to Adagrad. 5) add momentum and centered to RMSprop. 6) Adam optimize won't have vhat if amsgrad is not present. set_weights is override to maintain backward compatibility. 7) Adadelta adds iterations to its weight list. set_weights is override to maintain backward compatibility. 8) Adagrad adds iterations to its weight list. set_weights is override to maintain backward compatibility. 9) RMSprop adds iterations to its weight list. set_weights is override to maintain backward compatibility. 10) Nadam changes default learning rate from 0.002 to 0.001 11) Adamax changes default learning rate from 0.002 to 0.001 12) Adadelta changes default learning rate from 1.0 to 0.001 13) Adagrad changes default learning rate from 0.01 to 0.001 * Slightly refactor SGD. * Remove blank spaces. * Fix some pep8 errors. * Fix some error. * Restore learning rate to previous default. For Adadelta, Adamax, Adagrad * Adjust some more lr. * Nit
-
- 25 5月, 2019 1 次提交
-
-
由 Katherine Wu 提交于
* Use layer.dtype as the default dtype when adding a new weight, and add dtype to network initialization. * Fix CNTK test.
-
- 24 5月, 2019 4 次提交
-
-
由 Andreas Mueller 提交于
* don't reuse names in introductory example I would try to be as explicit as possible in the first example of the functional API * Update functional-api-guide.md rename symbolic tensors to output
-
由 salmituukka 提交于
* Fixed plot_model for expand_nested=True * Fixed plotting direct link from submodel to submodel * Simplified expression
-
由 CVxTz 提交于
* add cnn seq2seq example * PEP8 - Lines were too long * Style fixes.
-
由 Shawn Choi 提交于
Noticed some changes that hasn't been applied to the ReadMe Doc. This change will refactor those artifacts.
-
- 22 5月, 2019 1 次提交
-
-
由 cclauss 提交于
__sudo: required__ no longer is... [Travis are now recommending removing the __sudo__ tag](https://blog.travis-ci.com/2018-11-19-required-linux-infrastructure-migration). "_If you currently specify __sudo:__ in your __.travis.yml__, we recommend removing that configuration_"
-
- 21 5月, 2019 1 次提交
-
-
由 fpc 提交于
-
- 06 5月, 2019 1 次提交
-
-
由 Greg French 提交于
-
- 03 5月, 2019 1 次提交
-
-
由 Abhinav Sagar 提交于
* Updated readme for windows users * Fix phrasing
-
- 02 5月, 2019 1 次提交
-
-
由 cclauss 提交于
-