After exporting model with export_tflite_ssd_graph.py I am getting an model with only one output

I tried to convert my trained model to tflite but i get the output that isn't supported (attached a photo) TFlite_Detection_PostProcess that isn't splited to 4 separated outputs.

I trained ssd_mobilenet_v2_quantized_300x300_coco and ssd_mobilenet_v1_quantized_300x300_coco14_sync for both the same result.

I used commands:
python export_tflite_ssd_graph.py --pipeline_config_path=training/ssd_mobilenet_v1_quantized_300x300_coco14_sync.config --trained_checkpoint_prefix=training/model.ckpt-5697 --output_directory=tflite --add_postprocessing_op=true

tflite_convert --graph_def_file=tflite/tflite_graph.pb --output_file=tflite/detect.tflite --output_format=TFLITE --input_shapes=1,300,300,3 --input_arrays=normalized_input_image_tensor --output_arrays='TFLite_Detection_PostProcess','TFLite_Detection_PostProcess:1','TFLite_Detection_PostProcess:2','TFLite_Detection_PostProcess:3' --inference_type=QUANTIZED_UINT8 --mean_values=128 --std_dev_values=127 --change_concat_input_ranges=false --allow_custom_ops

Thanks for any help in advance.