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>

- 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....

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

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:
275131829  by Sergio Guadarrama:

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

--
274908068  by Sergio Guadarrama:

    Opensource MobilenetV3 detection models.

--
274697808  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.

--
273577462  by Sergio Guadarrama:

    Fixing `conv_defs['defaults']` override issue.

--
272801298  by Sergio Guadarrama:

    Adds links to trained models for Moblienet V3, adds a version of minimalistic mobilenet-v3 to the definitions.

--
268928503  by Sergio Guadarrama:

    Mobilenet v2 with group normalization.

--
263492735  by Sergio Guadarrama:

    Internal change

260037126  by Sergio Guadarrama:

    Adds an option of using a custom depthwise operation in `expanded_conv`.

--
259997001  by Sergio Guadarrama:

    Explicitly mark Python binaries/tests with python_version = "PY2".

--
252697685  by Sergio Guadarrama:

    Internal change

251918746  by Sergio Guadarrama:

    Internal change

251909704  by Sergio Guadarrama:

    Mobilenet V3 backbone implementation.

--
247510236  by Sergio Guadarrama:

    Internal change

246196802  by Sergio Guadarrama:

    Internal change

246014539  by Sergio Guadarrama:

    Internal change

245891435  by Sergio Guadarrama:

    Internal change

245834925  by Sergio Guadarrama:

    n/a

--

PiperOrigin-RevId: 275131829

* Merged commit includes the following changes:
274959989  by Zhichao Lu:

    Update detection model zoo with MobilenetV3 SSD candidates.

--
274908068  by Zhichao Lu:

    Opensource MobilenetV3 detection models.

--
274695889  by richardmunoz:

    RandomPatchGaussian preprocessing step

    This step can be used during model training to randomly apply gaussian noise to a random image patch. Example addition to an Object Detection API pipeline config:

    train_config {
      ...
      data_augmentation_options {
        random_patch_gaussian {
          random_coef: 0.5
          min_patch_size: 1
          max_patch_size: 250
          min_gaussian_stddev: 0.0
          max_gaussian_stddev: 1.0
        }
      }
      ...
    }

--
274257872  by lzc:

    Internal change.

--
274114689  by Zhichao Lu:

    Pass native_resize flag to other FPN variants.

--
274112308  by lzc:

    Internal change.

--
274090763  by richardmunoz:

    Util function for getting a patch mask on an image for use with the Object Detection API

--
274069806  by Zhichao Lu:

    Adding functions which will help compute predictions and losses for CenterNet.

--
273860828  by lzc:

    Internal change.

--
273380069  by richardmunoz:

    RandomImageDownscaleToTargetPixels preprocessing step

    This step can be used during model training to randomly downscale an image to a random target number of pixels. If the image does not contain more than the target number of pixels, then downscaling is skipped. Example addition to an Object Detection API pipeline config:

    train_config {
      ...
      data_augmentation_options {
        random_downscale_to_target_pixels {
          random_coef: 0.5
          min_target_pixels: 300000
          max_target_pixels: 500000
        }
      }
      ...
    }

--
272987602  by Zhichao Lu:

    Avoid -inf when empty box list is passed.

--
272525836  by Zhichao Lu:

    Cleanup repeated resizing code in meta archs.

--
272458667  by richardmunoz:

    RandomJpegQuality preprocessing step

    This step can be used during model training to randomly encode the image into a jpeg with a random quality level. Example addition to an Object Detection API pipeline config:

    train_config {
      ...
      data_augmentation_options {
        random_jpeg_quality {
          random_coef: 0.5
          min_jpeg_quality: 80
          max_jpeg_quality: 100
        }
      }
      ...
    }

--
271412717  by Zhichao Lu:

    Enables TPU training with the V2 eager + tf.function Object Detection training loops.

--
270744153  by Zhichao Lu:

    Adding the offset and size target assigners for CenterNet.

--
269916081  by Zhichao Lu:

    Include basic installation in Object Detection API tutorial.
    Also:
     - Use TF2.0
     - Use saved_model

--
269376056  by Zhichao Lu:

    Fix to variable loading in RetinaNet w/ custom loops. (makes the code rely on the exact name scopes that are generated a little bit less)

--
269256251  by lzc:

    Add use_partitioned_nms field to config and update post_prossing_builder to honor that flag when building nms function.

--
268865295  by Zhichao Lu:

    Adding functionality for importing and merging back internal state of the metric.

--
268640984  by Zhichao Lu:

    Fix computation of gaussian sigma value to create CenterNet heatmap target.

--
267475576  by Zhichao Lu:

    Fix for exporter trying to export non-existent exponential moving averages.

--
267286768  by Zhichao Lu:

    Update mixed-precision policy.

--
266166879  by Zhichao Lu:

    Internal change

265860884  by Zhichao Lu:

    Apply floor function to center coordinates when creating heatmap for CenterNet target.

--
265702749  by Zhichao Lu:

    Internal change

--
264241949  by ronnyvotel:

    Updating Faster R-CNN 'final_anchors' to be in normalized coordinates.

--
264175192  by lzc:

    Update model_fn to only read hparams if it is not None.

--
264159328  by Zhichao Lu:

    Modify nearest neighbor upsampling to eliminate a multiply operation. For quantized models, the multiply operation gets unnecessarily quantized and reduces accuracy (simple stacking would work in place of the broadcast op which doesn't require quantization). Also removes an unnecessary reshape op.

--
263668306  by Zhichao Lu:

    Add the option to use dynamic map_fn for batch NMS

--
263031163  by Zhichao Lu:

    Mark outside compilation for NMS as optional.

