While expoting an object detection model inference graph with Tensorflow Object Detection API (TFODAPI), I am getting a warning as:
WARNING:tensorflow:Skipping full serialization of Keras layer object_detection.meta_architectures.ssd_meta_arch.SSDMetaArch object at 0x7f7bf0096d00>, because it is not built.
W1211 12:05:10.070806 140172767647616 save_impl.py:66]
This warning also occurs while expoting tflite graph. This is resulting an error while converting the .pb model to tflite with metadata. Also this further gives an error while conversion as:
TypeError: EndVector() missing 1 required positional argument: 'vectorNumElems'
While the inference from .pb model works perfectly, I am not able to get inference from tflite model.
my expoting graph script is:
%cd /content/models/research/object_detection
##Export inference graph
!python exporter_main_v2.py --trained_checkpoint_dir=/content/gdrive/MyDrive/Road_potholes/new_try/training --pipeline_config_path=/content/gdrive/MyDrive/Road_potholes/new_try/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.config --output_directory /content/gdrive/MyDrive/Road_potholes/new_try/inference_graph
and export tflite graph code is :
%cd /content/models/research/object_detection
!python export_tflite_graph_tf2.py --pipeline_config_path /content/gdrive/MyDrive/Road_potholes/new_try/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.config --trained_checkpoint_dir /content/gdrive/MyDrive/Road_potholes/new_try/training --output_directory /content/gdrive/MyDrive/Road_potholes/new_try/tflite
I have followed the code as shown here: https://www.youtube.com/watch?v=eA5G-uL_OmQ&t=1591s
