- 04 10月, 2018 2 次提交
-
-
由 Francois Chollet 提交于
-
由 Fariz Rahman 提交于
* use mode arg * add loop test * add stricter condition * make dict behaviour similar
-
- 03 10月, 2018 3 次提交
-
-
由 Paul M 提交于
### Summary This PR provides fix for `engine.training_generator.fit_generator` when `workers=0`. It used train data for validation and ignored `len(val_data)` when `val_data` was instance of `keras.Sequence` ### Related Issues [#10855](https://github.com/keras-team/keras/issues/10855) ### PR Overview - [x] This PR requires new unit tests [y/n] (make sure tests are included) - [ ] This PR requires to update the documentation [y/n] (make sure the docs are up-to-date) - [ ] This PR is backwards compatible [y/n] - [ ] This PR changes the current API [y/n] (all API changes need to be approved by fchollet)
-
由 Taehoon Lee 提交于
* Add `conv_transpose` into reference operations * Add a white space
-
由 Gabriel Bianconi 提交于
* Graciously handle legacy Sequential configs * Remove warning
-
- 02 10月, 2018 3 次提交
-
-
由 Heath Henley 提交于
-
由 Gabriel de Marmiesse 提交于
* Working on improving tensor flow callbacks * Adding batch level TensorBoard logging (implementing the `on_batch_end` method to the TensorBoard class * Interim commit -- added notes. * Corrected stylistic issues -- brought to compliance w/ PEP8 * Added the missing argument in the test suite. * Added the possibility to choose how frequently tensorboard should log the metrics and losses. * Fixed the issue of the validation data not being displayed. * Fixed the issue about the callback not remembering when was the last time it wrote to the logs. * Removed the error check. * Used update_freq instead of write_step. * Forgot to change the constructor call.
-
由 Gabriel de Marmiesse 提交于
* Added a global timeout. * Fixed a typo.
-
- 01 10月, 2018 2 次提交
-
-
由 Gabriel de Marmiesse 提交于
* Trying to fix pep8 tests. * Fixed pep8 errors in master. * Adding a timeout. * Did not manage to find more about the timeout.
-
由 Dan Erez 提交于
* add variable initializers ( ones, zeros, ones_like, zeros_like ). consolidate tests of all variable initializers + add new tests. * split up the unit tests * spelling error * undo formating changes
-
- 30 9月, 2018 3 次提交
-
-
由 Dan Erez 提交于
-
由 Dan Erez 提交于
* add cos + sin + tests to numpy backend * add one black line at the end for pep 8 compliance
-
由 Taehoon Lee 提交于
-
- 29 9月, 2018 10 次提交
-
-
由 Francois Chollet 提交于
-
由 Francois Chollet 提交于
-
由 Francois Chollet 提交于
-
由 Francois Chollet 提交于
-
由 Gabriel de Marmiesse 提交于
* adjust softmax implementation * theano only handle 2-dim case for softmax [theano softmax](http://deeplearning.net/software/theano/library/tensor/nnet/nnet.html#theano.tensor.nnet.nnet.softmax) * clean softmax activation and add 3d softmax test * fix axis * fix 1d case and test case * fix 1d case and test case * change to standard test * fix test case * Update activations_test.py * got the value error back. * Moved correctness test to the backend tests. * Added a correctness test to activations_test.py.
-
由 Francois Chollet 提交于
-
由 Yanbo Liang 提交于
-
由 Chase Brignac 提交于
-
由 Álvaro Peris 提交于
* Save np data only as dataset * Fix docs * Update test for saving large np.array objects * Update tests for saving large np.array objects
-
由 望江车神 提交于
"from sklearn.grid_search import GridSearchCV" is out of date and has changed in the new version (0.18-). Detailed description: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. This module will be removed in 0.20. Update "from sklearn.grid_search import GridSearchCV" to “from sklearn.model_selection import GridSearchCV”.
-
- 28 9月, 2018 5 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
-
由 Taehoon Lee 提交于
-
- 27 9月, 2018 5 次提交
-
-
由 Jay Joshi 提交于
* Add better error message for model.summary() Added extra points in the error message to provide a better error message. For detailed discussion consider checking issue #11217 on keras repo. Old error message: "This model has never been called, thus its weights have not yet been created, so no summary can be displayed. Build the model first (e.g. by calling it on some test data)." New error message: "This model has not yet been built. Build the model first by calling build() or calling fit() with some data. Or specify input_shape or batch_input_shape in the first layer for automatic build" * Fix indentation problem causing build error in python 2.7
-
由 tedyu 提交于
* Raise ValueError when merge_mode is unknown in Bidirectional#call * use string formatting * Replace tabs with spaces
-
由 Taehoon Lee 提交于
-
由 Pattarawat Chormai 提交于
Because the first index returned from Keras' tokenizer is 1. Hence, the current condition will discard the last word, ie. index=20000.
-
由 Francois Chollet 提交于
-
- 26 9月, 2018 3 次提交
-
-
由 Francois Chollet 提交于
-
由 Francois Chollet 提交于
-
由 Gabriel de Marmiesse 提交于
-
- 25 9月, 2018 1 次提交
-
-
由 fuck_linux 提交于
if -> elif
-
- 24 9月, 2018 1 次提交
-
-
由 Yanbo Liang 提交于
* Fix bug in sparse_top_k_categorical_accuracy * Make unit test parametrization
-
- 23 9月, 2018 1 次提交
-
-
由 Taehoon Lee 提交于
* Style fixes for enabling PEP8 501 * Style fixes
-
- 22 9月, 2018 1 次提交
-
-
由 Francois Chollet 提交于
-