Merged commit includes the following changes:

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 sync.

--
183768772  by Zhichao Lu:

    Make test compatible with numpy 1.12 and higher

--
183767893  by Zhichao Lu:

    Make test compatible with numpy 1.12 and higher

--
183719318  by Zhichao Lu:

    Use the new test interface in ssd feature extractor.

--
183714671  by Zhichao Lu:

    Use the new test_case interface for all anchor generators.

--
183708155  by Zhichao Lu:

    Change variable scopes in ConvolutionalBoxPredictor such that previously trained checkpoints are still compatible after the change in BoxPredictor interface

--
183705798  by Zhichao Lu:

    Internal change.

--
183636023  by Zhichao Lu:

    Fixing argument name for np_box_list_ops.concatenate() function.

--
183490404  by Zhichao Lu:

    Make sure code that relies in SSD older code still works.

--
183426762  by Zhichao Lu:

    Internal change

183412315  by Zhichao Lu:

    Internal change

183337814  by Zhichao Lu:

    Internal change

183303933  by Zhichao Lu:

    Internal change

183257349  by Zhichao Lu:

    Internal change

183254447  by Zhichao Lu:

    Internal change

183251200  by Zhichao Lu:

    Internal change

183135002  by Zhichao Lu:

    Internal change

182851500  by Zhichao Lu:

    Internal change

182839607  by Zhichao Lu:

    Internal change

182830719  by Zhichao Lu:

    Internal change

182533923  by Zhichao Lu:

    Internal change

182391090  by Zhichao Lu:

    Internal change

182262339  by Zhichao Lu:

    Internal change

182244645  by Zhichao Lu:

    Internal change

182241613  by Zhichao Lu:

    Internal change

182133027  by Zhichao Lu:

    Internal change

182058807  by Zhichao Lu:

    Internal change

181812028  by Zhichao Lu:

    Internal change

181788857  by Zhichao Lu:

    Internal change

181656761  by Zhichao Lu:

    Internal change

181541125  by Zhichao Lu:

    Internal change

181538702  by Zhichao Lu:

    Internal change

181125385  by Zhichao Lu:

    Internal change

180957758  by Zhichao Lu:

    Internal change

180941434  by Zhichao Lu:

    Internal change

180852569  by Zhichao Lu:

    Internal change

180846001  by Zhichao Lu:

    Internal change

180832145  by Zhichao Lu:

    Internal change

180740495  by Zhichao Lu:

    Internal change

180729150  by Zhichao Lu:

    Internal change

180589008  by Zhichao Lu:

    Internal change

180585408  by Zhichao Lu:

    Internal change

180581039  by Zhichao Lu:

    Internal change

180286388  by Zhichao Lu:

    Internal change

179934081  by Zhichao Lu:

    Internal change

179841242  by Zhichao Lu:

    Internal change

179831694  by Zhichao Lu:

    Internal change

179761005  by Zhichao Lu:

    Internal change

179610632  by Zhichao Lu:

    Internal change

179605363  by Zhichao Lu:

    Internal change

179603774  by Zhichao Lu:

    Internal change

179598614  by Zhichao Lu:

    Internal change

179597809  by Zhichao Lu:

    Internal change

179494630  by Zhichao Lu:

    Internal change

179367492  by Zhichao Lu:

    Internal change

179250050  by Zhichao Lu:

    Internal change

179247385  by Zhichao Lu:

    Internal change

179207897  by Zhichao Lu:

    Internal change

179076230  by Zhichao Lu:

    Internal change

178862066  by Zhichao Lu:

    Internal change

178854216  by Zhichao Lu:

    Internal change

178853109  by Zhichao Lu:

    Internal change

178709753  by Zhichao Lu:

    Internal change

178640707  by Zhichao Lu:

    Internal change

178421534  by Zhichao Lu:

    Internal change

178287174  by Zhichao Lu:

    Internal change

178257399  by Zhichao Lu:

    Internal change

177681867  by Zhichao Lu:

    Internal change

177654820  by Zhichao Lu:

    Internal change

177654052  by Zhichao Lu:

    Internal change

177638787  by Zhichao Lu:

    Internal change

177598305  by Zhichao Lu:

    Internal change

177538488  by Zhichao Lu:

    Internal change

177474197  by Zhichao Lu:

    Internal change

177271928  by Zhichao Lu:

    Internal change

177250285  by Zhichao Lu:

    Internal change

177210762  by Zhichao Lu:

    Internal change

177197135  by Zhichao Lu:

    Internal change

177037781  by Zhichao Lu:

    Internal change

176917394  by Zhichao Lu:

    Internal change

176683171  by Zhichao Lu:

    Internal change

176450793  by Zhichao Lu:

    Internal change

176388133  by Zhichao Lu:

    Internal change

176197721  by Zhichao Lu:

    Internal change

176195315  by Zhichao Lu:

    Internal change

176128748  by Zhichao Lu:

    Internal change

175743440  by Zhichao Lu:

    Use Toggle instead of bool to make the layout optimizer name and usage consistent with other optimizers.

--
175578178  by Zhichao Lu:

    Internal change

175463518  by Zhichao Lu:

    Internal change

175316616  by Zhichao Lu:

    Internal change

175302470  by Zhichao Lu:

    Internal change

175300323  by Zhichao Lu:

    Internal change

175269680  by Zhichao Lu:

    Internal change

175260574  by Zhichao Lu:

    Internal change

175122281  by Zhichao Lu:

    Internal change

175111708  by Zhichao Lu:

    Internal change

175110183  by Zhichao Lu:

    Internal change

174877166  by Zhichao Lu:

    Internal change

174868399  by Zhichao Lu:

    Internal change

174754200  by Zhichao Lu:

    Internal change

174544534  by Zhichao Lu:

    Internal change

174536143  by Zhichao Lu:

    Internal change

174513795  by Zhichao Lu:

    Internal change

174463713  by Zhichao Lu:

    Internal change

174403525  by Zhichao Lu:

    Internal change

174385170  by Zhichao Lu:

    Internal change

174358498  by Zhichao Lu:

    Internal change

174249903  by Zhichao Lu:

    Fix nasnet image classification and object detection by moving the option to turn ON or OFF batch norm training into it's own arg_scope used only by detection

--
174216508  by Zhichao Lu:

    Internal change

174065370  by Zhichao Lu:

    Internal change

174048035  by Zhichao Lu:

    Fix the pointer for downloading the NAS Faster-RCNN model.

--
174042677  by Zhichao Lu:

    Internal change

173964116  by Zhichao Lu:

    Internal change

173790182  by Zhichao Lu:

    Internal change

173779919  by Zhichao Lu:

    Internal change

173753775  by Zhichao Lu:

    Internal change

173753160  by Zhichao Lu:

    Internal change

173737519  by Zhichao Lu:

    Internal change

173696066  by Zhichao Lu:

    Internal change

173611554  by Zhichao Lu:

    Internal change

173475124  by Zhichao Lu:

    Internal change

173412497  by Zhichao Lu:

    Internal change

173404010  by Zhichao Lu:

    Internal change

173375014  by Zhichao Lu:

    Internal change

173345107  by Zhichao Lu:

    Internal change

173298413  by Zhichao Lu:

    Internal change

173289754  by Zhichao Lu:

    Internal change

173275544  by Zhichao Lu:

    Internal change

173273275  by Zhichao Lu:

    Internal change

173271885  by Zhichao Lu:

    Internal change

173264856  by Zhichao Lu:

    Internal change

173263791  by Zhichao Lu:

    Internal change

173261215  by Zhichao Lu:

    Internal change

173175740  by Zhichao Lu:

    Internal change

173010193  by Zhichao Lu:

    Internal change

172815204  by Zhichao Lu:

    Allow for label maps in tf.Example decoding.

--
172696028  by Zhichao Lu:

    Internal change

172509113  by Zhichao Lu:

    Allow for label maps in tf.Example decoding.

--
172475999  by Zhichao Lu:

    Internal change

172166621  by Zhichao Lu:

    Internal change

172151758  by Zhichao Lu:

    Minor updates to some README files.

    As a result of these friendly issues:
    https://github.com/tensorflow/models/issues/2530
    https://github.com/tensorflow/models/issues/2534

--
172147420  by Zhichao Lu:

    Fix illegal summary name and move from slim's get_or_create_global_step deprecated use of tf.contrib.framework* to tf.train*.

