GitLab

* Put all python dependencies into one line.

This makes it easier to copy, paste & install all dependencies at once. In addition many users have custom setups (virtualenv, conda, .etc). Having it in one line easily allows to grap the dependencies.

* Remove 'sudo' from all pip install commands and adjust troubleshooting section.

* Make max_length and static_batch configurable.

* Fix line length.

* Fix incorrect parameters in building eval input.

* Improve comments for readability.

* Add flag to use custom training loop for keras NCF model.

* Add error check to NCF model for custom training loop + tf1.0.

* Add static batch benchmarks to estimator 

So we can distinguish how much static vs dynamic batch matter.

* change max_length for static_batch tests

* Add flag for max length

* Add a custom training loop for NCF model with TF2.0

* Fix long line in ncf_keras_main.py

* Remove dataset repeat when using custom training loop.

this is not going to help with current tf.data semantics. so removing it.

* Fixes that make transformer run.

* Remove debug print statements.

* Changed the permissions to 644.

* Fix the rest of the permissions.

* enable static batch in all benchmarks

* Restrict dist strat hack to training mode

For now we will do predict/eval without dist strat, so remove that hack in non training cases.

* Use `inputs` instead of `x` as arg name for call

Keras has different behavior based on whether the inputs are called `inputs` or not. Using `inputs` gives expected behaviors.

* Avoid extra map fn on input in dist strat case

* Update how we handle custom metrics

This new approach works with and without dist strat. The previous one didn't work with dist strat. We need to fix that but this is reasonable in meantime (b/133724664).

* Update benchmarks

* typo in metrics code

* Revert metrics change

Didn't actually work in distributed case..

250347237  by A. Unique TensorFlower<gardener@tensorflow.org>:

    Fix linting errors in BERT benchmark test.

--
250326131  by A. Unique TensorFlower<gardener@tensorflow.org>:

    Internal change

250315593  by A. Unique TensorFlower<gardener@tensorflow.org>:

    Internal change

250303528  by haoyuzhang<haoyuzhang@google.com>:

    Add method docstring to fix lint error.

--

PiperOrigin-RevId: 250347237

* Run different numbers of steps on different platforms

* Add new tests for delayed performance measurement

This shuffling should help in getting shuffling each epoch.

The ".mat" files loaded in the dataset are byte files. Python 3.7 requires them to be loaded using "rb".

250009207  by A. Unique TensorFlower<gardener@tensorflow.org>:

    Add feature in BERT to write training metrics to a summary file.

--

PiperOrigin-RevId: 250009207

249896208  by hongkuny<hongkuny@google.com>:

    Adds __init__.py

--

PiperOrigin-RevId: 249896208

Add early stopping logic to ncf keras when desired threshold is met. Also change the default batch size to match the tuned hyperparams

249883771  by hongkuny<hongkuny@google.com>:

    Creates a benchmark dir

--

PiperOrigin-RevId: 249883771

* Moved common keras code to utils.

* Initial 1 gpu benchmark

- Aligned flags with resnet example
- removed code/features that are not super useful
- eval as part of train if bleu source/ref provided
- add exp_per_second hook

* Rename benchmark classes, pass batch-size and log_steps.

* fix docstring

* Predict done with checkpoints inline

- perfzero baseclass

* steps not epochs with smoother training loop.

* do not initialize history outside loop.

* 5000 between eval not 500

* estimator to keras.

* remove epochs var.

* use range not xrange.

* 200K steps for 1 gpu

* fix global step

* Add a graph optional_next Reset benchmark.

* Fix lint error.

* Merged commit includes the following changes:
249776315  by tianlin<tianlin@google.com>:

    Internal change

249763206  by tianlin<tianlin@google.com>:

    For TF 2.0 (related to Beam Search), expand cond dims in tf.where(cond, x, y) to make all parameters broadcastable.

