GitLab

* research/attention_ocr: Minor changes to make it compatible with python 3.

* research/attention_ocr: Script to create a smaller test file.

* Remove differential_privacy and morph_net from research folder because they have been migrated to google-research/ for a while

* Update README.md

* Update CODEOWNERS

Remove resnet in readme

Since the GAN link is now dead, it can safely be removed.

The colab and github link were in wrong hrefs.

Colab will soon update the default version of tensorflow to 2.1.0. In order for this notebook to continue to work, I'm adding a line magic that will ensure this notebook continues to use tensorflow 1.x and execute without errors.

Internal cleanup (py2->py3) plus the following changes:

285513318  by Sergio Guadarrama:

    Adds a script for post-training quantization

284222305  by Sergio Guadarrama:

    Modified squeeze-excite operation to accommodate tensors of undefined (Nonetype) H/W.

282028343  by Sergio Guadarrama:

    Add MobilenetV3 and MobilenetEdgeTPU to the slim/nets_factory.

PiperOrigin-RevId: 289455329
Co-authored-by: Sergio Guadarrama <sguada@gmail.com>

- Made code work with either TF v1.x or TF v2.x, while explicitly
  enabling v1.x behavior.l
- Pulled slim from tf_slim package instead of through tensorflow
  contrib. Note that tf_slim itself uses tensorflow contrib so
  it requires using TF v1.x for now (referenced a relevant PR
  which should remove this limitation once it gets merged).
- Removed all mention of scipy. Switched wav writing to soundfile.
- Switched package name to soundfile instead of pysoundfile. The
  former is the newer name.
- Updated installation instructions for both vggish and yamnet to
  reflect these changes.
- Tested new installation procedures. vggish works with TF v1.15,
  yamnet works with TF v1.15.0 as well as TF v2.1.0.

* Update slim include.

* Force installation of tensorflow 1.14 (not tf2).

* Code will run without soundfile (but die if you attempt to read a sound file).

* Update slim include.

* Force installation of tensorflow 1.14 (not tf2).

* Push conflicting earlier changes in files touched.

PiperOrigin-RevId: 268414407
PiperOrigin-RevId: 278006953
PiperOrigin-RevId: 281567252
PiperOrigin-RevId: 288363770

* Removes tf.contrib usage and replaces them with direct imports for lstm object detection.

PiperOrigin-RevId: 286065032

* Internal changes.

PiperOrigin-RevId: 288363770

Colab will soon update the default version of tensorflow to 2.1.0. In order for this notebook to continue to work, I'm adding a line magic that will ensure this notebook continues to use tensorflow 1.x and execute without errors.

Fix link.

* Manually quantize selected inputs before summing them up.

PiperOrigin-RevId: 283653640

* Fix messy variable paths in LSTD head.

With a VariableScope passed as parameter into tf.variable_scope(),
TF gets all confused and starts placing variables into scopes different
from operations (variable_scope != name_scope).  That leads to very messy
TF graphs.

Before CL:
  FeatureExtractor/LSTM/conv_lstm_cell/bottleneck_0/depthwise_weights
  FeatureExtractor/LSTM/LSTM/conv_lstm_cell/bottleneck_0/separable_conv2d/depthwise

After CL:
  FeatureExtractor/LSTM/conv_lstm_cell/bottleneck_0/depthwise_weights
  FeatureExtractor/LSTM/conv_lstm_cell/bottleneck_0/separable_conv2d/depthwise

PiperOrigin-RevId: 284011539

Fix variable name issue in MobileNet example notebook.
Make sure all `base_name` variables are renamed to `checkpoint_name`.

The wget command for the KITTI dataset in the currently downloads the html for GitHub's fancy display of the text file. This change fixes that so it instead downloads the raw txt file (no more trying to resolve host '<')

Add files for YamNet, a sound event classifier.

* Make this file TensorFlow 2.0 compatible

* Update remove_gt_colormap.py

* Internal changes to tf.contrib symbols

PiperOrigin-RevId: 277940048

* Create visualwakewords dataset using slim scripts instead of custom scripts.

PiperOrigin-RevId: 278917344

* update for python3.0 compatibility

Thanks to issue raised at https://github.com/tensorflow/models/issues/7799

* Fix segmentation fault on client destruction.

edgetpu::EdgeTpuContext needs to be created before tflite::Interpreter

280142968  by Zhichao Lu:

    Opensource MobilenetEdgeTPU + ssdlite into third-party object detection APIs on EdgeTPU.

--
280134001  by Zhichao Lu:

    Adds MobilenetEdgeTpu + ssdlite into internal object detection APIs on EdgeTPU.

--
278941778  by Zhichao Lu:

    Add support for fixed input shapes for 'encoded_image_string_tensor' and 'tf_example' inputs.

--
278933274  by Zhichao Lu:

      Adding fool proof check to avoid using 1x1 depthwise conv op.

--
278762192  by Zhichao Lu:

    Ensure correct number of iterations after training resumes.

--
278746440  by Zhichao Lu:

    Internal change.

--
278006953  by Zhichao Lu:

    Internal changes to tf.contrib symbols

--
278006330  by Zhichao Lu:

    Internal changes to tf.contrib symbols

--
277593959  by Zhichao Lu:

      Make the ssd_feature_extractor_test.py PY3 compatible. The "six.zip" will use "itertools.izip" in Python 2 and "zip" in Python 3.

--
277344551  by Zhichao Lu:

    Internal change.

--
277154953  by Zhichao Lu:

    Conditionally use keras based optimizers so that check-pointing works correctly.
    This change also enables summaries on TPU which were previously not enabled
    due to a bug.

--
277087572  by Zhichao Lu:

    Fix resizing boxes when using keep_aspect_ratio_rezier with padding.

--
275898543  by Zhichao Lu:

    Support label_map_proto as input in label_map_util.

--
275347137  by Zhichao Lu:

    Add force_no_resize flag in eval.proto which replaces
    the resize config with identity resizer. This is useful
    when we want to test at the original image resolution.

--

PiperOrigin-RevId: 280142968

280061731  by Sergio Guadarrama:

    Fix table formatting in mobilenet readme

--
280059345  by Sergio Guadarrama:

    Internal change

PiperOrigin-RevId: 280061731

279978375  by Sergio Guadarrama:

    Pass s=2 to the expanded_conv block so it can apply residual correctly in case of fused convolutions.  (Before it was relying on channel mismatch only)

--
279788358  by Sergio Guadarrama:

    Update README to add mobilenet-edgetpu details

--
279774392  by Sergio Guadarrama:

    Adds MobilenetV3-EdgeTpu definition.

--
278917344  by Sergio Guadarrama:

    Create visualwakewords dataset using slim scripts instead of custom scripts.

--
277940048  by Sergio Guadarrama:

    Internal changes to tf.contrib symbols

--

PiperOrigin-RevId: 279978375

* Update for py3 and some internal changes

* \nInternal refactor\n

PiperOrigin-RevId: 279809827

* clean up