--
172111377  by Zhichao Lu:

    Internal change

172004247  by Zhichao Lu:

    Internal change

171996881  by Zhichao Lu:

    Internal change

171835204  by Zhichao Lu:

    Internal change

171826090  by Zhichao Lu:

    Internal change

171784016  by Zhichao Lu:

    Internal change

171699876  by Zhichao Lu:

    Internal change

171053425  by Zhichao Lu:

    Internal change

170905734  by Zhichao Lu:

    Internal change

170889179  by Zhichao Lu:

    Internal change

170734389  by Zhichao Lu:

    Internal change

170705852  by Zhichao Lu:

    Internal change

170401574  by Zhichao Lu:

    Internal change

170352571  by Zhichao Lu:

    Internal change

170215443  by Zhichao Lu:

    Internal change

170184288  by Zhichao Lu:

    Internal change

169936898  by Zhichao Lu:

    Internal change

169763373  by Zhichao Lu:

    Fix broken GitHub links in tensorflow and tensorflow_models resulting from The Great Models Move (a.k.a. the research subfolder)

--
169744825  by Zhichao Lu:

    Internal change

169638135  by Zhichao Lu:

    Internal change

169561814  by Zhichao Lu:

    Internal change

169444091  by Zhichao Lu:

    Internal change

169292330  by Zhichao Lu:

    Internal change

169145185  by Zhichao Lu:

    Internal change

168906035  by Zhichao Lu:

    Internal change

168790411  by Zhichao Lu:

    Internal change

168708911  by Zhichao Lu:

    Internal change

168611969  by Zhichao Lu:

    Internal change

168535975  by Zhichao Lu:

    Internal change

168381815  by Zhichao Lu:

    Internal change

168244740  by Zhichao Lu:

    Internal change

168240024  by Zhichao Lu:

    Internal change

168168016  by Zhichao Lu:

    Internal change

168071571  by Zhichao Lu:

    Move display strings to below the bounding box if they would otherwise be outside the image.

--
168067771  by Zhichao Lu:

    Internal change

167970950  by Zhichao Lu:

    Internal change

167884533  by Zhichao Lu:

    Internal change

167626173  by Zhichao Lu:

    Internal change

167277422  by Zhichao Lu:

    Internal change

167249393  by Zhichao Lu:

    Internal change

167248954  by Zhichao Lu:

    Internal change

167189395  by Zhichao Lu:

    Internal change

167107797  by Zhichao Lu:

    Internal change

167061250  by Zhichao Lu:

    Internal change

166871147  by Zhichao Lu:

    Internal change

166867617  by Zhichao Lu:

    Internal change

166862112  by Zhichao Lu:

    Internal change

166715648  by Zhichao Lu:

    Internal change

166635615  by Zhichao Lu:

    Internal change

166383182  by Zhichao Lu:

    Internal change

166371326  by Zhichao Lu:

    Internal change

166254711  by Zhichao Lu:

    Internal change

166106294  by Zhichao Lu:

    Internal change

166081204  by Zhichao Lu:

    Internal change

165972262  by Zhichao Lu:

    Internal change

165816702  by Zhichao Lu:

    Internal change

165764471  by Zhichao Lu:

    Internal change

165724134  by Zhichao Lu:

    Internal change

165655829  by Zhichao Lu:

    Internal change

165587904  by Zhichao Lu:

    Internal change

165534540  by Zhichao Lu:

    Internal change

165177692  by Zhichao Lu:

    Internal change

165091822  by Zhichao Lu:

    Internal change

165019730  by Zhichao Lu:

    Internal change

165002942  by Zhichao Lu:

    Internal change

164897728  by Zhichao Lu:

    Internal change

164782618  by Zhichao Lu:

    Internal change

164710379  by Zhichao Lu:

    Internal change

164639237  by Zhichao Lu:

    Internal change

164069251  by Zhichao Lu:

    Internal change

164058169  by Zhichao Lu:

    Internal change

163913796  by Zhichao Lu:

    Internal change

163756696  by Zhichao Lu:

    Internal change

163524665  by Zhichao Lu:

    Internal change

163393399  by Zhichao Lu:

    Internal change

163385733  by Zhichao Lu:

    Internal change

162525065  by Zhichao Lu:

    Internal change

162376984  by Zhichao Lu:

    Internal change

162026661  by Zhichao Lu:

    Internal change

161956004  by Zhichao Lu:

    Internal change

161817520  by Zhichao Lu:

    Internal change

161718688  by Zhichao Lu:

    Internal change

161624398  by Zhichao Lu:

    Internal change

161575120  by Zhichao Lu:

    Internal change

161483997  by Zhichao Lu:

    Internal change

161462189  by Zhichao Lu:

    Internal change

161452968  by Zhichao Lu:

    Internal change

161443992  by Zhichao Lu:

    Internal change

161408607  by Zhichao Lu:

    Internal change

161262084  by Zhichao Lu:

    Internal change

161214023  by Zhichao Lu:

    Internal change

161025667  by Zhichao Lu:

    Internal change

160982216  by Zhichao Lu:

    Internal change

160666760  by Zhichao Lu:

    Internal change

160570489  by Zhichao Lu:

    Internal change

160553112  by Zhichao Lu:

    Internal change

160458261  by Zhichao Lu:

    Internal change

160349302  by Zhichao Lu:

    Internal change

160296092  by Zhichao Lu:

    Internal change

160287348  by Zhichao Lu:

    Internal change

160199279  by Zhichao Lu:

    Internal change

160160156  by Zhichao Lu:

    Internal change

160151954  by Zhichao Lu:

    Internal change

160005404  by Zhichao Lu:

    Internal change

159983265  by Zhichao Lu:

    Internal change

159819896  by Zhichao Lu:

    Internal change

159749419  by Zhichao Lu:

    Internal change

159596448  by Zhichao Lu:

    Internal change

159587801  by Zhichao Lu:

    Internal change

159587342  by Zhichao Lu:

    Internal change

159476256  by Zhichao Lu:

    Internal change

159463992  by Zhichao Lu:

    Internal change

159455585  by Zhichao Lu:

    Internal change

159270798  by Zhichao Lu:

    Internal change

159256633  by Zhichao Lu:

    Internal change

159141989  by Zhichao Lu:

    Internal change

159079098  by Zhichao Lu:

    Internal change

159078559  by Zhichao Lu:

    Internal change

159077055  by Zhichao Lu:

    Internal change

159072046  by Zhichao Lu:

    Internal change

159071092  by Zhichao Lu:

    Internal change

159069262  by Zhichao Lu:

    Internal change

159037430  by Zhichao Lu:

    Internal change

159035747  by Zhichao Lu:

    Internal change

159023868  by Zhichao Lu:

    Internal change

158939092  by Zhichao Lu:

    Internal change

158912561  by Zhichao Lu:

    Internal change

158903825  by Zhichao Lu:

    Internal change

158894348  by Zhichao Lu:

    Internal change

158884934  by Zhichao Lu:

    Internal change

158878010  by Zhichao Lu:

    Internal change

158874620  by Zhichao Lu:

    Internal change

158869501  by Zhichao Lu:

    Internal change

158842623  by Zhichao Lu:

    Internal change

158801298  by Zhichao Lu:

    Internal change

158775487  by Zhichao Lu:

    Internal change

158773668  by Zhichao Lu:

    Internal change

158771394  by Zhichao Lu:

    Internal change

158668928  by Zhichao Lu:

    Internal change

158596865  by Zhichao Lu:

    Internal change

158587317  by Zhichao Lu:

    Internal change

158586348  by Zhichao Lu:

    Internal change

158585707  by Zhichao Lu:

    Internal change

158577134  by Zhichao Lu:

    Internal change

158459749  by Zhichao Lu:

    Internal change

158459678  by Zhichao Lu:

    Internal change

158328972  by Zhichao Lu:

    Internal change

158324255  by Zhichao Lu:

    Internal change

158319576  by Zhichao Lu:

    Internal change

158290802  by Zhichao Lu:

    Internal change

158273041  by Zhichao Lu:

    Internal change

158240477  by Zhichao Lu:

    Internal change

158204316  by Zhichao Lu:

    Internal change

158154161  by Zhichao Lu:

    Internal change

158077203  by Zhichao Lu:

    Internal change

158041397  by Zhichao Lu:

    Internal change

158029233  by Zhichao Lu:

    Internal change

157976306  by Zhichao Lu:

    Internal change

157966896  by Zhichao Lu:

    Internal change

157945642  by Zhichao Lu:

    Internal change

157943135  by Zhichao Lu:

    Internal change

157942158  by Zhichao Lu:

    Internal change

157897866  by Zhichao Lu:

    Internal change

157866667  by Zhichao Lu:

    Internal change

157845915  by Zhichao Lu:

    Internal change

157842592  by Zhichao Lu:

    Internal change

157832761  by Zhichao Lu:

    Internal change

157824451  by Zhichao Lu:

    Internal change

157816531  by Zhichao Lu:

    Internal change

157782130  by Zhichao Lu:

    Internal change

157733752  by Zhichao Lu:

    Internal change

157654577  by Zhichao Lu:

    Internal change

157639285  by Zhichao Lu:

    Internal change

157530694  by Zhichao Lu:

    Internal change

157518469  by Zhichao Lu:

    Internal change

157514626  by Zhichao Lu:

    Internal change

157481413  by Zhichao Lu:

    Internal change

157267863  by Zhichao Lu:

    Internal change

157263616  by Zhichao Lu:

    Internal change

157234554  by Zhichao Lu:

    Internal change

157174595  by Zhichao Lu:

    Internal change

157169681  by Zhichao Lu:

    Internal change

157156425  by Zhichao Lu:

    Internal change

157024436  by Zhichao Lu:

    Internal change

157016195  by Zhichao Lu:

    Internal change

156941658  by Zhichao Lu:

    Internal change

156880859  by Zhichao Lu:

    Internal change

156790636  by Zhichao Lu:

    Internal change

156565969  by Zhichao Lu:

    Internal change

156522345  by Zhichao Lu:

    Internal change

156518570  by Zhichao Lu:

    Internal change

156509878  by Zhichao Lu:

    Internal change

156509134  by Zhichao Lu:

    Internal change

156472497  by Zhichao Lu:

    Internal change

156471429  by Zhichao Lu:

    Internal change

156470865  by Zhichao Lu:

    Internal change

156461563  by Zhichao Lu:

    Internal change

156437521  by Zhichao Lu:

    Internal change

156334994  by Zhichao Lu:

    Internal change

156319604  by Zhichao Lu:

    Internal change

156234305  by Zhichao Lu:

    Internal change

156226207  by Zhichao Lu:

    Internal change

156215347  by Zhichao Lu:

    Internal change

156127227  by Zhichao Lu:

    Internal change

156120405  by Zhichao Lu:

    Internal change

156113752  by Zhichao Lu:

    Internal change

156098936  by Zhichao Lu:

    Internal change

155924066  by Zhichao Lu:

    Internal change

155883241  by Zhichao Lu:

    Internal change

155806887  by Zhichao Lu:

    Internal change

155641849  by Zhichao Lu:

    Internal change

155593034  by Zhichao Lu:

    Internal change

155570702  by Zhichao Lu:

    Internal change

155515306  by Zhichao Lu:

    Internal change

155514787  by Zhichao Lu:

    Internal change

155445237  by Zhichao Lu:

    Internal change

155438672  by Zhichao Lu:

    Internal change

155264448  by Zhichao Lu:

    Internal change

155222148  by Zhichao Lu:

    Internal change

155106590  by Zhichao Lu:

    Internal change

155090562  by Zhichao Lu:

    Internal change

154973775  by Zhichao Lu:

    Internal change

154972880  by Zhichao Lu:

    Internal change

154871596  by Zhichao Lu:

    Internal change

154835007  by Zhichao Lu:

    Internal change

154788175  by Zhichao Lu:

    Internal change

154731169  by Zhichao Lu:

    Internal change

154721261  by Zhichao Lu:

    Internal change

154594626  by Zhichao Lu:

    Internal change

154588305  by Zhichao Lu:

    Internal change

154578994  by Zhichao Lu:

    Internal change

154571515  by Zhichao Lu:

    Internal change

154552873  by Zhichao Lu:

    Internal change

154549672  by Zhichao Lu:

    Internal change

154463631  by Zhichao Lu:

    Internal change

154437690  by Zhichao Lu:

    Internal change

154412359  by Zhichao Lu:

    Internal change

154374026  by Zhichao Lu:

    Internal change

154361648  by Zhichao Lu:

    Internal change

154310164  by Zhichao Lu:

    Internal change

154220862  by Zhichao Lu:

    Internal change

154187281  by Zhichao Lu:

    Internal change

154186651  by Zhichao Lu:

    Internal change

154119783  by Zhichao Lu:

    Internal change

154114285  by Zhichao Lu:

    Internal change

154095717  by Zhichao Lu:

    Internal change

154057972  by Zhichao Lu:

    Internal change

154055285  by Zhichao Lu:

    Internal change

153659288  by Zhichao Lu:

    Internal change

153637797  by Zhichao Lu:

    Internal change

153561771  by Zhichao Lu:

    Internal change

153540765  by Zhichao Lu:

    Internal change

153496128  by Zhichao Lu:

    Internal change

153473323  by Zhichao Lu:

    Internal change

153368812  by Zhichao Lu:

    Internal change

153367292  by Zhichao Lu:

    Internal change

153201890  by Zhichao Lu:

    Internal change

153074177  by Zhichao Lu:

    Internal change

152980017  by Zhichao Lu:

    Internal change

152978434  by Zhichao Lu:

    Internal change

152951821  by Zhichao Lu:

    Internal change

152904076  by Zhichao Lu:

    Internal change

152883703  by Zhichao Lu:

    Internal change

152869747  by Zhichao Lu:

    Internal change

152827463  by Zhichao Lu:

    Internal change

152756886  by Zhichao Lu:

    Internal change

152752840  by Zhichao Lu:

    Internal change

152736347  by Zhichao Lu:

    Internal change

152728184  by Zhichao Lu:

    Internal change

152720120  by Zhichao Lu:

    Internal change

152710964  by Zhichao Lu:

    Internal change

152706735  by Zhichao Lu:

    Internal change

152681133  by Zhichao Lu:

    Internal change

152517758  by Zhichao Lu:

    Internal change

152516381  by Zhichao Lu:

    Internal change

152511258  by Zhichao Lu:

    Internal change

152319164  by Zhichao Lu:

    Internal change

152316404  by Zhichao Lu:

    Internal change

152309261  by Zhichao Lu:

    Internal change

152308007  by Zhichao Lu:

    Internal change

152296551  by Zhichao Lu:

    Internal change

152188069  by Zhichao Lu:

    Internal change

152158644  by Zhichao Lu:

    Internal change

152153578  by Zhichao Lu:

    Internal change

152152285  by Zhichao Lu:

    Internal change

152055035  by Zhichao Lu:

    Internal change

152036778  by Zhichao Lu:

    Internal change

152020728  by Zhichao Lu:

    Internal change

152014842  by Zhichao Lu:

    Internal change

151848225  by Zhichao Lu:

    Internal change

151741308  by Zhichao Lu:

    Internal change

151740499  by Zhichao Lu:

    Internal change

151736189  by Zhichao Lu:

    Internal change

151612892  by Zhichao Lu:

    Internal change

151599502  by Zhichao Lu:

    Internal change

151538547  by Zhichao Lu:

    Internal change

151496530  by Zhichao Lu:

    Internal change

151476070  by Zhichao Lu:

    Internal change

151448662  by Zhichao Lu:

    Internal change

151411627  by Zhichao Lu:

    Internal change

151397737  by Zhichao Lu:

    Internal change

151169523  by Zhichao Lu:

    Internal change

151148956  by Zhichao Lu:

    Internal change

150944227  by Zhichao Lu:

    Internal change

150276683  by Zhichao Lu:

    Internal change

149986687  by Zhichao Lu:

    Internal change

149218749  by Zhichao Lu:

    Internal change

PiperOrigin-RevId: 184048729

research/object_detection/models/ssd_mobilenet_v1_feature_extractor.py

@@ -20,6 +20,7 @@ import tensorflow as tf
 from object_detection.meta_architectures import ssd_meta_arch
 from object_detection.models import feature_map_generators
 from object_detection.utils import ops
+from object_detection.utils import shape_utils
 from nets import mobilenet_v1
 
 slim = tf.contrib.slim
@@ -35,7 +36,8 @@ class SSDMobileNetV1FeatureExtractor(ssd_meta_arch.SSDFeatureExtractor):
                pad_to_multiple,
                conv_hyperparams,
                batch_norm_trainable=True,
-               reuse_weights=None):
+               reuse_weights=None,
+               use_explicit_padding=False):
     """MobileNetV1 Feature Extractor for SSD Models.
 
     Args:
@@ -50,10 +52,13 @@ class SSDMobileNetV1FeatureExtractor(ssd_meta_arch.SSDFeatureExtractor):
         (e.g. 1), it is desirable to disable batch norm update and use
         pretrained batch norm params.
       reuse_weights: Whether to reuse variables. Default is None.
+      use_explicit_padding: Whether to use explicit padding when extracting
+        features. Default is False.
     """
     super(SSDMobileNetV1FeatureExtractor, self).__init__(
         is_training, depth_multiplier, min_depth, pad_to_multiple,
-        conv_hyperparams, batch_norm_trainable, reuse_weights)
+        conv_hyperparams, batch_norm_trainable, reuse_weights,
+        use_explicit_padding)
 
   def preprocess(self, resized_inputs):
     """SSD preprocessing.
@@ -81,34 +86,32 @@ class SSDMobileNetV1FeatureExtractor(ssd_meta_arch.SSDFeatureExtractor):
       feature_maps: a list of tensors where the ith tensor has shape
         [batch, height_i, width_i, depth_i]
     """
-    preprocessed_inputs.get_shape().assert_has_rank(4)
-    shape_assert = tf.Assert(
-        tf.logical_and(tf.greater_equal(tf.shape(preprocessed_inputs)[1], 33),
-                       tf.greater_equal(tf.shape(preprocessed_inputs)[2], 33)),
-        ['image size must at least be 33 in both height and width.'])
+    preprocessed_inputs = shape_utils.check_min_image_dim(
+        33, preprocessed_inputs)
 
     feature_map_layout = {
         'from_layer': ['Conv2d_11_pointwise', 'Conv2d_13_pointwise', '', '',
                        '', ''],
         'layer_depth': [-1, -1, 512, 256, 256, 128],
+        'use_explicit_padding': self._use_explicit_padding,
     }
 
