mobilenetv3 small 100.lamb in1k

提供商timm
分类image-classification
许可证apache-2.0
下载量2.2K
星标4

简介

MobileNetV3 Small 是专为端侧设备设计的轻量级图像分类模型。该版本基于 timm 库提供，并在 ImageNet-1K 上进行了优化。它通过结合硬件感知网络架构搜索（NAS）和轻量级注意力机制，在极低计算开销下维持了不错的识别精度。对于中国开发者而言，这款模型非常适合部署在 Android/iOS 移动端、嵌入式设备或对推理延迟要求极高的实时视觉应用中，是替代大型 ResNet 模型的理想选择，上手门槛低，且与 PyTorch 生态兼容良好。

核心亮点

  • 极轻量化设计，适配移动端与嵌入式设备
  • 低延迟推理，适合实时图像分类场景
  • 基于 timm 库，支持 PyTorch 快速调用
  • 兼顾能效比，大幅降低端侧计算资源压力

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("timm/mobilenetv3_small_100.lamb_in1k")
tokenizer = AutoTokenizer.from_pretrained("timm/mobilenetv3_small_100.lamb_in1k")

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：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download timm/mobilenetv3_small_100.lamb_in1k

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）

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 timm/mobilenetv3_small_100.lamb_in1k config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('timm/mobilenetv3_small_100.lamb_in1k')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/timm/mobilenetv3_small_100.lamb_in1k

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/mobilenetv3_small_100.lamb_in1k

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

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('timm/mobilenetv3_small_100.lamb_in1k')
tokenizer = AutoTokenizer.from_pretrained('timm/mobilenetv3_small_100.lamb_in1k')

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：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model timm/mobilenetv3_small_100.lamb_in1k

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）

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 timm/mobilenetv3_small_100.lamb_in1k README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('timm/mobilenetv3_small_100.lamb_in1k')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/timm/mobilenetv3_small_100.lamb_in1k.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/mobilenetv3_small_100.lamb_in1k.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

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

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'timm/mobilenetv3_small_100.lamb_in1k')

完整文档

来源: HuggingFace

---
tags:

  • image-classification

  • timm

  • transformers

library_name: timm
license: apache-2.0
datasets:
  • imagenet-1k

---

Model card for mobilenetv3_small_100.lamb_in1k

A MobileNet-v3 image classification model. Trained on ImageNet-1k in timm using recipe template described below.

Recipe details:
* A LAMB optimizer based recipe that is similar to ResNet Strikes Back A2 but 50% longer with EMA weight averaging, no CutMix
* Step (exponential decay w/ staircase) LR schedule with warmup

Model Details

  • Model Type: Image classification / feature backbone
  • Model Stats:
- Params (M): 2.5 - GMACs: 0.1 - Activations (M): 1.4 - Image size: 224 x 224
  • Papers:
- Searching for MobileNetV3: https://arxiv.org/abs/1905.02244
  • Dataset: ImageNet-1k
  • Original: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model('mobilenetv3_small_100.lamb_in1k', pretrained=True)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1


top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Feature Map Extraction

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model(
    'mobilenetv3_small_100.lamb_in1k',
    pretrained=True,
    features_only=True,
)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1


for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 16, 112, 112])
    #  torch.Size([1, 16, 56, 56])
    #  torch.Size([1, 24, 28, 28])
    #  torch.Size([1, 48, 14, 14])
    #  torch.Size([1, 576, 7, 7])


print(o.shape)

Image Embeddings

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model(
    'mobilenetv3_small_100.lamb_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor


or equivalently (without needing to set num_classes=0)


output = model.forward_features(transforms(img).unsqueeze(0))
output is unpooled, a (1, 576, 7, 7) shaped tensor


output = model.forward_head(output, pre_logits=True)
output is a (1, num_features) shaped tensor

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

bibtex
@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
bibtex
@inproceedings{howard2019searching,
  title={Searching for mobilenetv3},
  author={Howard, Andrew and Sandler, Mark and Chu, Grace and Chen, Liang-Chieh and Chen, Bo and Tan, Mingxing and Wang, Weijun and Zhu, Yukun and Pang, Ruoming and Vasudevan, Vijay and others},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  pages={1314--1324},
  year={2019}
}
查看官方来源