You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
I try to use c-api as this demo, it is ok. but when I try to quantize squeeze.onnx to float 16, and then inference again, it report:
Unexpected input data type. Actual: (N11onnxruntime11NonOnnxTypeIfEE) , expected: (N11onnxruntime11NonOnnxTypeINS_9MLFloat16EEE)
I use the follow script to convert float32 model to float16:
Is your feature request related to a problem? Please describe.
I try to use c-api as this demo, it is ok. but when I try to quantize squeeze.onnx to float 16, and then inference again, it report:
I use the follow script to convert float32 model to float16:
can onnxruntime support fp16 inference? any plan?
System information
0.4
Describe the solution you'd like
load fp 16 model, input float 32 data, then get float 32 result.
Describe alternatives you've considered
how to convert float32 input to float16 for inference?
The text was updated successfully, but these errors were encountered: