Transform the object detection model trained on TensorFlow to iOS CoreML model type used tfcoreml(reference) and coremltools.

• mlmodels_IOU0.4_Conf0.6
  Core ML models(iOS) transformed from the models that trained on tensorflow(threshold: IOU=0.4; Confidece=0.6)
• MobileNetV1_SSD/MobileNetV2_SSDLite/MobileNetV3_Large_SSDLite/MobileNetV3_Small_SSDLite/MobileDet_SSD_CPU

The transform process from file list

Original Model trained on tensorflow contains:preprocess + mobilenet_ssd + anchor generate + NMS + predictor parts.

1. check_modelNodes.py
   Load the frozen_inference_graph.pb,and print the name of nodes in each layer. Then get the input_node_name(mobilenet) and output_node_name(scores/boundingboxes)
2. frozenToSimplePB.py
   Simplify the model(Strip unused subgraphs get simplified frozen graph-ssd_mobilenet.pb)
3. simplePB_ToCoreml.py
   Main network tranceform(ssd_mobilenet.mlmodel)
4. Decoder.py

6. NMS.py
7. pipelines.py