Hello,
I am looking for a complete list of Tensorflow2 models (preferably from the Tensorflow Model Zoo or others like YOLO) that are fully supported by SNPE. I seem to have some trouble converting a few custom trained Tensorflow2 models to DLC like F-RCNN, YOLOv4 or YOLOv4 tiny. Is there any way to successfully convert a model that may not be fully supported by snpe-tensorflow-to-dlc tool?
Regards,
Amith
Hello,
We were able convert YOLO V3 model in ONNX (https://github.com/onnx/models/tree/master/vision/object_detection_segme...) to DLC using the following command.
snpe-onnx-to-dlc --input_network yolov3-10.onnx -d input_1 1,416,416,3
For YOLO V3 tiny we used another approach to convert it to DLC. The steps are as follows:
snpe-tensorflow-to-dlc --input_network <path_to_frozen_graph> --input_dim input_1 1,416,416,3 --out_node conv2d_9/BiasAdd --out_node conv2d_12/BiasAdd --output_path <Path_to_DLC>.dlc
Hello,
When i use the following command ,snpe-onnx-to-dlc --input_network yolov3-10.onnx -d input_1 1,416,416,3
i met the issue
So what is your version of onnx and snpe?
Dear customer,
What's SNPE version you used?
Currently, the SNPE supports TF1.15 only. Definitely, we have supported the environment from TF2. We're recommending to develop and train the model based on TF1.15.
BR.
Wei