Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Trained Model and Code? #2

Open
ysong10 opened this issue Sep 28, 2023 · 4 comments
Open

Trained Model and Code? #2

ysong10 opened this issue Sep 28, 2023 · 4 comments

Comments

@ysong10
Copy link

ysong10 commented Sep 28, 2023

Hi,
Thank you for providing the code corresponding to the paper; the outcomes are noteworthy, especially when compared with TinEye. I have observed that there is some code missing, as highlighted in a separate issue. Could you also share the trained model and the associated code, please?

@morawi
Copy link
Owner

morawi commented Sep 29, 2023

Hi

the code in here is outdated .... there's the another repo that has even more functionalities ...
it has a better color counting methods which I took some time to discover ... as well as some other functions ... have a look and let me know what you think ....
FashionColor

@ysong10
Copy link
Author

ysong10 commented Oct 1, 2023

Hi,
Thank you so much for sharing the code! I will check it out. I have another thing to clarify with you, so from the paper, it seems you fine-tuned one pretrained masked-rcnn model using that 50k modanet dataset, is this correct?

@dshaw002
Copy link

dshaw002 commented Apr 14, 2024

@ysong10 I've found a pre-trained model here: https://github.com/cad0p/maskrcnn-modanet/blob/38551c4ae684000a4c6f31c46c6912db5fdbe2c3/maskrcnn_modanet/download.sh#L141

EDIT: Looks like you can train model using get_prediction_method from his custom segmentation functions: https://github.com/morawi/FashionColor/blob/174ea1d83af48a4afc48e564b3440e42ef44de40/draw_image.py#L28

You can see something more detailed in one of the pytorch documents he references: https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

From there, I'm assuming you can train the saved model to the pth file using pickle, etc. I'm also going through this on my own for a project and will post an article when done

@nadia886
Copy link

@ysong10 I've found a pre-trained model here: https://github.com/cad0p/maskrcnn-modanet/blob/38551c4ae684000a4c6f31c46c6912db5fdbe2c3/maskrcnn_modanet/download.sh#L141

EDIT: Looks like you can train model using get_prediction_method from his custom segmentation functions: https://github.com/morawi/FashionColor/blob/174ea1d83af48a4afc48e564b3440e42ef44de40/draw_image.py#L28

You can see something more detailed in one of the pytorch documents he references: https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

From there, I'm assuming you can train the saved model to the pth file using pickle, etc. I'm also going through this on my own for a project and will post an article when done

Hi, do you know how can I use the trained model in google colab?

Thanks for your help.

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

No branches or pull requests

4 participants