INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, Name: , Context feature 'depth' is required but could not be found.

[ghost]

I'm getting above error while training fasterrcnn using luminoth. can someone provide solution for this.

Error:- tensorflow.python.framework.errors_impl.InvalidArgumentError: Name: , Context feature 'depth' is required but could not be found. [[Node: object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample = ParseSingleSequenceExample[Ncontext_dense=5, Ncontex t_sparse=0, Nfeature_list_dense=0, Nfeature_list_sparse=5, Tcontext_dense=[DT_INT64, DT_STRING, DT_INT64, DT_STRING, DT_INT64], context_dense_shapes=[ [], [], [], [], []], context_sparse_types=[], feature_list_dense_shapes=[], feature_list_dense_types=[], feature_list_sparse_types=[DT_INT64, DT_INT64 , DT_INT64, DT_INT64, DT_INT64], _device="/job:localhost/replica:0/task:0/device:CPU:0"](object_detection_dataset/ReaderReadV2:1, object_detection_dat aset/ParseSingleSequenceExample/ParseSingleSequenceExample/feature_list_dense_missing_assumed_empty, object_detection_dataset/ParseSingleSequenceExamp le/ParseSingleSequenceExample/context_dense_keys_0, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/context_densekeys 1, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/context_dense_keys_2, object_detection_dataset/ParseSingleSequenceEx ample/ParseSingleSequenceExample/context_dense_keys_3, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/context_dense_ke ys_4, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/feature_list_sparse_keys_0, object_detection_dataset/ParseSingleS equenceExample/ParseSingleSequenceExample/feature_list_sparse_keys_1, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/f eature_list_sparse_keys_2, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/feature_list_sparse_keys_3, object_detection _dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/feature_list_sparse_keys_4, object_detection_dataset/ParseSingleSequenceExample/Const, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/feature_list_dense_missing_assumed_empty, object_detection_dataset/Pars eSingleSequenceExample/Const, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/feature_list_dense_missing_assumed_empty, object_detection_dataset/ParseSingleSequenceExample/Const, object_detection_dataset/ParseSingleSequenceExample/ParseSingleSequenceExample/debug_name) ]]

Error snapshot :--

[nagitsu]

Seems to be a malformed tfrecords file. What dataset are you using? How did you get it transformed?

Also, which TF and Luminoth version are you using?

[ghost]

I'm using RBC dataset from this https://github.com/cosmicad/dataset link for RBC detection in images. I used xml_to_csv.py script from https://github.com/datitran/raccoon_dataset to convert xml to csv. Here's the snapshot of csv generated.

And generate_tfrecord.py script from the same repo to create train.tfrecords. while creating train.tfrecords , I've attached .jpg extension to filename.

Python version :- 3.6.3 Luminoth version :- 0.1.1

[FalconMadhab]

Same Error