--
249392724  by hongkuny<hongkuny@google.com>:

    Internal change

PiperOrigin-RevId: 249776315

* Merged commit includes the following changes:
249823043  by tianlin<tianlin@google.com>:

    Bring back v2 test for predict and eval.

--

PiperOrigin-RevId: 249823043

* Add a test enabling get_next_as_optional behavior.

* Remove repeated flag.

* Remove trailing space.

* Make the name shorter.

* Fix lint error.

* Refine the benchmark name.

Adding validation every epoch allows us to view the progress during training instead of having to wait until the last eval. Mostly useful for manual runs.

Current batch size 160000 does not converge to the desired HR. So we decrease to 99k which is known to converge. Tested locally and got to 63.5 at epoch 7. Also decreasing number of epochs as I don't see any improvement after epoch 7-8.

249580533  by A. Unique TensorFlower<gardener@tensorflow.org>:

    Internal change

249566870  by A. Unique TensorFlower<gardener@tensorflow.org>:

    Set up BERT benchmark test.

--

PiperOrigin-RevId: 249580533

* Add enable_get_next_as_optional flag.

* Set enable_get_next_as_optional to strategy.

* Add comments to explain the flag.

* Remove trailing whitespace.

* Remove trailing space.

249500988  by hongkuny<hongkuny@google.com>:

    Lints

--

PiperOrigin-RevId: 249500988

* Add big tests.

* fix super

* Add fp16, increase 8xGPU batch-sizes

* Adding the rest of the fp16 tests.

* Big accuracy test batch_perf_gpu

* fix docstrings

* add _run_and_report

* Edited docstrings

247226201  by ronnyvotel:

    Updating the visualization tools to accept unique_ids for color coding.

--
247067830  by Zhichao Lu:

    Add box_encodings_clip_range options for the convolutional box predictor (for TPU compatibility).

--
246888475  by Zhichao Lu:

    Remove unused _update_eval_steps function.

--
246163259  by lzc:

    Add a gather op that can handle ignore indices (which are "-1"s in this case).

--
246084944  by Zhichao Lu:

    Keras based implementation for SSD + MobilenetV2 + FPN.

--
245544227  by rathodv:

    Add batch_get_targets method to target assigner module to gather any groundtruth tensors based on the results of target assigner.

--
245540854  by rathodv:

    Update target assigner to return match tensor instead of a match object.

--
245434441  by Zhichao Lu:

    Add README for tpu_exporters package.

--
245381834  by lzc:

    Internal change.

--
245298983  by Zhichao Lu:

    Add conditional_shape_resizer to config_util

--
245134666  by Zhichao Lu:

    Adds ConditionalShapeResizer to the ImageResizer proto which enables resizing only if input image height or width is is greater or smaller than a certain size. Also enables specification of resize method in resize_to_{max, min}_dimension methods.

--
245093975  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (faster-rcnn)

--
245072421  by Zhichao Lu:

    Adds a new image resizing method "resize_to_max_dimension" which resizes images only if a dimension is greater than the maximum desired value while maintaining aspect ratio.

--
244946998  by lzc:

    Internal Changes.

--
244943693  by Zhichao Lu:

    Add a custom config to mobilenet v2 that makes it more detection friendly.

--
244754158  by derekjchow:

    Internal change.

--
244699875  by Zhichao Lu:

    Add check_range=False to box_list_ops.to_normalized_coordinates when training
    for instance segmentation.  This is consistent with other calls when training
    for object detection.  There could be wrongly annotated boxes in the dataset.

--
244507425  by rathodv:

    Support bfloat16 for ssd models.

--
244399982  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (ssd)

--
244209387  by Zhichao Lu:

    Internal change.

--
243922296  by rathodv:

    Change `raw_detection_scores` to contain softmax/sigmoid scores (not logits) for `raw_ detection_boxes`.

--
243883978  by Zhichao Lu:

    Add a sample fully conv config.

--
243369455  by Zhichao Lu:

    Fix regularization loss gap in Keras and Slim.

--
243292002  by lzc:

    Internal changes.

