1. 01 Feb, 2018 1 commit
    • Zhichao Lu's avatar
      Merged commit includes the following changes: · 7a9934df
      Zhichao Lu authored
      184048729  by Zhichao Lu:
      
          Modify target_assigner so that it creates regression targets taking keypoints into account.
      
      --
      184027183  by Zhichao Lu:
      
          Resnet V1 FPN based feature extractors for SSD meta architecture in Object Detection V2 API.
      
      --
      184004730  by Zhichao Lu:
      
          Expose a lever to override the configured mask_type.
      
      --
      183933113  by Zhichao Lu:
      
          Weight shared convolutional box predictor as described in https://arxiv.org/abs/1708.02002
      
      --
      183929669  by Zhichao Lu:
      
          Expanding box list operations for future data augmentations.
      
      --
      183916792  by Zhichao Lu:
      
          Fix unrecognized assertion function in tests.
      
      --
      183906851  by Zhichao Lu:
      
          - Change ssd meta architecture to use regression weights to compute loss normalizer.
      
      --
      183871003  by Zhichao Lu:
      
          Fix config_util_test wrong dependency.
      
      --
      183782120  by Zhichao Lu:
      
          Add __init__ file to third_party directories.
      
      --
      183779109  by Zhichao Lu:
      
          Setup regular version s...
      7a9934df
  2. 28 Oct, 2017 1 commit
  3. 21 Sep, 2017 1 commit
  4. 18 Jul, 2017 3 commits
    • Derek Chow's avatar
      Enable inference with dynamic batch size in SSD. · 4f14cb62
      Derek Chow authored
      * Creates a new batch_decode method in SSD Meta architecture that can handle
        dynamic batch size.
      * use combined_shapes in _get_feature_maps_spatial_dims method to handle
        dynamic batch image_size.
      * Add dynamic batch size tests to check preprocess, predict and postprocess
        methods in SSD Meta architecture.
      4f14cb62
    • Derek Chow's avatar
      Enable inference with dynamic batch size in Faster RCNN. · 5d5fb7cc
      Derek Chow authored
      * Adds a util function to compute a mix of dynamic and static shapes
        preferring static when available.
      * Uses batch_multiclass_non_max_suppression function in postprocess_rpn
        instead of looping over static batch shape and performing
        multiclass_non_max_suppression.
      * Adds a new helper function _unpad_proposals_and_sample_boxclassifier_batch
        to sample from a batch of tensors possibly containing paddings.
      * Tests batch inference with various configurations of static shape via
        unittests.
      5d5fb7cc
    • Derek Chow's avatar
  5. 15 Jun, 2017 1 commit