search

lucidrains / deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
MIT License
4.37k stars 327 forks source link

Can't run #68

Closed 24mjihad closed 3 years ago

24mjihad commented 3 years ago

I have installed the pip and installed CUDA but when I run this happens, any idea on what's the problem. I'm new to coding so I have no idea.

(base) PS C:\Users\jihad> imagine "a house in the forest" Traceback (most recent call last): File "c:\users\jihad\anaconda3\lib\runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "c:\users\jihad\anaconda3\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "C:\Users\jihad\anaconda3\Scripts\imagine.exe__main__.py", line 4, in File "c:\users\jihad\anaconda3\lib\site-packages\deep_daze__init__.py", line 1, in from deep_daze.deep_daze import DeepDaze, Imagine File "c:\users\jihad\anaconda3\lib\site-packages\deep_daze\deep_daze.py", line 25, in assert torch.cuda.is_available(), 'CUDA must be available in order to use Deep Daze' AssertionError: CUDA must be available in order to use Deep Daze

24mjihad commented 3 years ago

I did import torch torch.cuda.is_available() and it came back false what do I do :(

bytehut commented 3 years ago

I was able to solve this issue by downloading pytorch from their site here. I used CUDA 11.1 and the error disappeared, but I'm still having trouble with Method 'forward' is not defined.

mroosen commented 3 years ago

Are you guys using a fresh (anaconda) environment?

@24mjihad which videocard do you have?

24mjihad commented 3 years ago

@bytehut I will try that, @mroosen no I don't, do you think that's the problem? I have the rtx 3060 ti

24mjihad commented 3 years ago

I install pytorch but now I get this error

(base) PS C:\Users\jihad> imagine "space mushroom" Traceback (most recent call last): File "c:\users\jihad\anaconda3\lib\runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "c:\users\jihad\anaconda3\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "C:\Users\jihad\anaconda3\Scripts\imagine.exe__main__.py", line 4, in File "c:\users\jihad\anaconda3\lib\site-packages\deep_daze__init.py", line 1, in from deep_daze.deep_daze import DeepDaze, Imagine File "c:\users\jihad\anaconda3\lib\site-packages\deep_daze\deep_daze.py", line 14, in from torch.cuda.amp import GradScaler, autocast ImportError: cannot import name 'autocast' from 'torch.cuda.amp' (c:\users\jihad\anaconda3\lib\site-packages\torch\cuda\amp\init__.py) (base) PS C:\Users\jihad>