DPT

🚀 DPT Model Card

This is a model card for the DPT model used in image segmentation, providing details on model loading, initialization parameters, and more.

🚀 Quick Start

Load trained model

import segmentation_models_pytorch as smp

model = smp.from_pretrained("<save-directory-or-this-repo>")

✨ Features

This model is related to image segmentation and has the following features:

• It uses the segmentation-models-pytorch library.
• It can be initialized with specific parameters for different segmentation tasks.

📦 Installation

No installation steps are provided in the original README, so this section is skipped.

💻 Usage Examples

Basic Usage

import segmentation_models_pytorch as smp

model = smp.from_pretrained("<save-directory-or-this-repo>")

Advanced Usage

# Initialize the model with custom parameters
model_init_params = {
    "encoder_name": "tu-vit_large_patch16_384",
    "encoder_depth": 4,
    "encoder_weights": None,
    "feature_dim": 256,
    "in_channels": 3,
    "classes": 150,
    "activation": None,
    "aux_params": None,
    "output_stride": None
}

📚 Documentation

Model init parameters

model_init_params = {
    "encoder_name": "tu-vit_large_patch16_384",
    "encoder_depth": 4,
    "encoder_weights": None,
    "feature_dim": 256,
    "in_channels": 3,
    "classes": 150,
    "activation": None,
    "aux_params": None,
    "output_stride": None
}

More Information

• Library: https://github.com/qubvel/segmentation_models.pytorch
• Docs: https://smp.readthedocs.io/en/latest/

This model has been pushed to the Hub using the PytorchModelHubMixin

📄 License

This project is licensed under the MIT license.