这里面的pytorch模型如何使用bf16进行推理呢

[LY000001]

作者，你好！我使用./PaddleOCR2Pytorch/tools/infer/predict_rec.py 进行推理，我把模型和数据转换成bfloat16后报一下错误，Traceback (most recent call last):
File "./PaddleOCR2Pytorch/tools/infer/predict_rec.py", line 169, in
main(utility.parse_args())
File "./PaddleOCR2Pytorch/tools/infer/predict_rec.py", line 155, in main
rec_res, predict_time = text_recognizer(img_list)
File "./PaddleOCR2Pytorch/tools/infer/predict_rec.py", line 122, in call
prob_out = self.net(inp)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/root/PaddleOCR2Pytorch/pytorchocr/modeling/architectures/base_model.py", line 94, in forward
x = self.backbone(x)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/root/PaddleOCR2Pytorch/pytorchocr/modeling/backbones/rec_mv1_enhance.py", line 198, in forward
y = self.conv1(inputs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/root/PaddleOCR2Pytorch/pytorchocr/modeling/backbones/rec_mv1_enhance.py", line 36, in forward
y = self._conv(inputs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/opt/rh/rh-python38/root/usr/local/lib64/python3.8/site-packages/torch/nn/modules/conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: could not create a primitive descriptor for a convolution forward propagation primitive