Model card for mit_b4.

This repository contains the imagenet pre-trained weights for the mit_b4 model used as encoder in the segmentation-models-pytorch library.

Example usage:

  1. Install the library:
pip install segmentation-models-pytorch
  1. Use the encoder in your code:
import segmentation_models_pytorch as smp

model = smp.Unet("mit_b4", encoder_weights="imagenet")

References

Downloads last month
10
Safetensors
Model size
61.4M params
Tensor type
F32
·
Inference Examples
Inference API (serverless) does not yet support segmentation-models-pytorch models for this pipeline type.