the performance of onxx fp16 seems to be even worse than that of onnx fp32

[lierer007]

src/transformer_deploy/convert.py

model_path = onnx_model_path if is_fp16 else optim_model_paths[0]

Maybe there is something wrong with this line of code, which causes the experimental results to appear that the performance of onnx fp16 is even worse than that of onnx fp32.