-    with tf.control_dependencies([shape_assert]):
-      with slim.arg_scope(self._conv_hyperparams):
-        with slim.arg_scope([slim.batch_norm], fused=False):
-          with tf.variable_scope('MobilenetV1',
-                                 reuse=self._reuse_weights) as scope:
-            _, image_features = mobilenet_v1.mobilenet_v1_base(
-                ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
-                final_endpoint='Conv2d_13_pointwise',
-                min_depth=self._min_depth,
-                depth_multiplier=self._depth_multiplier,
-                scope=scope)
-            feature_maps = feature_map_generators.multi_resolution_feature_maps(
-                feature_map_layout=feature_map_layout,
-                depth_multiplier=self._depth_multiplier,
-                min_depth=self._min_depth,
-                insert_1x1_conv=True,
-                image_features=image_features)
+    with slim.arg_scope(self._conv_hyperparams):
+      # TODO: Enable fused batch norm once quantization supports it.
+      with slim.arg_scope([slim.batch_norm], fused=False):
+        with tf.variable_scope('MobilenetV1',
+                               reuse=self._reuse_weights) as scope:
+          _, image_features = mobilenet_v1.mobilenet_v1_base(
+              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
+              final_endpoint='Conv2d_13_pointwise',
+              min_depth=self._min_depth,
+              depth_multiplier=self._depth_multiplier,
+              scope=scope)
+          feature_maps = feature_map_generators.multi_resolution_feature_maps(
+              feature_map_layout=feature_map_layout,
+              depth_multiplier=self._depth_multiplier,
+              min_depth=self._min_depth,
+              insert_1x1_conv=True,
+              image_features=image_features)
 
     return feature_maps.values()

research/object_detection/models/ssd_mobilenet_v1_feature_extractor_test.py

@@ -24,7 +24,7 @@ slim = tf.contrib.slim
 
 
 class SsdMobilenetV1FeatureExtractorTest(
-    ssd_feature_extractor_test.SsdFeatureExtractorTestBase, tf.test.TestCase):
+    ssd_feature_extractor_test.SsdFeatureExtractorTestBase):
 
   def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                 is_training=True, batch_norm_trainable=True):
@@ -52,11 +52,11 @@ class SsdMobilenetV1FeatureExtractorTest(
     image_width = 128
     depth_multiplier = 1.0
     pad_to_multiple = 1
-    expected_feature_map_shape = [(4, 8, 8, 512), (4, 4, 4, 1024),
-                                  (4, 2, 2, 512), (4, 1, 1, 256),
-                                  (4, 1, 1, 256), (4, 1, 1, 128)]
+    expected_feature_map_shape = [(2, 8, 8, 512), (2, 4, 4, 1024),
+                                  (2, 2, 2, 512), (2, 1, 1, 256),
+                                  (2, 1, 1, 256), (2, 1, 1, 128)]
     self.check_extract_features_returns_correct_shape(
-        image_height, image_width, depth_multiplier, pad_to_multiple,
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
         expected_feature_map_shape)
 
   def test_extract_features_returns_correct_shapes_299(self):
@@ -64,11 +64,23 @@ class SsdMobilenetV1FeatureExtractorTest(
     image_width = 299
     depth_multiplier = 1.0
     pad_to_multiple = 1
-    expected_feature_map_shape = [(4, 19, 19, 512), (4, 10, 10, 1024),
-                                  (4, 5, 5, 512), (4, 3, 3, 256),
-                                  (4, 2, 2, 256), (4, 1, 1, 128)]
+    expected_feature_map_shape = [(2, 19, 19, 512), (2, 10, 10, 1024),
+                                  (2, 5, 5, 512), (2, 3, 3, 256),
+                                  (2, 2, 2, 256), (2, 1, 1, 128)]
     self.check_extract_features_returns_correct_shape(
-        image_height, image_width, depth_multiplier, pad_to_multiple,
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
+        expected_feature_map_shape)
+
+  def test_extract_features_with_dynamic_image_shape(self):
+    image_height = 128
+    image_width = 128
+    depth_multiplier = 1.0
+    pad_to_multiple = 1
+    expected_feature_map_shape = [(2, 8, 8, 512), (2, 4, 4, 1024),
+                                  (2, 2, 2, 512), (2, 1, 1, 256),
+                                  (2, 1, 1, 256), (2, 1, 1, 128)]
+    self.check_extract_features_returns_correct_shapes_with_dynamic_inputs(
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
         expected_feature_map_shape)
 
   def test_extract_features_returns_correct_shapes_enforcing_min_depth(self):
@@ -76,11 +88,11 @@ class SsdMobilenetV1FeatureExtractorTest(
     image_width = 299
     depth_multiplier = 0.5**12
     pad_to_multiple = 1
-    expected_feature_map_shape = [(4, 19, 19, 32), (4, 10, 10, 32),
-                                  (4, 5, 5, 32), (4, 3, 3, 32),
-                                  (4, 2, 2, 32), (4, 1, 1, 32)]
+    expected_feature_map_shape = [(2, 19, 19, 32), (2, 10, 10, 32),
+                                  (2, 5, 5, 32), (2, 3, 3, 32),
+                                  (2, 2, 2, 32), (2, 1, 1, 32)]
     self.check_extract_features_returns_correct_shape(
-        image_height, image_width, depth_multiplier, pad_to_multiple,
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
         expected_feature_map_shape)
 
   def test_extract_features_returns_correct_shapes_with_pad_to_multiple(self):
@@ -88,11 +100,11 @@ class SsdMobilenetV1FeatureExtractorTest(
     image_width = 299
     depth_multiplier = 1.0
     pad_to_multiple = 32
-    expected_feature_map_shape = [(4, 20, 20, 512), (4, 10, 10, 1024),
-                                  (4, 5, 5, 512), (4, 3, 3, 256),
-                                  (4, 2, 2, 256), (4, 1, 1, 128)]
+    expected_feature_map_shape = [(2, 20, 20, 512), (2, 10, 10, 1024),
+                                  (2, 5, 5, 512), (2, 3, 3, 256),
+                                  (2, 2, 2, 256), (2, 1, 1, 128)]
     self.check_extract_features_returns_correct_shape(
-        image_height, image_width, depth_multiplier, pad_to_multiple,
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
         expected_feature_map_shape)
 
   def test_extract_features_raises_error_with_invalid_image_size(self):
@@ -108,7 +120,7 @@ class SsdMobilenetV1FeatureExtractorTest(
     image_width = 128
     depth_multiplier = 1
     pad_to_multiple = 1
-    test_image = np.random.rand(4, image_height, image_width, 3)
+    test_image = np.random.rand(2, image_height, image_width, 3)
     feature_extractor = self._create_feature_extractor(depth_multiplier,
                                                        pad_to_multiple)
     preprocessed_image = feature_extractor.preprocess(test_image)

research/object_detection/models/ssd_resnet_v1_fpn_feature_extractor.py

+"""SSD Feature Pyramid Network (FPN) feature extractors based on Resnet v1.
+
+See https://arxiv.org/abs/1708.02002 for details.
+"""
+
+import tensorflow as tf
+
+from object_detection.meta_architectures import ssd_meta_arch
+from object_detection.models import feature_map_generators
+from object_detection.utils import ops
+from object_detection.utils import shape_utils
+from nets import resnet_v1
+
+slim = tf.contrib.slim
+
+
+class _SSDResnetV1FpnFeatureExtractor(ssd_meta_arch.SSDFeatureExtractor):
+  """SSD FPN feature extractor based on Resnet v1 architecture."""
+
+  def __init__(self,
+               is_training,
+               depth_multiplier,
+               min_depth,
+               pad_to_multiple,
+               conv_hyperparams,
+               resnet_base_fn,
+               resnet_scope_name,
+               batch_norm_trainable=True,
+               reuse_weights=None,
+               use_explicit_padding=False):
+    """SSD FPN feature extractor based on Resnet v1 architecture.
+
+    Args:
+      is_training: whether the network is in training mode.
+      depth_multiplier: float depth multiplier for feature extractor.
+        UNUSED currently.
+      min_depth: minimum feature extractor depth. UNUSED Currently.
+      pad_to_multiple: the nearest multiple to zero pad the input height and
+        width dimensions to.
+      conv_hyperparams: tf slim arg_scope for conv2d and separable_conv2d ops.
+      resnet_base_fn: base resnet network to use.
+      resnet_scope_name: scope name to construct resnet
+      batch_norm_trainable: Whether to update batch norm parameters during
+        training or not. When training with a small batch size
+        (e.g. 1), it is desirable to disable batch norm update and use
+        pretrained batch norm params.
+      reuse_weights: Whether to reuse variables. Default is None.
+      use_explicit_padding: Whether to use explicit padding when extracting
+        features. Default is False. UNUSED currently.
+
+    Raises:
+      ValueError: On supplying invalid arguments for unused arguments.
+    """
+    super(_SSDResnetV1FpnFeatureExtractor, self).__init__(
+        is_training, depth_multiplier, min_depth, pad_to_multiple,
+        conv_hyperparams, batch_norm_trainable, reuse_weights,
+        use_explicit_padding)
+    if self._depth_multiplier != 1.0:
+      raise ValueError('Only depth 1.0 is supported, found: {}'.
+                       format(self._depth_multiplier))
+    if self._use_explicit_padding is True:
+      raise ValueError('Explicit padding is not a valid option.')
+    self._resnet_base_fn = resnet_base_fn
+    self._resnet_scope_name = resnet_scope_name
+
+  def preprocess(self, resized_inputs):
+    """SSD preprocessing.
+
+    VGG style channel mean subtraction as described here:
+    https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-mdnge.
+
+    Args:
+      resized_inputs: a [batch, height, width, channels] float tensor
+        representing a batch of images.
+
+    Returns:
+      preprocessed_inputs: a [batch, height, width, channels] float tensor
+        representing a batch of images.
+    """
+    channel_means = [123.68, 116.779, 103.939]
+    return resized_inputs - [[channel_means]]
+
+  def _filter_features(self, image_features):
+    # TODO: Change resnet endpoint to strip scope prefixes instead
+    # of munging the scope here.
+    filtered_image_features = dict({})
+    for key, feature in image_features.items():
+      feature_name = key.split('/')[-1]
+      if feature_name in ['block2', 'block3', 'block4']:
+        filtered_image_features[feature_name] = feature
+    return filtered_image_features
+
+  def extract_features(self, preprocessed_inputs):
+    """Extract features from preprocessed inputs.
+
+    Args:
+      preprocessed_inputs: a [batch, height, width, channels] float tensor
+        representing a batch of images.
+
+    Returns:
+      feature_maps: a list of tensors where the ith tensor has shape
+        [batch, height_i, width_i, depth_i]
+
+    Raises:
+      ValueError: depth multiplier is not supported.
+    """
+    if self._depth_multiplier != 1.0:
+      raise ValueError('Depth multiplier not supported.')
+
+    preprocessed_inputs = shape_utils.check_min_image_dim(
+        129, preprocessed_inputs)
+
+    with tf.variable_scope(
+        self._resnet_scope_name, reuse=self._reuse_weights) as scope:
+      with slim.arg_scope(resnet_v1.resnet_arg_scope()):
+        _, image_features = self._resnet_base_fn(
+            inputs=ops.pad_to_multiple(preprocessed_inputs,
+                                       self._pad_to_multiple),
+            num_classes=None,
+            is_training=self._is_training and self._batch_norm_trainable,
+            global_pool=False,
+            output_stride=None,
+            store_non_strided_activations=True,
+            scope=scope)
+      image_features = self._filter_features(image_features)
+      last_feature_map = image_features['block4']
+      with slim.arg_scope(self._conv_hyperparams):
+        for i in range(5, 7):
+          last_feature_map = slim.conv2d(
+              last_feature_map,
+              num_outputs=256,
+              kernel_size=[3, 3],
+              stride=2,
+              padding='SAME',
+              scope='block{}'.format(i))
+          image_features['bottomup_{}'.format(i)] = last_feature_map
+        feature_maps = feature_map_generators.fpn_top_down_feature_maps(
+            [
+                image_features[key] for key in
+                ['block2', 'block3', 'block4', 'bottomup_5', 'bottomup_6']
+            ],
+            depth=256,
+            scope='top_down_features')
+    return feature_maps.values()
+
+
+class SSDResnet50V1FpnFeatureExtractor(_SSDResnetV1FpnFeatureExtractor):
+
+  def __init__(self,
+               is_training,
+               depth_multiplier,
+               min_depth,
+               pad_to_multiple,
+               conv_hyperparams,
+               batch_norm_trainable=True,
+               reuse_weights=None,
+               use_explicit_padding=False):
+    """Resnet50 v1 FPN Feature Extractor for SSD Models.
+
+    Args:
+      is_training: whether the network is in training mode.
+      depth_multiplier: float depth multiplier for feature extractor.
+      min_depth: minimum feature extractor depth.
+      pad_to_multiple: the nearest multiple to zero pad the input height and
+        width dimensions to.
+      conv_hyperparams: tf slim arg_scope for conv2d and separable_conv2d ops.
+      batch_norm_trainable: Whether to update batch norm parameters during
+        training or not. When training with a small batch size
+        (e.g. 1), it is desirable to disable batch norm update and use
+        pretrained batch norm params.
+      reuse_weights: Whether to reuse variables. Default is None.
+      use_explicit_padding: Whether to use explicit padding when extracting
+        features. Default is False.
+    """
+    super(SSDResnet50V1FpnFeatureExtractor, self).__init__(
+        is_training, depth_multiplier, min_depth, pad_to_multiple,
+        conv_hyperparams, resnet_v1.resnet_v1_50, 'resnet_v1_50_fpn',
+        batch_norm_trainable, reuse_weights, use_explicit_padding)
+
+
+class SSDResnet101V1FpnFeatureExtractor(_SSDResnetV1FpnFeatureExtractor):
+
+  def __init__(self,
+               is_training,
+               depth_multiplier,
+               min_depth,
+               pad_to_multiple,
+               conv_hyperparams,
+               batch_norm_trainable=True,
+               reuse_weights=None,
+               use_explicit_padding=False):
+    """Resnet101 v1 FPN Feature Extractor for SSD Models.
+
+    Args:
+      is_training: whether the network is in training mode.
+      depth_multiplier: float depth multiplier for feature extractor.
+      min_depth: minimum feature extractor depth.
+      pad_to_multiple: the nearest multiple to zero pad the input height and
+        width dimensions to.
+      conv_hyperparams: tf slim arg_scope for conv2d and separable_conv2d ops.
+      batch_norm_trainable: Whether to update batch norm parameters during
+        training or not. When training with a small batch size
+        (e.g. 1), it is desirable to disable batch norm update and use
+        pretrained batch norm params.
+      reuse_weights: Whether to reuse variables. Default is None.
+      use_explicit_padding: Whether to use explicit padding when extracting
+        features. Default is False.
+    """
+    super(SSDResnet101V1FpnFeatureExtractor, self).__init__(
+        is_training, depth_multiplier, min_depth, pad_to_multiple,
+        conv_hyperparams, resnet_v1.resnet_v1_101, 'resnet_v1_101_fpn',
+        batch_norm_trainable, reuse_weights, use_explicit_padding)
+
+
+class SSDResnet152V1FpnFeatureExtractor(_SSDResnetV1FpnFeatureExtractor):
+
+  def __init__(self,
+               is_training,
+               depth_multiplier,
+               min_depth,
+               pad_to_multiple,
+               conv_hyperparams,
+               batch_norm_trainable=True,
+               reuse_weights=None,
+               use_explicit_padding=False):
+    """Resnet152 v1 FPN Feature Extractor for SSD Models.
+
+    Args:
+      is_training: whether the network is in training mode.
+      depth_multiplier: float depth multiplier for feature extractor.
+      min_depth: minimum feature extractor depth.
+      pad_to_multiple: the nearest multiple to zero pad the input height and
+        width dimensions to.
+      conv_hyperparams: tf slim arg_scope for conv2d and separable_conv2d ops.
+      batch_norm_trainable: Whether to update batch norm parameters during
+        training or not. When training with a small batch size
+        (e.g. 1), it is desirable to disable batch norm update and use
+        pretrained batch norm params.
+      reuse_weights: Whether to reuse variables. Default is None.
+      use_explicit_padding: Whether to use explicit padding when extracting
+        features. Default is False.
+    """
+    super(SSDResnet152V1FpnFeatureExtractor, self).__init__(
+        is_training, depth_multiplier, min_depth, pad_to_multiple,
+        conv_hyperparams, resnet_v1.resnet_v1_152, 'resnet_v1_152_fpn',
+        batch_norm_trainable, reuse_weights, use_explicit_padding)

research/object_detection/models/ssd_resnet_v1_fpn_feature_extractor_test.py

+"""Tests for ssd resnet v1 FPN feature extractors."""
+import tensorflow as tf
+
+from object_detection.models import ssd_resnet_v1_fpn_feature_extractor
+from object_detection.models import ssd_resnet_v1_fpn_feature_extractor_testbase
+
+
+class SSDResnet50V1FeatureExtractorTest(
+    ssd_resnet_v1_fpn_feature_extractor_testbase.
+    SSDResnetFeatureExtractorTestBase):
+  """SSDResnet50v1Fpn feature extractor test."""
+
+  def _create_feature_extractor(self, depth_multiplier, pad_to_multiple):
+    min_depth = 32
+    conv_hyperparams = {}
+    batch_norm_trainable = True
+    is_training = True
+    return ssd_resnet_v1_fpn_feature_extractor.SSDResnet50V1FpnFeatureExtractor(
+        is_training, depth_multiplier, min_depth, pad_to_multiple,
+        conv_hyperparams, batch_norm_trainable)
+
+  def _scope_name(self):
+    return 'resnet_v1_50_fpn'
+
+
+class SSDResnet101V1FeatureExtractorTest(
+    ssd_resnet_v1_fpn_feature_extractor_testbase.
+    SSDResnetFeatureExtractorTestBase):
+  """SSDResnet101v1Fpn feature extractor test."""
+
+  def _create_feature_extractor(self, depth_multiplier, pad_to_multiple):
+    min_depth = 32
+    conv_hyperparams = {}
+    batch_norm_trainable = True
+    is_training = True
+    return (
+        ssd_resnet_v1_fpn_feature_extractor.SSDResnet101V1FpnFeatureExtractor(
+            is_training, depth_multiplier, min_depth, pad_to_multiple,
+            conv_hyperparams, batch_norm_trainable))
+
+  def _scope_name(self):
+    return 'resnet_v1_101_fpn'
+
+
+class SSDResnet152V1FeatureExtractorTest(
+    ssd_resnet_v1_fpn_feature_extractor_testbase.
+    SSDResnetFeatureExtractorTestBase):
+  """SSDResnet152v1Fpn feature extractor test."""
+
+  def _create_feature_extractor(self, depth_multiplier, pad_to_multiple):
+    min_depth = 32
+    conv_hyperparams = {}
+    batch_norm_trainable = True
+    is_training = True
+    return (
+        ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor(
+            is_training, depth_multiplier, min_depth, pad_to_multiple,
+            conv_hyperparams, batch_norm_trainable))
+
+  def _scope_name(self):
+    return 'resnet_v1_152_fpn'
+
+
+if __name__ == '__main__':
+  tf.test.main()

