search

LTH14 / mage

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
MIT License
507 stars 26 forks source link

Error While Running the Pre-Train Command on a local Machine #40

Closed SaadH-077 closed 1 year ago

SaadH-077 commented 1 year ago

Hello Mage-Error , I've been trying to run the pre-train command on my local machine (CPU) , but I keep getting this error and eventually the socket times out:

[W ..\torch\csrc\distributed\c10d\socket.cpp:601] [c10d] The client socket has failed to connect to [DESKTOP-VS9LK6T]:29500 (system error: 10049 - The requested address is not valid in its context.).

I think the issue is with the line: --master_addr="192.168.56.1" --master_port=12344 \ I have been using my local ipv4 address but still getting issues as I'm unable to connect to the server. Any guidance on how to run this code would be appreciated. Thank You.

LTH14 commented 1 year ago

Hi, thanks for your interest! Unfortunately our code currently only supports GPU training.