Upernet Convnext Xlarge

🚀 UPerNet Model Card

This UPerNet model is designed for image segmentation tasks. It provides a straightforward way to load a trained model, understand its initialization parameters, and work with a specific dataset.

🚀 Quick Start

You can quickly start using the UPerNet model by following these steps. Click the button below to open the example in Google Colab:

Installation

First, install the required libraries:

pip install -U segmentation_models_pytorch albumentations

Inference

Then, run the inference code:

import torch
import requests
import numpy as np
import albumentations as A
import segmentation_models_pytorch as smp

from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"

# Load pretrained model and preprocessing function
checkpoint = "smp-hub/upernet-convnext-xlarge"
model = smp.from_pretrained(checkpoint).eval().to(device)
preprocessing = A.Compose.from_pretrained(checkpoint)

# Load image
url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg"
image = Image.open(requests.get(url, stream=True).raw)

# Preprocess image
np_image = np.array(image)
normalized_image = preprocessing(image=np_image)["image"]
input_tensor = torch.as_tensor(normalized_image)
input_tensor = input_tensor.permute(2, 0, 1).unsqueeze(0)  # HWC -> BCHW
input_tensor = input_tensor.to(device)

# Perform inference
with torch.no_grad():
    output_mask = model(input_tensor)

# Postprocess mask
mask = mask.argmax(1).cpu().numpy()  # argmax over predicted classes (channels dim)

✨ Features

• Easy to Use: The model can be easily loaded from a pre - trained checkpoint and used for inference.
• Flexible Initialization: You can customize the model's initialization parameters according to your needs.

📦 Installation

To install the necessary libraries for this model, run the following command:

pip install -U segmentation_models_pytorch albumentations

💻 Usage Examples

Basic Usage

The above quick - start code shows the basic usage of loading a pre - trained model, preprocessing an image, performing inference, and post - processing the output mask.

Advanced Usage

You can customize the model's initialization parameters to adapt to different tasks. Here is an example of model initialization parameters:

model_init_params = {
    "encoder_name": "tu-convnext_xlarge",
    "encoder_depth": 5,
    "encoder_weights": None,
    "decoder_channels": 512,
    "decoder_use_norm": "batchnorm",
    "in_channels": 3,
    "classes": 150,
    "activation": None,
    "upsampling": 4,
    "aux_params": None
}

📚 Documentation

Model Init Parameters

The following are the parameters for initializing the model:

model_init_params = {
    "encoder_name": "tu-convnext_xlarge",
    "encoder_depth": 5,
    "encoder_weights": None,
    "decoder_channels": 512,
    "decoder_use_norm": "batchnorm",
    "in_channels": 3,
    "classes": 150,
    "activation": None,
    "upsampling": 4,
    "aux_params": None
}

Dataset

The model uses the ADE20K dataset.

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.