Instructions to use SpotLab/MobileViT_DeepLabv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SpotLab/MobileViT_DeepLabv3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="SpotLab/MobileViT_DeepLabv3")# Load model directly from transformers import AutoImageProcessor, MobileViTForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("SpotLab/MobileViT_DeepLabv3") model = MobileViTForSemanticSegmentation.from_pretrained("SpotLab/MobileViT_DeepLabv3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| from transformers import TFMobileViTForSemanticSegmentation | |
| import tensorflow as tf | |
| if __name__ == '__main__': | |
| model = TFMobileViTForSemanticSegmentation.from_pretrained(".") | |
| converter = tf.lite.TFLiteConverter.from_keras_model(model) | |
| converter.optimizations = [tf.lite.Optimize.DEFAULT] | |
| converter.target_spec.supported_ops = [ | |
| tf.lite.OpsSet.TFLITE_BUILTINS, | |
| tf.lite.OpsSet.SELECT_TF_OPS, | |
| ] | |
| tflite_model = converter.convert() | |
| tflite_filename = "tflite_model.tflite" | |
| with open(tflite_filename, "wb") as f: | |
| f.write(tflite_model) |