库名称：segmentation-models-pytorch
许可证：mit
管道标签：image-segmentation
标签：

• model_hub_mixin
• pytorch_model_hub_mixin
• segmentation-models-pytorch
• semantic-segmentation
• pytorch
• upernet
  语言：
• python

UPerNet模型卡片

目录：

• 加载训练好的模型
• 模型初始化参数
• 数据集

加载训练好的模型

1. 安装依赖项。

pip install -U segmentation_models_pytorch albumentations  

2. 运行推理。

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"  

# 加载预训练模型和预处理函数  
checkpoint = "smp-hub/upernet-convnext-xlarge"  
model = smp.from_pretrained(checkpoint).eval().to(device)  
preprocessing = A.Compose.from_pretrained(checkpoint)  

# 加载图像  
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)  

# 预处理图像  
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)  

# 执行推理  
with torch.no_grad():  
    output_mask = model(input_tensor)  

# 后处理掩码  
mask = mask.argmax(1).cpu().numpy()  # 对预测类别（通道维度）进行argmax  

模型初始化参数

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  
}  

数据集

数据集名称：ADE20K

更多信息

• 库地址：https://github.com/qubvel/segmentation_models.pytorch
• 文档：https://smp.readthedocs.io/en/latest/

此模型已通过PytorchModelHubMixin推送到Hub。