库名称: segmentation-models-pytorch
许可证: mit
流水线标签: 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

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-tiny"
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-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
}

数据集

数据集名称: ADE20K

更多信息

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

此模型已使用PytorchModelHubMixin推送到Hub。