GitLab

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>

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

275538818  by Sergio Guadarrama:

    Support grayscale input images in Slim model training

--
275355841  by Sergio Guadarrama:

    Fixed cases where tf.TensorShape was constructed with float dimensions

    This is a prerequisite for making TensorShape and Dimension more strict
    about the types of their arguments.

--
275131829  by Sergio Guadarrama:

    updates mobilenet/README.md to be github compatible adds V2+ reference to mobilenet_v1.md file and fixes invalid markdown

--

PiperOrigin-RevId: 275538818

* Merged commit includes the following changes:
213899768  by Sergio Guadarrama:

    Fixes #3819.

--
213493831  by Sergio Guadarrama:

    Internal change

212057654  by Sergio Guadarrama:

    Internal change

210747685  by Sergio Guadarrama:

    For FPN, when use_depthwise is set to true, use slightly modified mobilenet v1 config.

--
210128931  by Sergio Guadarrama:

    Allow user-defined current_step in NASNet.

--
209092664  by Sergio Guadarrama:

    Add quantized fine-tuning / training / eval and export to slim image classifier binaries.

--
207651347  by Sergio Guadarrama:

    Update mobilenet v1 docs to include revised tflite models.

--
207165245  by Sergio Guadarrama:

    Internal change

207095064  by Sergio Guadarrama:

    Internal change

PiperOrigin-RevId: 213899768

* Update model_lib.py to fix eval_spec name issue.

2. Flag that allows to prevent imagenet.py  from downloading label_to_names from github and/or dumping into training directory (which might be read-only)
3. Adds some comments about how decay steps are computed, since it computed differently when there are clones vs sync replicas.
4. Updates mobilenet.md to describe the training process using train_image_classifer
5. Add citation for TF-Slim model library.

PiperOrigin-RevId: 191955231

PiperOrigin-RevId: 193254125

PiperOrigin-RevId: 193371562

PiperOrigin-RevId: 194085628

PiperOrigin-RevId: 194857067

PiperOrigin-RevId: 196125653

PiperOrigin-RevId: 196589070

PiperOrigin-RevId: 199522873

PiperOrigin-RevId: 200351305

* Make codes more pythonic.

* Restore the indents

Restore the indents.

* Adding option for one_box_for_all_classes to the box_predictor

PiperOrigin-RevId: 192813444

* Extend to accept different ratios of conv channels.

PiperOrigin-RevId: 192837477

* Remove inaccurate caveat from proto file.

PiperOrigin-RevId: 192850747

* Add option to set dropout for classification net in weight shared box predictor.

PiperOrigin-RevId: 192922089

* fix flakiness in testSSDRandomCropWithMultiClassScores due to randomness.

PiperOrigin-RevId: 193067658

* Post-process now works again in train mode.

PiperOrigin-RevId: 193087707

* Adding support for reading in logits as groundtruth labels and applying an optional temperature (scaling) before softmax in support of distillation.

PiperOrigin-RevId: 193119411

* Add a util function to visualize value histogram as a tf.summary.image.

PiperOrigin-RevId: 193137342

* Do not add batch norm parameters to final conv2d ops that predict boxes encodings and class...

* fix issue 'could not satisfy explicit device'

* remove the line unrelated to fix issue

This patch assigns dequeue node to inputs_device. And nolonger shows
"Ignoring device specification /device:GPU:X for node
'clone_X/fifo_queue_Dequeue'" message.

Variable summaries and the learning rate are added elsewhere in the
code.  A quick search also shows that this function is never called.

The flag description for the momentum flag states that it is `The
momentum for the MomentumOptimizer and RMSPropOptimizer`, however its
not actually used in the RMSPropOptimizer.  Instead, a separate
`rmsprop_momentum` flag was used.  This deletes that flag for
simplicity.  It was not referenced anywhere else in the repo.