--
243097958  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (ssd model)

--
243007177  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (ssd model)

--
242776550  by Zhichao Lu:

    Make object detection pre-processing run on GPU.  tf.map_fn() uses
    TensorArrayV3 ops, which have no int32 GPU implementation.  Cast to int64,
    then cast back to int32.

--
242723128  by Zhichao Lu:

    Using sorted dictionaries for additional heads in non_max_suppression to ensure tensor order

--
242495311  by Zhichao Lu:

    Update documentation to reflect new TFLite examples repo location

--
242230527  by Zhichao Lu:

    Fix Dropout bugs for WeightSharedConvolutionalBoxPred.

--
242226573  by Zhichao Lu:

    Create Keras-based WeightSharedConvolutionalBoxPredictor.

--
241806074  by Zhichao Lu:

    Add inference in unit tests of TFX OD template.

--
241641498  by lzc:

    Internal change.

--
241637481  by Zhichao Lu:

    matmul_crop_and_resize(): Switch to dynamic shaping, so that not all dimensions are required to be known.

--
241429980  by Zhichao Lu:

    Internal change

--
241167237  by Zhichao Lu:

    Adds a faster_rcnn_inception_resnet_v2 Keras feature extractor, and updates the model builder to construct it.

--
241088616  by Zhichao Lu:

    Make it compatible with different dtype, e.g. float32, bfloat16, etc.

--
240897364  by lzc:

    Use image_np_expanded in object_detection_tutorial notebook.

--
240890393  by Zhichao Lu:

    Disable multicore inference for OD template as its not yet compatible.

--
240352168  by Zhichao Lu:

    Make SSDResnetV1FpnFeatureExtractor not protected to allow inheritance.

--
240351470  by lzc:

    Internal change.

--
239878928  by Zhichao Lu:

    Defines Keras box predictors for Faster RCNN and RFCN

--
239872103  by Zhichao Lu:

    Delete duplicated inputs in test.

--
239714273  by Zhichao Lu:

    Adding scope variable to all class heads

--
239698643  by Zhichao Lu:

    Create FPN feature extractor for object detection.

--
239696657  by Zhichao Lu:

    Internal Change.

--
239299404  by Zhichao Lu:

    Allows the faster rcnn meta-architecture to support Keras subcomponents

--
238502595  by Zhichao Lu:

    Lay the groundwork for symmetric quantization.

--
238496885  by Zhichao Lu:

    Add flexible_grid_anchor_generator

--
238138727  by lzc:

    Remove dead code.

    _USE_C_SHAPES has been forced True in TensorFlow releases since
    TensorFlow 1.9
    (https://github.com/tensorflow/tensorflow/commit/1d74a69443f741e69f9f52cb6bc2940b4d4ae3b7)

--
238123936  by rathodv:

    Add num_matched_groundtruth summary to target assigner in SSD.

--
238103345  by ronnyvotel:

    Raising error if input file pattern does not match any files.
    Also printing the number of evaluation images for coco metrics.

--
238044081  by Zhichao Lu:

    Fix docstring to state the correct dimensionality of `class_predictions_with_background`.

--
237920279  by Zhichao Lu:

    [XLA] Rework debug flags for dumping HLO.

    The following flags (usually passed via the XLA_FLAGS envvar) are removed:

      xla_dump_computations_to
      xla_dump_executions_to
      xla_dump_ir_to
      xla_dump_optimized_hlo_proto_to
      xla_dump_per_pass_hlo_proto_to
      xla_dump_unoptimized_hlo_proto_to
      xla_generate_hlo_graph
      xla_generate_hlo_text_to
      xla_hlo_dump_as_html
      xla_hlo_graph_path
      xla_log_hlo_text

    The following new flags are added:

      xla_dump_to
      xla_dump_hlo_module_re
      xla_dump_hlo_pass_re
      xla_dump_hlo_as_text
      xla_dump_hlo_as_proto
      xla_dump_hlo_as_dot
      xla_dump_hlo_as_url
      xla_dump_hlo_as_html
      xla_dump_ir
      xla_dump_hlo_snapshots

    The default is not to dump anything at all, but as soon as some dumping flag is
    specified, we enable the following defaults (most of which can be overridden).

     * dump to stdout (overridden by --xla_dump_to)
     * dump HLO modules at the very beginning and end of the optimization pipeline
     * don't dump between any HLO passes (overridden by --xla_dump_hlo_pass_re)
     * dump all HLO modules (overridden by --xla_dump_hlo_module_re)
     * dump in textual format (overridden by
       --xla_dump_hlo_as_{text,proto,dot,url,html}).

    For example, to dump optimized and unoptimized HLO text and protos to /tmp/foo,
    pass

      --xla_dump_to=/tmp/foo --xla_dump_hlo_as_text --xla_dump_hlo_as_proto

    For details on these flags' meanings, see xla.proto.

    The intent of this change is to make dumping both simpler to use and more
    powerful.

    For example:

     * Previously there was no way to dump the HLO module during the pass pipeline
       in HLO text format; the only option was --dump_per_pass_hlo_proto_to, which
       dumped in proto format.

       Now this is --xla_dump_pass_re=.* --xla_dump_hlo_as_text.  (In fact, the
       second flag is not necessary in this case, as dumping as text is the
       default.)

     * Previously there was no way to dump HLO as a graph before and after
       compilation; the only option was --xla_generate_hlo_graph, which would dump
       before/after every pass.

       Now this is --xla_dump_hlo_as_{dot,url,html} (depending on what format you
       want the graph in).

     * Previously, there was no coordination between the filenames written by the
       various flags, so info about one module might be dumped with various
       filename prefixes.  Now the filenames are consistent and all dumps from a
       particular module are next to each other.

    If you only specify some of these flags, we try to figure out what you wanted.
    For example:

     * --xla_dump_to implies --xla_dump_hlo_as_text unless you specify some
       other --xla_dump_as_* flag.

     * --xla_dump_hlo_as_text or --xla_dump_ir implies dumping to stdout unless you
       specify a different --xla_dump_to directory.  You can explicitly dump to
       stdout with --xla_dump_to=-.

    As part of this change, I simplified the debugging code in the HLO passes for
    dumping HLO modules.  Previously, many tests explicitly VLOG'ed the HLO module
    before, after, and sometimes during the pass.  I removed these VLOGs.  If you
    want dumps before/during/after an HLO pass, use --xla_dump_pass_re=<pass_name>.

--
237510043  by lzc:

    Internal Change.

--
237469515  by Zhichao Lu:

    Parameterize model_builder.build in inputs.py.

--
237293511  by rathodv:

    Remove multiclass_scores from tensor_dict in transform_data_fn always.

--
237260333  by ronnyvotel:

    Updating faster_rcnn_meta_arch to define prediction dictionary fields that are batched.

--

PiperOrigin-RevId: 247226201

* Merged commit includes the following changes:
249218656  by tianlin<tianlin@google.com>:

    Deal with imports, fix a typo and make unit tests fast.

--
249198645  by tianlin<tianlin@google.com>:

    Trivial: Remove one empty line before "import tensorflow"

--
249195490  by tianlin<tianlin@google.com>:

    Initialize Transformer TF V2 Model with Keras subclassing implementation. (Compatible with TF V1)

--
249195008  by tianlin<tianlin@google.com>:

    Internal change

249173564  by hongkuny<hongkuny@google.com>:

    Internal change

249079258  by hongkuny<hongkuny@google.com>:

    Internal change

247691534  by haoyuzhang<haoyuzhang@google.com>:

    Internal change

247533725  by haoyuzhang<haoyuzhang@google.com>:

    Internal change

247509295  by haoyuzhang<haoyuzhang@google.com>:

    Internal change

247311355  by wangtz<wangtz@google.com>:

    Internal change

247303127  by wangtz<wangtz@google.com>:

  ...