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

add test for input_boxes #1141

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

sabman
Copy link

@sabman sabman commented Jan 12, 2025

The model should in theory support input_boxes as per this issue: https://huggingface.co/Xenova/slimsam-77-uniform/discussions/2#65c022977c6ad1994b893a8d but there's not test or example to verify this. I also couldn't get the model to accept the input_boxes on the main branch. Getting error:

Error: An error occurred during model execution: "Missing the following inputs: input_points, input_labels.

The model should in theory support input_boxes as per this issue: https://huggingface.co/Xenova/slimsam-77-uniform/discussions/2#65c022977c6ad1994b893a8d but there's not test or example to verify this.
@mhassanch
Copy link

mhassanch commented Jan 12, 2025

I checked optimum package and it seems that input_boxes is missing as input in SamOnnxConfig https://github.com/huggingface/optimum/blob/adcae3841ac638aa911e6a185d3f1617e58495f8/optimum/exporters/onnx/model_configs.py#L2408

Also there is no test available with input_boxes as a input in transformer.js https://github.com/huggingface/transformers.js/blob/1130961ac26766ba4a0f5af2640925f4f39b9974/tests/models/sam/test_modeling_sam.js

But it can be seen that SamImageProcessor is using input_boxes to process image.

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.

2 participants