Internal changes for object detection. #3656
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PiperOrigin-RevId: 188335318
…tes. PiperOrigin-RevId: 188338852
The C API has improved shape inference over the original Python code. This causes some previously-working conds to fail. Switching to smart_cond fixes this. Another effect of the improved shape inference is that one of the failures tested gets caught earlier, so I modified the test to reflect this. PiperOrigin-RevId: 188409792
Without this change, the event files might get corrupted when multiple evaluations are run in parallel. PiperOrigin-RevId: 188502560
Replace with a string field fine_tune_checkpoint_type to train_config to provide extensibility. The fine_tune_checkpoint_type can currently take value of `detection`, `classification`, or others when the restore_map is overwritten. PiperOrigin-RevId: 188518685
PiperOrigin-RevId: 188519969
…rics to be computed in tensorflow using the tf.learn Estimator. PiperOrigin-RevId: 188528485
… compatible. PiperOrigin-RevId: 188550683
…Evaluator`s. PiperOrigin-RevId: 188560474
PiperOrigin-RevId: 188561908
PiperOrigin-RevId: 188799033
PiperOrigin-RevId: 188916897
…ith id zero. PiperOrigin-RevId: 188951089
…min_scale is always less than max_scale. PiperOrigin-RevId: 189026868
…type isn't set. PiperOrigin-RevId: 189052833
…names on tensorboard. PiperOrigin-RevId: 189069837
…del) with batch_size >= 1. PiperOrigin-RevId: 189117178
PiperOrigin-RevId: 189189123
…N) in both training and eval so they can be compared on tensorboard. Log localization and classification losses in evaluation. PiperOrigin-RevId: 189189940
PiperOrigin-RevId: 189229327
PiperOrigin-RevId: 189361039
…tection.data_decoders.tf_example_decoder.LookupTensor. PiperOrigin-RevId: 189388556
PiperOrigin-RevId: 189393190
PiperOrigin-RevId: 189396001
…1039 PiperOrigin-RevId: 189396697
PiperOrigin-RevId: 189393190
PiperOrigin-RevId: 189396001
PiperOrigin-RevId: 189407487
… the same name. Directly adding family suffix to the name gets rid of this problem. 2. Make sure the eval losses have the same name. PiperOrigin-RevId: 189434618
PiperOrigin-RevId: 189437519
…cope and set batchnorm is_training based on the value passed in the constructor. PiperOrigin-RevId: 189460890
PiperOrigin-RevId: 189463882
PiperOrigin-RevId: 189601955
… number of steps and cosine decay it. PiperOrigin-RevId: 189606169
…tectures return the activations (end_points). PiperOrigin-RevId: 189619301
…boxes being in absolute coordinates if scale_to_absolute=True. PiperOrigin-RevId: 189641294
PiperOrigin-RevId: 189654520
derekjchow
approved these changes
Mar 21, 2018
sguada
approved these changes
Mar 22, 2018
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.