segformer b0 finetuned ade 512 512
简介
核心亮点
- 轻量化架构,端侧部署推理速度极快
- 基于 ADE20K 微调,支持多种常见场景语义分割
- 兼顾全局上下文感知与局部细节还原
- Apache-2.0 协议,商业集成无压力
使用方法
# 安装 Hugging Face transformers
pip install transformers torch
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("Xenova/segformer-b0-finetuned-ade-512-512")
tokenizer = AutoTokenizer.from_pretrained("Xenova/segformer-b0-finetuned-ade-512-512")
Hugging Face 下载
我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。
操作指引:在下载前,请先通过如下命令安装 huggingface_hub:
pip install -U huggingface_hub
命令行下载
下载完整模型库
huggingface-cli download Xenova/segformer-b0-finetuned-ade-512-512
下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)
huggingface-cli download Xenova/segformer-b0-finetuned-ade-512-512 config.json --local-dir ./dir
SDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Xenova/segformer-b0-finetuned-ade-512-512')
Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://huggingface.co/Xenova/segformer-b0-finetuned-ade-512-512
如果您希望跳过 lfs 大文件下载,可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Xenova/segformer-b0-finetuned-ade-512-512
模型文件托管在 Hugging Face Hub,使用 HF CLI / SDK / Git 直接下载,不经过本站。
PyTorch / Transformers 使用
安装 Transformers
pip install -U transformers torch
模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('Xenova/segformer-b0-finetuned-ade-512-512')
tokenizer = AutoTokenizer.from_pretrained('Xenova/segformer-b0-finetuned-ade-512-512')
模型下载
我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。
操作指引:在下载前,请先通过如下命令安装 ModelScope:
pip install modelscope
命令行下载
下载完整模型库
modelscope download --model Xenova/segformer-b0-finetuned-ade-512-512
下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)
modelscope download --model Xenova/segformer-b0-finetuned-ade-512-512 README.md --local_dir ./dir
SDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Xenova/segformer-b0-finetuned-ade-512-512')
Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://www.modelscope.cn/Xenova/segformer-b0-finetuned-ade-512-512.git
如果您希望跳过 lfs 大文件下载,可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Xenova/segformer-b0-finetuned-ade-512-512.git
ModelScope 模型页直接下载模型文件;无需将模型文件放在本站服务器。
Notebook 快速开发
下载并安装 ModelScope library
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
模型加载和推理
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline('text-generation', 'Xenova/segformer-b0-finetuned-ade-512-512')
完整文档
---
base_model: nvidia/segformer-b0-finetuned-ade-512-512
library_name: transformers.js
pipeline_tag: image-segmentation
---
https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512 with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformersExample: Image segmentation with Xenova/segformer-b0-finetuned-ade-512-512.
import { pipeline } from '@huggingface/transformers';
// Create an image segmentation pipeline
const segmenter = await pipeline('image-segmentation', 'Xenova/segformer-b0-finetuned-ade-512-512');
// Segment an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/house.jpg';
const output = await segmenter(url);
console.log(output)
// [
// {
// score: null,
// label: 'wall',
// mask: RawImage { ... }
// },
// {
// score: null,
// label: 'building',
// mask: RawImage { ... }
// },
// ...
// ]
You can visualize the outputs with:
for (const l of output) {
l.mask.save(${l.label}.png);
}---
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).