I'm trying to launch model R100 (mxnet) from here:
https://github.com/deepinsight/insightface/tree/master/model_zoo
I converted it to onnx with that:
sym = './model-symbol.json'
params = './model-0000.params'
input_shape = (1,3,112,112)
onnx_file = './R100_mxnet.onnx'
converted_model_path = onnx_mxnet.export_model(sym, params, [input_shape], np.float32, onnx_file)
This check is passed:
model_proto = onnx.load_model('./R100_mxnet.onnx')
checker.check_graph(model_proto.graph)
But when I try to inference with:
classifier.run(None, {'data': np.ones([1, 3, 112, 112]).astype('float32')})[0].shape
I get:
~/.local/lib/python3.6/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py in run(self, output_names, input_feed, run_options)
190 output_names = [output.name for output in self._outputs_meta]
191 try:
--> 192 return self._sess.run(output_names, input_feed, run_options)
193 except C.EPFail as err:
194 if self._enable_fallback:
Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running PRelu node. Name:'conv_1_relu' Status Message: conv_1_relu: left operand cannot broadcast on dim 3 LeftShape: {1,64,56,56}, RightShape: {64}
Is it an error with exporting or with importing and can I fix it?
