Upernet Swin Tiny

🚀 UPerNet Model Card

This is a model card for the UPerNet model in the field of image segmentation, providing detailed information on model loading, initialization parameters, and the associated dataset.

🚀 Quick Start

You can start using the UPerNet model by following these steps:

1. Install the necessary libraries.
2. Run inference on a sample image.

Click the button below to open the notebook in Google Colab:

📦 Installation

Install the required packages using the following command:

pip install -U segmentation_models_pytorch albumentations

💻 Usage Examples

Basic Usage

Here is a basic example of running inference with the pre - trained UPerNet model:

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-tiny"
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)

🔧 Technical Details

Model Init Parameters

The following are the parameters used to initialize the model:

model_init_params = {
    "encoder_name": "tu-swin_tiny_patch4_window7_224",
    "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,
    "img_size": 512
}

Dataset

The model uses the ADE20K dataset.

📚 Documentation

• 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.