cyrusbehr opened a new issue #17195: Unable to convert Insightface resnet 100 model to onnx URL: https://github.com/apache/incubator-mxnet/issues/17195 I originally posted this question to the onnxruntime github page, but was hold to repost it here. The original post can be found [here](https://github.com/microsoft/onnxruntime/issues/2743#issue-542643478): I am trying to convert the Insightface resnet 100 model (` LResNet100E-IR,ArcFace@ms1m-refine-v2`) which can be found [here](https://github.com/deepinsight/insightface/wiki/Model-Zoo) to work with onnxruntime. I use the following conversion python script to convert the model. The model converts successfully. ``` import mxnet as mx import numpy as np from mxnet.contrib import onnx as onnx_mxnet import logging logging.basicConfig(level=logging.INFO) sym = 'model-symbol.json' params = 'model-0000.params' input_shape = (1,3,112,112) # Path of the output file onnx_file = './insightface_resnet100.onnx' converted_model_path = onnx_mxnet.export_model(sym, params, [input_shape], np.float32, onnx_file) from onnx import checker import onnx model_proto = onnx.load_model(converted_model_path) # Check if converted ONNX protobuf is valid checker.check_graph(model_proto.graph) ``` Next, I try to load the model in C++ using the following code. Note, I am following the example found [here](https://github.com/microsoft/onnxruntime/blob/master/csharp/test/Microsoft.ML.OnnxRuntime.EndToEndTests.Capi/CXX_Api_Sample.cpp) : ``` int main(int argc, char* argv[]) { Ort::Env env(ORT_LOGGING_LEVEL_WARNING, "test"); Ort::SessionOptions session_options; session_options.SetIntraOpNumThreads(1); session_options.SetGraphOptimizationLevel(GraphOptimizationLevel::ORT_ENABLE_EXTENDED); const char* model_path = "../models/insightface_resnet100.onnx"; Ort::Session session(env, model_path, session_options); return 0; } ``` When I run this code, I get the following error: ``` terminate called after throwing an instance of 'Ort::Exception' what(): Type Error: Type parameter (T) bound to different types (tensor(float) and tensor(double) in node (_minusscalar0). Aborted ``` I am using `libonnxruntime.so.1.1.0`
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
