Instructions to use apple/deeplabv3-mobilevit-xx-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/deeplabv3-mobilevit-xx-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="apple/deeplabv3-mobilevit-xx-small")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, MobileViTForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("apple/deeplabv3-mobilevit-xx-small") model = MobileViTForSemanticSegmentation.from_pretrained("apple/deeplabv3-mobilevit-xx-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add TF weights
#1
by sayakpaul HF Staff - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its Pytorch counterpart.
Maximum crossload output difference=4.139e-04; Maximum crossload hidden layer difference=4.911e-04;
Maximum conversion output difference=4.139e-04; Maximum conversion hidden layer difference=4.911e-04;
CAUTION: The maximum admissible error was manually increased to 0.0005!
more information about the threshold bing crossed: https://github.com/huggingface/transformers/pull/18555#issuecomment-1229703811.
Matthijs changed pull request status to merged