You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am currently using the SAM2 model from the DJL ModelZoo for inference purposes. However, I have encountered a couple of limitations that I would like to request your support in resolving:
ONNX Model Format: Currently, the SAM2 model is only available in the PyTorch (.pt) format. For broader compatibility and ease of integration with other frameworks, I would like to request that an ONNX (.onnx) format version of the SAM2 model be added to the ModelZoo.
Classification Output and Synset File: It appears that the SAM2 model's inference results do not provide classification outputs. To facilitate classification tasks, could you please provide a synset.txt file or any relevant label mapping file for this model, so that users can easily interpret the classification results?
These features would greatly enhance the usability and flexibility of the SAM2 model in a variety of projects.
Thank you for your work and consideration!
The text was updated successfully, but these errors were encountered:
Description
Hello DJL Team,
I am currently using the SAM2 model from the DJL ModelZoo for inference purposes. However, I have encountered a couple of limitations that I would like to request your support in resolving:
ONNX Model Format: Currently, the SAM2 model is only available in the PyTorch (.pt) format. For broader compatibility and ease of integration with other frameworks, I would like to request that an ONNX (.onnx) format version of the SAM2 model be added to the ModelZoo.
Classification Output and Synset File: It appears that the SAM2 model's inference results do not provide classification outputs. To facilitate classification tasks, could you please provide a synset.txt file or any relevant label mapping file for this model, so that users can easily interpret the classification results?
These features would greatly enhance the usability and flexibility of the SAM2 model in a variety of projects.
Thank you for your work and consideration!
The text was updated successfully, but these errors were encountered: