fujingling

运行demo.py速度太慢

5

您好，我还没有开始训练自己的模型，正在用预训练的模型跑demo.py,我发现速度特别的慢，5分钟左右demo.py才能跑出结果，这个模型本来就慢吗?还是我自身的问题

OSError: [Errno 4] Interrupted system call Exception NameError: "global name 'FileNotFoundError' is not defined" in <bound method _DataLoaderIter.__del__ of <torch.utils.data.dataloader._DataLoaderIter object at 0x7f1ebbb37f50>> ignored

2

正常的跑了几个epoch以后，我总会遇到下面这个报错，每次都会遇到，哪位大神帮忙看一下！ I can run train.py for some epoch, and the loss always keep decay, but when run a while ,it always Interrupt, the following is the error informations, How can...

速度慢的问题

18

大帅您好，我发现这个模型在P40上大概要15ms才能搞定一张图片，CPU上就慢的简直不能接受，一张图推理时间2-3s。您测试时快吗？

A problem when make

8

I got a error when I make the project, who knows how can I solve it? cuda version :8.0 TensorRT :3.0.4 env: Ubantu The following is the error information: `project/tf_to_trt_image_classification-master/examples/classify_image/classify_image.cu:10:21:...

a problem about pse ImportError: libopencv_cudabgsegm.so.3.4:

6

from .adaptor import pse as cpse ImportError: libopencv_cudabgsegm.so.3.4: cannot open shared object file: No such file or directory