Skip to content

GitLab

Switch branch/tag
  1. 03 Jun, 2020 5 commits
  3. 02 Jun, 2020 8 commits
    • xinliupitt's avatar
      Add relative positional embedding to KerasBERT (#8606) · 2db2501b
      xinliupitt authored 
      * root dir

* zone updated

* print mask

* preview emb

* tf print

* input only

* emb

* tf print

* emb after mask

* masked_softmax print

* print scores

* multi folder

* first pos emb

* check input shape

* add test temp

* import math

* two classes

* prints

* all get_pos replace

* make time scale private

* pos emb comments

* print input

* embedding_inputs

* tf shape

* dimention list

* tf_util

* print tf_util

* concise

* transformer pos change to layer

* keep length var

* length as input

* None as input

* print time signal

* print time signal

* remove print

* test input shape

* double check shape

* double check shape

* double check shape

* more test

* shape check

* shape check

* print 97 info

* print 97 info new

* test if sam

* assert same

* remove assert

* tf print same

* tf print diff

* output example

* output example

* output example

* formal test

* formal test length

* raise valurerror

* test valurerror

* double check

* comments

* remove prints

* rename relative

* delet naive test

* delete docs in xinliu branch

* code reformat

* import order

* indentation fix

* more files

* adjust char number

* disable not callable

* comment to length

* error of length unequal to input_shape
      2db2501b
    • A. Unique TensorFlower's avatar
      A minor change to model_training_utils of BERT. · fc724b3e
      A. Unique TensorFlower authored 
      PiperOrigin-RevId: 314417394
      fc724b3e
    • Maxim Neumann's avatar
      Internal change · 3d99cc89
      Maxim Neumann authored 
      PiperOrigin-RevId: 314412294
      3d99cc89
    • A. Unique TensorFlower's avatar
      Fix total block num bug in tf2 efficientnet. · 2af9696b
      A. Unique TensorFlower authored 
      PiperOrigin-RevId: 314405729
      2af9696b
    • Hongkun Yu's avatar
      write_meta_graph=False as we do not care the graph. · 7580f0a2
      Hongkun Yu authored 
      PiperOrigin-RevId: 314394246
      7580f0a2
    • Chen Chen's avatar
      Internal change · 8eb91073
      Chen Chen authored 
      PiperOrigin-RevId: 314373769
      8eb91073
    • A. Unique TensorFlower's avatar
      Add unit tests for bert_models.py · c25c3e88
      A. Unique TensorFlower authored 
      PiperOrigin-RevId: 314270569
      c25c3e88
    • Hongkun Yu's avatar
      Fix cycle deps found through github CI · 8fd10a57
      Hongkun Yu authored 
      PiperOrigin-RevId: 314254688
      8fd10a57
  5. 01 Jun, 2020 4 commits
  7. 30 May, 2020 2 commits
  9. 29 May, 2020 11 commits
  11. 28 May, 2020 4 commits
    • Abdullah Rashwan's avatar
      Internal change · 980b27d5
      Abdullah Rashwan authored 
      PiperOrigin-RevId: 313662797
      980b27d5
    • Hongkun Yu's avatar
      Deprecate old customized training loop for run_classifier.py as compile/fit... · abf60128
      Hongkun Yu authored 
      Deprecate old customized training loop for run_classifier.py as compile/fit fully satisfy needs/performance.

PiperOrigin-RevId: 313660745
      abf60128
    • Reed Wanderman-Milne's avatar
      Use float32 activation in Transformer. · 94b1efc1
      Reed Wanderman-Milne authored 
      Float32 is used if the model uses mixed precision with bfloat16. Float16 activation are unchanged.

The motivation is that BERT with the LAMB optimizer with a gelu activation has an unstable loss when gelu is in bfloat16. Unfortunately, it is not easy to check if the LAMB optimizer and gelu is used, and perhaps there are other cases that work better with float32 activations instead of bfloat16 activations, so we always do the activation in float32 instead of bfloat16.

PiperOrigin-RevId: 313618322
      94b1efc1
    • A. Unique TensorFlower's avatar
      Internal change · fbec2dbe
      A. Unique TensorFlower authored 
      PiperOrigin-RevId: 313536026
      fbec2dbe
  13. 27 May, 2020 4 commits
  15. 26 May, 2020 2 commits
    • pkulzc's avatar
      Release MobileDet code and model, and require tf_slim installation for OD API. (#8562) · 451906e4
      pkulzc authored 
      * Merged commit includes the following changes:
311933687  by Sergio Guadarrama:

    Removes spurios use of tf.compat.v2, which results in spurious tf.compat.v1.compat.v2. Adds basic test to nasnet_utils.
    Replaces all remaining import tensorflow as tf with import tensorflow.compat.v1 as tf

--
311766063  by Sergio Guadarrama:

    Removes explicit tf.compat.v1 in all call sites (we already import tf.compat.v1, so this code was  doing tf.compat.v1.compat.v1). The existing code worked in latest version of tensorflow, 2.2, (and 1.15) but not in 1.14 or in 2.0.0a, this CL fixes it.

--
311624958  by Sergio Guadarrama:

    Updates README that doesn't render properly in github documentation

--
310980959  by Sergio Guadarrama:

    Moves research_models/slim off tf.contrib.slim/layers/framework to tf_slim

--
310263156  by Sergio Guadarrama:

    Adds model breakdown for MobilenetV3

--
308640...
      451906e4
    • Allen Wang's avatar
      Modify `augment.transform` to use `tf.rank` rather than `len(shape)`. · 73b5be67
      Allen Wang authored 
      PiperOrigin-RevId: 313259032
      73b5be67