Hi,
I am converting from yolov3.pb to yolov3.dlc with the following command:
snpe-tensorflow-to-dlc --graph yolov3.pb --input_dim input_1 1,416,416,3 --out_node output0 --out_node output1 --out_node output2 --dlc yolov3.dlc --verbose --allow_unconsumed_nodes
The model is converted but it just recongnizes the output2 and not all of them. In addition, if I apply the same command but only with one output node it recognizes the output specified.
I have also tried to convert it with the previous name of the output nodes, and the same problem happens:
snpe-tensorflow-to-dlc --graph yolov3.pb --input_dim input_1 1,416,416,3 --out_node conv2d_59/BiasAdd --out_node conv2d_67/BiasAdd --out_node conv2d_75/BiasAdd --dlc yolov3.dlc --verbose --allow_unconsumed_nodes
I am following the same steps as convert_mobilenetssd
Has anyone been able to convert yolov3 with the three output nodes? Is this a bug of snpe-tensorflow-to-dlc?
Thanks, Ignacio
Hi,
I am having a trouble on using snpe sdk to convert yolov3.
Did you had any progress after this wirte?
If it is, which code did you used for tensorflow version of Yolov3??
Need your help whatever it is.. It works with inceptionV3 which is tutorial of snpe_tensorflow_to_dlc
Thanks,
Chris