tb2-sy

Results 26 comments of tb2-sy

Which tool/method you used to count flops?

just google yourself

can you provide the parameter settings for finetune on 384 from 224 of image classification?

Modify config.py

can't install by using:pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext

> cd apex python setup.py install try it Thanks,it is efficient

can't install by using:pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext

If use “python setup.py install”,it will show error when I eval?But it is Ok,when I train model. Traceback (most recent call last): File "main.py", line 347, in main(config) File "main.py",...

can't install by using:pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext

> Oh thanks, I will give it a try.

following the readme,the conda env is wrong. when i run :pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

cd apex python setup.py install try it

Colmap on linux without display and with GPU

> I solved the issue, as it were, by using The docker environment provided and running the gui locally to see the results. Could you please explain in detail how...

module 'kaolin._C.ops.spc' has no attribute 'points_to_morton_cuda'

Hello! > Hi @logan-hs , you might have a not-so-recent kaolin version installed, make sure you have the latest master, if yes, you might want to delete `kaolin/_C.so` and `build/`...

I am training indoor scene, training takes forever

> if that is the case, I have to give up. the cool demo seems only take 3 minutes to train. It claim it is 100 times fast. Hi, which...

I am training indoor scene, training takes forever

> I have the same case with the `forest1`. However, I checked the paper: ![image](https://user-images.githubusercontent.com/12138158/246707963-17b1d08b-d6b3-4c7f-a772-9ea43c2e1dfd.png) So it will take more than a day ( or 2 days ) to train....