--
263024916  by Zhichao Lu:

    Add an ExperimentalModel meta arch for experimenting with new model types.

--
262655894  by Zhichao Lu:

    Add the center heatmap target assigner for CenterNet

--
262431036  by Zhichao Lu:

    Adding add_eval_dict to allow for evaluation on model_v2

--
262035351  by ronnyvotel:

    Removing any non-Tensor predictions from the third stage of Mask R-CNN.

--
261953416  by Zhichao Lu:

    Internal change.

--
261834966  by Zhichao Lu:

    Fix the NMS OOM issue on TPU by forcing NMS to run outside of TPU.

--
261775941  by Zhichao Lu:

    Make Keras InputLayer compatible with both TF 1.x and TF 2.0.

--
261775633  by Zhichao Lu:

    Visualize additional channels with ground-truth bounding boxes.

--
261768117  by lzc:

    Internal change.

--
261766773  by ronnyvotel:

    Exposing `return_raw_detections_during_predict` in Faster R-CNN Proto.

--
260975089  by ronnyvotel:

    Moving calculation of batched prediction tensor names after all tensors in prediction dictionary are created.

--
259816913  by ronnyvotel:

    Adding raw detection boxes and feature map indices to SSD

--
259791955  by Zhichao Lu:

    Added a flag to control the use partitioned_non_max_suppression.

--
259580475  by Zhichao Lu:

    Tweak quantization-aware training re-writer to support NasFpn model architecture.

--
259579943  by rathodv:

    Add a meta target assigner proto and builders in OD API.

--
259577741  by Zhichao Lu:

    Internal change.

--
259366315  by lzc:

    Internal change.

--
259344310  by ronnyvotel:

    Updating faster rcnn so that raw_detection_boxes from predict() are in normalized coordinates.

--
259338670  by Zhichao Lu:

    Add support for use_native_resize_op to more feature extractors. Use dynamic shapes when static shapes are not available.

--
259083543  by ronnyvotel:

    Updating/fixing documentation.

--
259078937  by rathodv:

    Add prediction fields for tensors returned from detection_model.predict.

--
259044601  by Zhichao Lu:

    Add protocol buffer and builders for temperature scaling calibration.

--
259036770  by lzc:

    Internal changes.

--
259006223  by ronnyvotel:

    Adding detection anchor indices to Faster R-CNN Config. This is useful when one wishes to associate final detections and the anchors (or pre-nms boxes) from which they originated.

--
258872501  by Zhichao Lu:

    Run the training pipeline of ssd + resnet_v1_50 + fpn with a checkpoint.

--
258840686  by ronnyvotel:

    Adding standard outputs to DetectionModel.predict(). This CL only updates Faster R-CNN. Other meta architectures will be updated in future CLs.

--
258672969  by lzc:

    Internal change.

--
258649494  by lzc:

    Internal changes.

--
258630321  by ronnyvotel:

    Fixing documentation in shape_utils.flatten_dimensions().

--
258468145  by Zhichao Lu:

    Add additional output tensors parameter to Postprocess op.

--
258099219  by Zhichao Lu:

    Internal changes

--

PiperOrigin-RevId: 274959989

After Eager was moved to core Tensorflow, this notebook gives the error:
AttributeError: module 'tensorflow.contrib.eager' has no attribute 'Variable'
I just fixed it.

* Updating python API to use CombinedNonMaxSuppresion TF operator

1. Adds a unit test to test post_processing python API
2. Currently sets clip_window to None as the kernel uses the default
   clip_window of [0,0,1,1]
3. Added use_static_shapes to the API. In old API if
   use_static_shapes is true, then it pads/clips outputs to max_total_size, if
specified. If not specified, it pads to num_classes*max_size_per_class.
 If use_static_shapes is false, it always pads/clips to max_total_size.

Update unit test to account for clipped bouding boxes

Changed the name to CombinedNonMaxSuppression based on feedback from Google

Added additional parameters to combinedNMS python function. They are currently
unused and required for networks like FasterRCNN and MaskRCNN

* Delete selected_indices from API

Because it was removed from CombinedNMS recently in the PR.

* Improve doc of function combined_non_max_suppression

* Enable CombinedNonMaxSuppression for first_stage_nms

* fix bug

* Ensure agnostic_nms is not used with combined_nms

Remove redundant arguments from combined_nms

* Fix pylint

* Add checks for unsupported args

* Fix pylint

* Move combined_non_max_suppression to batch_multiclass_non_max_suppression

Also rename combined_nms to use_combined_nms

* Delete combined_nms for first_stage_nms because it does not work

* Revert "Delete combined_nms for first_stage_nms because it does not work"

This reverts commit 2a3cc5145f17cee630a67ddedd20e90c2920fa9f.

* Use nmsed_additional_fields.get to avoid error

* Merge combined_non_max_suppression with main nms function

* Rename combined_nms for first stage nms

* Improve  docs

* Use assertListEqual for numpy arrays

* Fix pylint errors

* End comments with period

* Fix TensorRT test output and add int8 result.

* Fix comments

* Removing footnote declaration as well

* Remove TF-TRT examples and point users to new example repo

* Update urls

* Fix review comments and links

The reference implementation can be found at
https://github.com/tensorflow/minigo

This fork was originally created to experiment with performance upgrades
for MLPerf, but since MLPerf work is focused in the original repo,
this fork's existence only serves to confuse.

Add specification for what dataset link to use on the website.