research/object_detection/models/ssd_resnet_v1_fpn_feature_extractor_testbase.py

+"""Tests for ssd resnet v1 FPN feature extractors."""
+import abc
+import numpy as np
+
+from object_detection.models import ssd_feature_extractor_test
+
+
+class SSDResnetFeatureExtractorTestBase(
+    ssd_feature_extractor_test.SsdFeatureExtractorTestBase):
+  """Helper test class for SSD Resnet v1 FPN feature extractors."""
+
+  @abc.abstractmethod
+  def _scope_name(self):
+    pass
+
+  def test_extract_features_returns_correct_shapes_256(self):
+    image_height = 256
+    image_width = 256
+    depth_multiplier = 1.0
+    pad_to_multiple = 1
+    expected_feature_map_shape = [(2, 32, 32, 256), (2, 16, 16, 256),
+                                  (2, 8, 8, 256), (2, 4, 4, 256),
+                                  (2, 2, 2, 256)]
+    self.check_extract_features_returns_correct_shape(
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
+        expected_feature_map_shape)
+
+  def test_extract_features_returns_correct_shapes_with_dynamic_inputs(self):
+    image_height = 256
+    image_width = 256
+    depth_multiplier = 1.0
+    pad_to_multiple = 1
+    expected_feature_map_shape = [(2, 32, 32, 256), (2, 16, 16, 256),
+                                  (2, 8, 8, 256), (2, 4, 4, 256),
+                                  (2, 2, 2, 256)]
+    self.check_extract_features_returns_correct_shapes_with_dynamic_inputs(
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
+        expected_feature_map_shape)
+
+  def test_extract_features_returns_correct_shapes_with_pad_to_multiple(self):
+    image_height = 254
+    image_width = 254
+    depth_multiplier = 1.0
+    pad_to_multiple = 32
+    expected_feature_map_shape = [(2, 32, 32, 256), (2, 16, 16, 256),
+                                  (2, 8, 8, 256), (2, 4, 4, 256),
+                                  (2, 2, 2, 256)]
+
+    self.check_extract_features_returns_correct_shape(
+        2, image_height, image_width, depth_multiplier, pad_to_multiple,
+        expected_feature_map_shape)
+
+  def test_extract_features_raises_error_with_invalid_image_size(self):
+    image_height = 32
+    image_width = 32
+    depth_multiplier = 1.0
+    pad_to_multiple = 1
+    self.check_extract_features_raises_error_with_invalid_image_size(
+        image_height, image_width, depth_multiplier, pad_to_multiple)
+
+  def test_preprocess_returns_correct_value_range(self):
+    image_height = 128
+    image_width = 128
+    depth_multiplier = 1
+    pad_to_multiple = 1
+    test_image = np.random.rand(4, image_height, image_width, 3)
+    feature_extractor = self._create_feature_extractor(depth_multiplier,
+                                                       pad_to_multiple)
+    preprocessed_image = feature_extractor.preprocess(test_image)
+    self.assertAllClose(preprocessed_image,
+                        test_image - [[123.68, 116.779, 103.939]])
+
+  def test_variables_only_created_in_scope(self):
+    depth_multiplier = 1
+    pad_to_multiple = 1
+    self.check_feature_extractor_variables_under_scope(
+        depth_multiplier, pad_to_multiple, self._scope_name())

research/object_detection/protos/BUILD

@@ -9,6 +9,7 @@ licenses(["notice"])
 proto_library(
     name = "argmax_matcher_proto",
     srcs = ["argmax_matcher.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -20,6 +21,7 @@ py_proto_library(
 proto_library(
     name = "bipartite_matcher_proto",
     srcs = ["bipartite_matcher.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -31,6 +33,7 @@ py_proto_library(
 proto_library(
     name = "matcher_proto",
     srcs = ["matcher.proto"],
+    cc_api_version = 2,
     deps = [
         ":argmax_matcher_proto",
         ":bipartite_matcher_proto",
@@ -46,6 +49,7 @@ py_proto_library(
 proto_library(
     name = "faster_rcnn_box_coder_proto",
     srcs = ["faster_rcnn_box_coder.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -57,6 +61,7 @@ py_proto_library(
 proto_library(
     name = "keypoint_box_coder_proto",
     srcs = ["keypoint_box_coder.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -68,6 +73,7 @@ py_proto_library(
 proto_library(
     name = "mean_stddev_box_coder_proto",
     srcs = ["mean_stddev_box_coder.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -79,6 +85,7 @@ py_proto_library(
 proto_library(
     name = "square_box_coder_proto",
     srcs = ["square_box_coder.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -90,6 +97,7 @@ py_proto_library(
 proto_library(
     name = "box_coder_proto",
     srcs = ["box_coder.proto"],
+    cc_api_version = 2,
     deps = [
         ":faster_rcnn_box_coder_proto",
         ":keypoint_box_coder_proto",
@@ -107,6 +115,7 @@ py_proto_library(
 proto_library(
     name = "grid_anchor_generator_proto",
     srcs = ["grid_anchor_generator.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -118,6 +127,7 @@ py_proto_library(
 proto_library(
     name = "ssd_anchor_generator_proto",
     srcs = ["ssd_anchor_generator.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -126,11 +136,25 @@ py_proto_library(
     deps = [":ssd_anchor_generator_proto"],
 )
 
+proto_library(
+    name = "multiscale_anchor_generator_proto",
+    srcs = ["multiscale_anchor_generator.proto"],
+    cc_api_version = 2,
+)
+
+py_proto_library(
+    name = "multiscale_anchor_generator_py_pb2",
+    api_version = 2,
+    deps = [":multiscale_anchor_generator_proto"],
+)
+
 proto_library(
     name = "anchor_generator_proto",
     srcs = ["anchor_generator.proto"],
+    cc_api_version = 2,
     deps = [
         ":grid_anchor_generator_proto",
+        ":multiscale_anchor_generator_proto",
         ":ssd_anchor_generator_proto",
     ],
 )
@@ -144,6 +168,7 @@ py_proto_library(
 proto_library(
     name = "input_reader_proto",
     srcs = ["input_reader.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -155,6 +180,7 @@ py_proto_library(
 proto_library(
     name = "losses_proto",
     srcs = ["losses.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -166,6 +192,7 @@ py_proto_library(
 proto_library(
     name = "optimizer_proto",
     srcs = ["optimizer.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -177,6 +204,7 @@ py_proto_library(
 proto_library(
     name = "post_processing_proto",
     srcs = ["post_processing.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -188,6 +216,7 @@ py_proto_library(
 proto_library(
     name = "hyperparams_proto",
     srcs = ["hyperparams.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -199,6 +228,7 @@ py_proto_library(
 proto_library(
     name = "box_predictor_proto",
     srcs = ["box_predictor.proto"],
+    cc_api_version = 2,
     deps = [":hyperparams_proto"],
 )
 
@@ -211,6 +241,7 @@ py_proto_library(
 proto_library(
     name = "region_similarity_calculator_proto",
     srcs = ["region_similarity_calculator.proto"],
+    cc_api_version = 2,
     deps = [],
 )
 
