- 28 Feb, 2018 3 commits
-
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
- 26 Feb, 2018 5 commits
-
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
- 23 Feb, 2018 1 commit
-
-
Andrew M. Dai authored
PiperOrigin-RevId: 186781401
-
- 22 Feb, 2018 4 commits
-
-
Andrew M. Dai authored
Move gen_data and gen_vocab to parent directory to prevent import madness in the open-source code. Remove unnecessary bazel dependency and documentation in README. PiperOrigin-RevId: 186638059
-
Andrew M. Dai authored
-
Andrew M. Dai authored
-
Andrew M. Dai authored
PiperOrigin-RevId: 186541910
-
- 20 Feb, 2018 2 commits
-
-
Andrew M. Dai authored
PiperOrigin-RevId: 186265033
-
Andrew M Dai authored
Merging in improvements and fixes to adversarial_text
-
- 17 Feb, 2018 12 commits
-
-
Andrew M. Dai authored
-
Andrew M. Dai authored
PiperOrigin-RevId: 185783053
-
Andrew M. Dai authored
Replace tf.contrib.framework.get_or_create_global_step() with tf.train.get_or_create_global_step() in third_party/tensorflow_models See https://www.tensorflow.org/api_docs/python/tf/contrib/framework/get_or_create_global_step and #2795 PiperOrigin-RevId: 176534973
-
Andrew M. Dai authored
PiperOrigin-RevId: 173414999
-
Andrew M. Dai authored
Add option for when there is only one label for classification, for speed. (The case for the standard datasets). PiperOrigin-RevId: 172774825
-
Andrew M. Dai authored
PiperOrigin-RevId: 172665358
-
Andrew M. Dai authored
memory and fixes the OOM errors. PiperOrigin-RevId: 172374935
-
Andrew M. Dai authored
Change logit and activation shapes to follow standard convention with batch size in the first dimension. PiperOrigin-RevId: 172172495
-
Andrew M. Dai authored
PiperOrigin-RevId: 171498799
-
Asim Shankar authored
MNIST: Eager execution.
-
Asim Shankar authored
-
Asim Shankar authored
-
- 16 Feb, 2018 5 commits
-
-
Asim Shankar authored
-
Asim Shankar authored
-
Asim Shankar authored
-
Asim Shankar authored
Add an example showing how to train the MNIST model with eager execution enabled. (This change requires changes to TensorFlow made after the 1.6 release branch was cut, i.e., will require a build from source or TensorFlow 1.7+)
-
Karmel Allison authored
* Refining preprocessing, part 1 * Refinements to preprocessing resulting from multi-GPU tests * Reviving one-hot labels * Reviving one-hot labels * Fixing label shapes * Adding random flip back in * Reverting unnecessary linting of test file * Respond to CR * Respond to CR * Respond to CR
-
- 14 Feb, 2018 1 commit
-
-
Lukasz Kaiser authored
Small polishing changes to DELF code.
-
- 13 Feb, 2018 6 commits
-
-
Dan Ellis authored
Cosmetic changes to spectrogram_to_mel_matrix()
-
Manoj Plakal authored
To simplify syncing this c ode back into Google.
-
Manoj Plakal authored
Add sanity checks to mel computation.
-
Manoj Plakal authored
-
Manoj Plakal authored
Clamp the requested frequency range to [0, Nyquist].
-
Andre Araujo authored
PiperOrigin-RevId: 185469605
-
- 12 Feb, 2018 1 commit
-
-
derekjchow authored
Update installation.md
-