Instructions to use tue-mps/ade20k_semantic_eomt_large_512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tue-mps/ade20k_semantic_eomt_large_512 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="tue-mps/ade20k_semantic_eomt_large_512")# Load model directly from transformers import AutoImageProcessor, EomtForUniversalSegmentation processor = AutoImageProcessor.from_pretrained("tue-mps/ade20k_semantic_eomt_large_512") model = EomtForUniversalSegmentation.from_pretrained("tue-mps/ade20k_semantic_eomt_large_512", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Not working
#3
by Mohamedfarag96 - opened
Hi
I am trying to use the code provided here for importing the model, but it is not working
Hey @Mohamedfarag96 , Are you installing the transformers from main as the model is not yet in a transformers pypi package yet (We should get it in next release). Do refer this inference tutorial: https://colab.research.google.com/drive/1XSQgAS0uWp4wrEJgyTy7dXEZckdTZdJf?usp=sharing#scrollTo=MkoUL5r_GjtF
Ah now it is working
put I am facing some difficulties with the training pipeline
I have already made the pipeline for MF and M2F
put I guess it would be different for this model
As I am using the hugging face pipeline, not the main one from the authors