search

nerdyrodent / VQGAN-CLIP

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
Other
2.59k stars 427 forks source link

No matching distribution found for torch==1.9.0+cu111 #75

Closed OfficialCRUGG closed 2 years ago

OfficialCRUGG commented 2 years ago

Hey there! I'm trying to run this on an M1 MacBook Pro.

I installed Anaconda and created and activated the environment like in the Readme. Then I tried to run the first pip command, but I get an error: image

Any clue what's causing this and how to fix it?

very-meanly commented 2 years ago

I was able to get around this by just removing the +cu111 part.

OfficialCRUGG commented 2 years ago

I think I tried that, but I only removed it from 1.9.0, did you also remove it from 0.10.0? @very-meanly

very-meanly commented 2 years ago

I think I tried that, but I only removed it from 1.9.0, did you also remove it from 0.10.0? @very-meanly

Yes.

psx2 commented 2 years ago

hey, did you manage to get

I think I tried that, but I only removed it from 1.9.0, did you also remove it from 0.10.0? @very-meanly

hey, did you manage to get it working? What is the performance like on a M1 Mac?

nerdyrodent commented 2 years ago

Information for installing Pytorch is available at https://pytorch.org/get-started/locally/ Note that only Nvidia CUDA has been tested.

gselsidi commented 2 years ago

I left all the specific versions out, and just ran conda install pytorch

gselsidi commented 2 years ago

hey, did you manage to get

I think I tried that, but I only removed it from 1.9.0, did you also remove it from 0.10.0? @very-meanly

hey, did you manage to get it working? What is the performance like on a M1 Mac?

running the basic apple in a bowl and performance is brutal, as pytroch doesn't support the M1's built in GPU yet, it's been running for over 30m and nothing I expect it to be fairly useless running just on the cpu.

Lola58 commented 1 year ago

I successfully solved the problem after I downgraded my python version from 3.10 to 3.8