hypercost

Results 21 comments of hypercost

@fabianboth Because PASCAL GPU must run with CUDA8 and cuDNN-v5, I try a nvidia-docker caffe with CUDA7.0 and cuDNN-v4 and it works. But my annother docker with CUDA7.5 and cuDNN-v5...

According to `requirements.txt`, use pytorch 0.2. 2018-02-09 2:29 GMT+08:00 wuyi1983 : > This also happened to me. My pytorch version is 0.3.0 on Windows 10. > How to fix this...

Hi, I can't run evaluation on DND dataset on one 1080Ti even with TC. By the way, when I install Tc with conda, the pytorch will downgrade to 0.3.1.

I commented out `./include/caffe/FRCNN/util/frcnn_utils.hpp:25` and it worked. ![Screenshot from 2017-11-07 17-30-38.png](https://i.loli.net/2017/11/07/5a017d656a106.png)

May you release the whole python file that defines the SegNet? It will help me a lot. Thanks.

@Ashutosh1995 Have you solved this problem?

I also observed that old version nerfstudio instant-ngp works well, but the current version does not work on the same capture. You can try 0.1.6.

latest commit also has this problem ``` 12:58:30 WARNING Vulkan: loader_scanned_icd_add: Driver /usr/lib/x86_64-linux-gnu/libvulkan_intel.so supports Vulkan 1.2, but only supports loader interface version 4. Interface version 5 or newer required to...

Waiting for pre-trained weights.