Lunbin Zeng
Lunbin Zeng
感觉搜索二叉树深度第一个解法，不能用全局变量，要通过指针来传递res，depth
> I believe it's because you aren't installing `freqencoder` from the directory found in the repo, and rather trying to pull from online. Notice how in `scripts/install_ext.sh` the command is...
No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6'
I have the same issue like you , the possible cause may be the CUDA and pytorch is dismatched you can print this code to test it in python： ```...
Same BUG for me. Have you solved it? @x4080
https://github.com/NVlabs/tiny-cuda-nn/issues/183#issuecomment-1342828785 I solve it by use the way in this link.
> thank you both, Ill check it Hi , Have you solve it , I have the same issue like yours.
我认为应该是作者在实际调参的时候通过测试和训练发现模型预测出来的置信度过低或contain loss过高 所以调整了权重参数以获得更好的检测效果
> Hello. Thanks for sharing your code! > > I'm curious about the training dataset to evaluate "nocaps". > > I was wondering if the model(clipcap model) was trained with...
w > 我也出现了同样的问题，难道是ubuntu版本的原因 @ginogogo @Y-huange @yhr20000319 请问你们解决了吗？我也出现了同样的问题
> w > > > 我也出现了同样的问题，难道是ubuntu版本的原因 > > @ginogogo @Y-huange @yhr20000319 请问你们解决了吗？我也出现了同样的问题 已解决，思路来自https://discuss.jittor.org/t/topic/475 将jittor版本下降到1.3.6.5即可，我的版本Ubuntu22.04 Cuda11.7 python3.8