koobas.hobune.stream
TFException unity export custom model
Hi
please some one help me I am stuck with this exception it has become a show stopper for my project
E/Unity: TFException: NodeDef mentions attr 'index_type' not in Op output:T; attr=T:type>; NodeDef: GridAnchorGenerator/Meshgrid_3/ExpandedShape_1/ones = Fill[T=DT_INT32, index_type=DT_INT32](GridAnchorGenerator/Meshgrid_3/ExpandedShape_1/Reshape, GridAnchorGenerator/Meshgrid_3/ExpandedShape_1/ones/Const). (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.). at TensorFlow.TFStatus.CheckMaybeRaise (TensorFlow.TFStatus incomingStatus, System.Boolean last) [0x0004a] in :0 at TensorFlow.TFGraph.Import (TensorFlow.TFBuffer graphDef, TensorFlow.TFImportGraphDefOptions options, TensorFlow.TFStatus status) [0x00068] in :0 at TensorFlow.TFGraph.Import (System.Byte[] buffer, TensorFlow.TFImportGraphDefOptions options, TensorFlow.TFStatus status) [0x00055] in :0 at TensorFlow.TFGraph.Import (System.Byte[] buffer, System.Stri 2019-12-30 12:18:35.766 28206-28223/? E/Unity: OPENGL NATIVE PLUG-IN ERROR: GL_INVALID_FRAMEBUFFER_OPERATION: Framebuffer is not complete or incompatible with command
Environment using: Ubuntu 16.4 for training a custom model using tensorflow object detection api. Tensorflow version 1.14 python version 3.6 Windows Unity 2018.4.10f1 for generating an android apk for detection.
I have tried following ways: 1. Directly changed the name of the .pb generated to .bytes 2. Tried to freeze the graph using freeze_graph.py and generated .bytes file response is the same.
Thanks, Jahnavi