@@ -223,6 +254,7 @@ py_proto_library(
 proto_library(
     name = "preprocessor_proto",
     srcs = ["preprocessor.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -234,6 +266,7 @@ py_proto_library(
 proto_library(
     name = "train_proto",
     srcs = ["train.proto"],
+    cc_api_version = 2,
     deps = [
         ":optimizer_proto",
         ":preprocessor_proto",
@@ -249,6 +282,7 @@ py_proto_library(
 proto_library(
     name = "eval_proto",
     srcs = ["eval.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -260,6 +294,7 @@ py_proto_library(
 proto_library(
     name = "image_resizer_proto",
     srcs = ["image_resizer.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(
@@ -271,19 +306,21 @@ py_proto_library(
 proto_library(
     name = "faster_rcnn_proto",
     srcs = ["faster_rcnn.proto"],
+    cc_api_version = 2,
     deps = [
         ":box_predictor_proto",
-        "//object_detection/protos:anchor_generator_proto",
-        "//object_detection/protos:hyperparams_proto",
-        "//object_detection/protos:image_resizer_proto",
-        "//object_detection/protos:losses_proto",
-        "//object_detection/protos:post_processing_proto",
+        "//tensorflow/models/research/object_detection/protos:anchor_generator_proto",
+        "//tensorflow/models/research/object_detection/protos:hyperparams_proto",
+        "//tensorflow/models/research/object_detection/protos:image_resizer_proto",
+        "//tensorflow/models/research/object_detection/protos:losses_proto",
+        "//tensorflow/models/research/object_detection/protos:post_processing_proto",
     ],
 )
 
 proto_library(
     name = "ssd_proto",
     srcs = ["ssd.proto"],
+    cc_api_version = 2,
     deps = [
         ":anchor_generator_proto",
         ":box_coder_proto",
@@ -300,6 +337,7 @@ proto_library(
 proto_library(
     name = "model_proto",
     srcs = ["model.proto"],
+    cc_api_version = 2,
     deps = [
         ":faster_rcnn_proto",
         ":ssd_proto",
@@ -315,6 +353,7 @@ py_proto_library(
 proto_library(
     name = "pipeline_proto",
     srcs = ["pipeline.proto"],
+    cc_api_version = 2,
     deps = [
         ":eval_proto",
         ":input_reader_proto",
@@ -332,6 +371,7 @@ py_proto_library(
 proto_library(
     name = "string_int_label_map_proto",
     srcs = ["string_int_label_map.proto"],
+    cc_api_version = 2,
 )
 
 py_proto_library(

research/object_detection/protos/anchor_generator.proto

@@ -4,6 +4,7 @@ package object_detection.protos;
 
 import "object_detection/protos/grid_anchor_generator.proto";
 import "object_detection/protos/ssd_anchor_generator.proto";
+import "object_detection/protos/multiscale_anchor_generator.proto";
 
 // Configuration proto for the anchor generator to use in the object detection
 // pipeline. See core/anchor_generator.py for details.
@@ -11,5 +12,6 @@ message AnchorGenerator {
   oneof anchor_generator_oneof {
     GridAnchorGenerator grid_anchor_generator = 1;
     SsdAnchorGenerator ssd_anchor_generator = 2;
+    MultiscaleAnchorGenerator multiscale_anchor_generator = 3;
   }
 }

research/object_detection/protos/box_predictor.proto

@@ -11,6 +11,7 @@ message BoxPredictor {
     ConvolutionalBoxPredictor convolutional_box_predictor = 1;
     MaskRCNNBoxPredictor mask_rcnn_box_predictor = 2;
     RfcnBoxPredictor rfcn_box_predictor = 3;
+    WeightSharedConvolutionalBoxPredictor weight_shared_convolutional_box_predictor = 4;
   }
 }
 
@@ -46,12 +47,39 @@ message ConvolutionalBoxPredictor {
   optional int32 box_code_size = 8 [default = 4];
 
   // Whether to apply sigmoid to the output of class predictions.
-  // TODO: Do we need this since we have a post processing module.?
+  // TODO(jonathanhuang): Do we need this since we have a post processing
+  // module.?
   optional bool apply_sigmoid_to_scores = 9 [default = false];
 
   optional float class_prediction_bias_init = 10 [default = 0.0];
 }
 
+// Configuration proto for weight shared convolutional box predictor.
+message WeightSharedConvolutionalBoxPredictor {
+  // Hyperparameters for convolution ops used in the box predictor.
+  optional Hyperparams conv_hyperparams = 1;
+
+  // Number of the additional conv layers before the predictor.
+  optional int32 num_layers_before_predictor = 4 [default = 0];
+
+  // Output depth for the convolution ops prior to predicting box encodings
+  // and class predictions.
+  optional int32 depth = 2 [default = 0];
+
+  // Size of final convolution kernel. If the spatial resolution of the feature
+  // map is smaller than the kernel size, then the kernel size is set to
+  // min(feature_width, feature_height).
+  optional int32 kernel_size = 7 [default = 3];
+
+  // Size of the encoding for boxes.
+  optional int32 box_code_size = 8 [default = 4];
+
+  // Bias initialization for class prediction. It has been show to stabilize
+  // training where there are large number of negative boxes. See
+  // https://arxiv.org/abs/1708.02002 for details.
+  optional float class_prediction_bias_init = 10 [default = 0.0];
+}
+
 message MaskRCNNBoxPredictor {
   // Hyperparameters for fully connected ops used in the box predictor.
   optional Hyperparams fc_hyperparams = 1;
@@ -71,12 +99,22 @@ message MaskRCNNBoxPredictor {
   // Whether to predict instance masks inside detection boxes.
   optional bool predict_instance_masks = 6 [default = false];
 
-  // The depth for the first conv2d_transpose op  applied to the
-  // image_features in the mask prediciton branch
+  // The depth for the first conv2d_transpose op applied to the
+  // image_features in the mask prediction branch. If set to 0, the value
+  // will be set automatically based on the number of channels in the image
+  // features and the number of classes.
   optional int32 mask_prediction_conv_depth = 7 [default = 256];
 
   // Whether to predict keypoints inside detection boxes.
   optional bool predict_keypoints = 8 [default = false];
+
+  // The height and the width of the predicted mask.
+  optional int32 mask_height = 9 [default = 15];
+  optional int32 mask_width = 10 [default = 15];
+
+  // The number of convolutions applied to image_features in the mask prediction
+  // branch.
+  optional int32 mask_prediction_num_conv_layers = 11 [default = 2];
 }
 
 message RfcnBoxPredictor {

research/object_detection/protos/eval.proto

@@ -26,9 +26,8 @@ message EvalConfig {
   // BNS name of the TensorFlow master.
   optional string eval_master = 7 [default=""];
 
-  // Type of metrics to use for evaluation. Currently supports only Pascal VOC
-  // detection metrics.
-  optional string metrics_set = 8 [default="pascal_voc_metrics"];
+  // Type of metrics to use for evaluation.
+  repeated string metrics_set = 8;
 
   // Path to export detections to COCO compatible JSON format.
   optional string export_path = 9 [default=''];
@@ -38,10 +37,35 @@ message EvalConfig {
   optional bool ignore_groundtruth = 10 [default=false];
 
   // Use exponential moving averages of variables for evaluation.
+  // TODO(rathodv): When this is false make sure the model is constructed
+  // without moving averages in restore_fn.
   optional bool use_moving_averages = 11 [default=false];
 
   // Whether to evaluate instance masks.
   // Note that since there is no evaluation code currently for instance
   // segmenation this option is unused.
   optional bool eval_instance_masks = 12 [default=false];
+
+  // Minimum score threshold for a detected object box to be visualized
+  optional float min_score_threshold = 13 [default=0.5];
+
+  // Maximum number of detections to visualize
+  optional int32 max_num_boxes_to_visualize = 14 [default=20];
+
+  // When drawing a single detection, each label is by default visualized as
+  // <label name> : <label score>. One can skip the name or/and score using the
+  // following fields:
+  optional bool skip_scores = 15 [default=false];
+  optional bool skip_labels = 16 [default=false];
+
+  // Whether to show groundtruth boxes in addition to detected boxes in
+  // visualizations.
+  optional bool visualize_groundtruth_boxes = 17 [default=false];
+
+  // Box color for visualizing groundtruth boxes.
+  optional string groundtruth_box_visualization_color = 18 [default="black"];
+
+  // Whether to keep image identifier in filename when exported to
+  // visualization_export_dir.
+  optional bool keep_image_id_for_visualization_export = 19 [default=false];
 }

research/object_detection/protos/faster_rcnn.proto

@@ -20,7 +20,7 @@ import "object_detection/protos/post_processing.proto";
 message FasterRcnn {
 
   // Whether to construct only the Region Proposal Network (RPN).
-  optional bool first_stage_only = 1 [default=false];
+  optional int32 number_of_stages = 1 [default=2];
 
   // Number of classes to predict.
   optional int32 num_classes = 3;

research/object_detection/protos/image_resizer.proto

@@ -29,6 +29,11 @@ message KeepAspectRatioResizer {
 
   // Desired method when resizing image.
   optional ResizeType resize_method = 3 [default = BILINEAR];
+
+  // Whether to pad the image with zeros so the output spatial size is
+  // [max_dimension, max_dimension]. Note that the zeros are padded to the
+  // bottom and the right of the resized image.
+  optional bool pad_to_max_dimension = 4 [default = false];
 }
 
 // Configuration proto for image resizer that resizes to a fixed shape.

research/object_detection/protos/input_reader.proto

@@ -15,6 +15,13 @@ package object_detection.protos;
 // 'groundtruth_instance_masks': (Optional), a [num_boxes, image_height,
 //    image_width] float tensor storing binary mask of the objects in boxes.
 
