Skip to content

Use half precision to reduce memory usage. #74

Open
kexul wants to merge 2 commits into
hkchengrex:masterfrom
kexul:patch-1
Open

Use half precision to reduce memory usage. #74
kexul wants to merge 2 commits into
hkchengrex:masterfrom
kexul:patch-1

Conversation

@kexul

@kexul kexul commented May 21, 2024

Copy link
Copy Markdown

Hi, this is a simple trick to reduce memory usage.

kexul added 2 commits May 21, 2024 16:47
Use half precision to reduce memory usage.
Use half precision.
@huchunjun425

Copy link
Copy Markdown

Hello, it is a pleasure to read this code, but when I want to train my own dataset, I find that "python download_training_dataset.py" this line of code needs this.py file to run, but I don't see this file, should I set up my own training dataset?

@kexul

kexul commented Sep 25, 2024

Copy link
Copy Markdown
Author

Hello, it is a pleasure to read this code, but when I want to train my own dataset, I find that "python download_training_dataset.py" this line of code needs this.py file to run, but I don't see this file, should I set up my own training dataset?

Sorry, I'm not the owner of this repo and never tried to train. You may consider consulting @hkchengrex for more information.

@hkchengrex

Copy link
Copy Markdown
Owner

Hello, it is a pleasure to read this code, but when I want to train my own dataset, I find that "python download_training_dataset.py" this line of code needs this.py file to run, but I don't see this file, should I set up my own training dataset?

@huchunjun425 The script is here: https://github.com/hkchengrex/CascadePSP/blob/master/scripts/download_training_dataset.py. I am not sure what you meant by "this.py".

@huchunjun425

huchunjun425 commented Sep 29, 2024 via email

Copy link
Copy Markdown

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants