🚀 Segformer模型卡片
Segformer是一个用于图像分割的模型,借助该模型可以方便地进行图像分割任务,在语义分割领域有着重要的应用价值。
🚀 快速开始
加载预训练模型
点击下方按钮可在Colab中打开示例:

步骤如下:
- 安装所需依赖:
pip install -U segmentation_models_pytorch albumentations
- 运行推理代码:
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"
checkpoint = "smp-hub/segformer-b1-512x512-ade-160k"
model = smp.from_pretrained(checkpoint).eval().to(device)
preprocessing = A.Compose.from_pretrained(checkpoint)
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)
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)
input_tensor = input_tensor.to(device)
with torch.no_grad():
output_mask = model(input_tensor)
mask = torch.nn.functional.interpolate(
output_mask, size=(image.height, image.width), mode="bilinear", align_corners=False
)
mask = mask.argmax(1).cpu().numpy()
✨ 主要特性
模型初始化参数
model_init_params = {
"encoder_name": "mit_b1",
"encoder_depth": 5,
"encoder_weights": None,
"decoder_segmentation_channels": 256,
"in_channels": 3,
"classes": 150,
"activation": None,
"aux_params": None
}
📦 安装指南
安装所需依赖:
pip install -U segmentation_models_pytorch albumentations
💻 使用示例
基础用法
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"
checkpoint = "smp-hub/segformer-b1-512x512-ade-160k"
model = smp.from_pretrained(checkpoint).eval().to(device)
preprocessing = A.Compose.from_pretrained(checkpoint)
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)
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)
input_tensor = input_tensor.to(device)
with torch.no_grad():
output_mask = model(input_tensor)
mask = torch.nn.functional.interpolate(
output_mask, size=(image.height, image.width), mode="bilinear", align_corners=False
)
mask = mask.argmax(1).cpu().numpy()
📚 详细文档
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/
- 许可证:https://github.com/NVlabs/SegFormer/blob/master/LICENSE
此模型已使用 PytorchModelHubMixin 推送到模型中心。
📄 许可证
许可证类型:其他
详细信息:https://github.com/NVlabs/SegFormer/blob/master/LICENSE