CoinCheung
CoinCheung
请问这个数据集是只有5000条是训练集还有5000条是没有村注的测试集吗,我看那个链接里面说是10000条训练集,下载下来csv后发现只有5000行
我搞错连接了,请无视我....
What is the configuration of your platform? Did you modify the code? Please align the cuda/cudnn/tensorrt/pytorch/cmake version as mine listed in readme.
Did you export onnx model with the same command as in README?
I mean, did you add `--aux-mode eval` when you export onnx model?
I tried again on my platform, and it works as expected. Maybe you should align your platform configuration as mine, especially the cuda/cudnn version.
I use pytorch3.8 from miniconda and pytorch1.11.0(cuda11).
What is your platform like and your pytorch version?
If you fix batchsize=2, maybe you do not need to use dynamic batch.
What are the steps to reproduce this error?