+// Instance mask format. Note that PNG masks are much more space efficient.
+enum InstanceMaskType {
+  DEFAULT = 0;          // Default implementation, currently NUMERICAL_MASKS
+  NUMERICAL_MASKS = 1;  // [num_masks, H, W] float32 binary masks.
+  PNG_MASKS = 2;        // Encoded PNG masks.
+}
+
 message InputReader {
   // Path to StringIntLabelMap pbtxt file specifying the mapping from string
   // labels to integer ids.
@@ -24,6 +31,12 @@ message InputReader {
   // shuffled randomly.
   optional bool shuffle = 2 [default=true];
 
+  // Buffer size to be used when shuffling.
+  optional uint32 shuffle_buffer_size = 11 [default = 100];
+
+  // Buffer size to be used when shuffling file names.
+  optional uint32 filenames_shuffle_buffer_size = 12 [default = 100];
+
   // Maximum number of records to keep in reader queue.
   optional uint32 queue_capacity = 3 [default=2000];
 
@@ -38,9 +51,15 @@ message InputReader {
   // Number of reader instances to create.
   optional uint32 num_readers = 6 [default=8];
 
+  // Size of the buffer for prefetching (in batches).
+  optional uint32 prefetch_buffer_size = 13 [default = 2];
+
   // Whether to load groundtruth instance masks.
   optional bool load_instance_masks = 7 [default = false];
 
+  // Type of instance mask.
+  optional InstanceMaskType mask_type = 10 [default = NUMERICAL_MASKS];
+
   oneof input_reader {
     TFRecordInputReader tf_record_input_reader = 8;
     ExternalInputReader external_input_reader = 9;

research/object_detection/protos/losses.proto

@@ -33,12 +33,14 @@ message LocalizationLoss {
 
 // L2 location loss: 0.5 * ||weight * (a - b)|| ^ 2
 message WeightedL2LocalizationLoss {
+  // DEPRECATED, do not use.
   // Output loss per anchor.
   optional bool anchorwise_output = 1 [default=false];
 }
 
 // SmoothL1 (Huber) location loss: .5 * x ^ 2 if |x| < 1 else |x| - .5
 message WeightedSmoothL1LocalizationLoss {
+  // DEPRECATED, do not use.
   // Output loss per anchor.
   optional bool anchorwise_output = 1 [default=false];
 }
@@ -59,6 +61,7 @@ message ClassificationLoss {
 
 // Classification loss using a sigmoid function over class predictions.
 message WeightedSigmoidClassificationLoss {
+  // DEPRECATED, do not use.
   // Output loss per anchor.
   optional bool anchorwise_output = 1 [default=false];
 }
@@ -66,6 +69,7 @@ message WeightedSigmoidClassificationLoss {
 // Sigmoid Focal cross entropy loss as described in
 // https://arxiv.org/abs/1708.02002
 message SigmoidFocalClassificationLoss {
+  // DEPRECATED, do not use.
   optional bool anchorwise_output = 1 [default = false];
   // modulating factor for the loss.
   optional float gamma = 2 [default = 2.0];
@@ -75,6 +79,7 @@ message SigmoidFocalClassificationLoss {
 
 // Classification loss using a softmax function over class predictions.
 message WeightedSoftmaxClassificationLoss {
+  // DEPRECATED, do not use.
   // Output loss per anchor.
   optional bool anchorwise_output = 1 [default=false];
   // Scale logit (input) value before calculating softmax classification loss.
@@ -93,6 +98,7 @@ message BootstrappedSigmoidClassificationLoss {
   // probabilities.
   optional bool hard_bootstrap = 2 [default=false];
 
+  // DEPRECATED, do not use.
   // Output loss per anchor.
   optional bool anchorwise_output = 3 [default=false];
 }

research/object_detection/protos/multiscale_anchor_generator.proto

+  syntax = "proto2";
+
+package object_detection.protos;
+
+// Configuration proto for RetinaNet anchor generator described in
+// https://arxiv.org/abs/1708.02002. See
+// anchor_generators/multiscale_grid_anchor_generator.py for details.
+message MultiscaleAnchorGenerator {
+  // minimum level in feature pyramid
+  optional int32 min_level = 1 [default = 3];
+
+  // maximum level in feature pyramid
+  optional int32 max_level = 2 [default = 7];
+
+  // Scale of anchor to feature stride
+  optional float anchor_scale = 3 [default = 4.0];
+
+  // Aspect ratios for anchors at each grid point.
+  repeated float aspect_ratios = 4;
+
+  // Number of intermediate scale each scale octave
+}

research/object_detection/protos/pipeline.proto

@@ -15,4 +15,5 @@ message TrainEvalPipelineConfig {
   optional InputReader train_input_reader = 3;
   optional EvalConfig eval_config = 4;
   optional InputReader eval_input_reader = 5;
+  extensions 1000 to max;
 }

research/object_detection/protos/preprocessor.proto

@@ -3,7 +3,7 @@ syntax = "proto2";
 package object_detection.protos;
 
 // Message for defining a preprocessing operation on input data.
-// See: //object_detection/core/preprocessor.py
+// See: //third_party/tensorflow_models/object_detection/core/preprocessor.py
 message PreprocessingStep {
   oneof preprocessing_step {
     NormalizeImage normalize_image = 1;
@@ -202,7 +202,7 @@ message RandomCropPadImage {
   repeated float max_padded_size_ratio = 9;
 
   // Color of the padding. If unset, will pad using average color of the input
-  // image.
+  // image. This field should be of length 3.
   repeated float pad_color = 10;
 }
 

research/object_detection/protos/ssd.proto

@@ -82,4 +82,8 @@ message SsdFeatureExtractor {
   // will apply only to the additional layers that are added and are outside the
   // canned arg_scope.
   optional bool batch_norm_trainable = 6 [default=true];
+
+  // Whether to use explicit padding when extracting SSD multiresolution
+  // features. Note that this does not apply to the base feature extractor.
+  optional bool use_explicit_padding = 7 [default=false];
 }

research/object_detection/protos/train.proto

@@ -35,6 +35,11 @@ message TrainConfig {
   // If false, it assumes the checkpoint was a object classification model.
   optional bool from_detection_checkpoint = 8 [default=false];
 
+  // Whether to load all checkpoint vars that match model variable names and
+  // sizes. This option is only available if `from_detection_checkpoint` is
+  // True.
+  optional bool load_all_detection_checkpoint_vars = 19 [default = false];
+
   // Number of steps to train the DetectionModel for. If 0, will train the model
   // indefinitely.
   optional uint32 num_steps = 9 [default=0];
@@ -66,4 +71,11 @@ message TrainConfig {
   // This is useful when each box can have multiple labels.
   // Note that only Sigmoid classification losses should be used.
   optional bool merge_multiple_label_boxes = 17 [default=false];
+
+  // Whether to add regularization loss to `total_loss`. This is true by
+  // default and adds all regularization losses defined in the model to
+  // `total_loss`.
+  // Setting this option to false is very useful while debugging the model and
+  // losses.
+  optional bool add_regularization_loss = 18 [default=true];
 }

research/object_detection/samples/configs/BUILD

+package(
+    default_visibility = ["//visibility:public"],
+)
+
+licenses(["notice"])
+
+exports_files([
+    "faster_rcnn_resnet50_pets.config",
+    "ssd_inception_v2_pets.config",
+])

research/object_detection/samples/configs/embedded_ssd_mobilenet_v1_coco.config

+# Embedded SSD with Mobilenet v1 configuration for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  ssd {
+    num_classes: 90
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 10.0
+        x_scale: 10.0
+        height_scale: 5.0
+        width_scale: 5.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    anchor_generator {
+      ssd_anchor_generator {
+        num_layers: 5
+        min_scale: 0.2
+        max_scale: 0.95
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        aspect_ratios: 3.0
+        aspect_ratios: 0.3333
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 256
+        width: 256
+      }
+    }
+    box_predictor {
+      convolutional_box_predictor {
+        min_depth: 0
+        max_depth: 0
+        num_layers_before_predictor: 0
+        use_dropout: false
+        dropout_keep_probability: 0.8
+        kernel_size: 1
+        box_code_size: 4
+        apply_sigmoid_to_scores: false
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.03
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            train: true,
+            scale: true,
+            center: true,
+            decay: 0.9997,
+            epsilon: 0.001,
+          }
+        }
+      }
+    }
+    feature_extractor {
+      type: 'embedded_ssd_mobilenet_v1'
+      min_depth: 16
+      depth_multiplier: 0.125
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          train: true,
+          scale: true,
+          center: true,
+          decay: 0.9997,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid {
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      hard_example_miner {
+        num_hard_examples: 3000
+        iou_threshold: 0.99
+        loss_type: CLASSIFICATION
+        max_negatives_per_positive: 3
+        min_negatives_per_image: 0
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  batch_size: 32
+  optimizer {
+    rms_prop_optimizer: {
+      learning_rate: {
+        exponential_decay_learning_rate {
+          initial_learning_rate: 0.004
+          decay_steps: 800720
+          decay_factor: 0.95
+        }
+      }
+      momentum_optimizer_value: 0.9
+      decay: 0.9
+      epsilon: 1.0
+    }
+  }
+  fine_tune_checkpoint: "/PATH_TO_BE_CONFIGURED/model.ckpt"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    ssd_random_crop {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  use_moving_averages: true
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}