MobileNet v3
MobileNetV3 是一款专为移动手机 CPU 设计的卷积神经网络。 网络设计包括使用 硬 sigmoid 激活 和 挤压和激励 模块在 MBConv 块 中。
如何在图像上使用此模型？
加载预训练模型
>>> import timm
>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True)
>>> model.eval()加载并预处理图像
>>> import urllib
>>> from PIL import Image
>>> from timm.data import resolve_data_config
>>> from timm.data.transforms_factory import create_transform
>>> config = resolve_data_config({}, model=model)
>>> transform = create_transform(**config)
>>> url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
>>> urllib.request.urlretrieve(url, filename)
>>> img = Image.open(filename).convert('RGB')
>>> tensor = transform(img).unsqueeze(0) # transform and add batch dimension获取模型预测
>>> import torch
>>> with torch.no_grad():
... out = model(tensor)
>>> probabilities = torch.nn.functional.softmax(out[0], dim=0)
>>> print(probabilities.shape)
>>> # prints: torch.Size([1000])获取前 5 个预测类名
>>> # Get imagenet class mappings
>>> url, filename = ("https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt", "imagenet_classes.txt")
>>> urllib.request.urlretrieve(url, filename)
>>> with open("imagenet_classes.txt", "r") as f:
... categories = [s.strip() for s in f.readlines()]
>>> # Print top categories per image
>>> top5_prob, top5_catid = torch.topk(probabilities, 5)
>>> for i in range(top5_prob.size(0)):
... print(categories[top5_catid[i]], top5_prob[i].item())
>>> # prints class names and probabilities like:
>>> # [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]将模型名称替换为您要使用的变体，例如 mobilenetv3_large_100。 您可以在此页面顶部的模型摘要中找到 ID。
要使用此模型提取图像特征，请按照 timm 特征提取示例 操作，只需更改要使用的模型名称即可。
如何微调此模型？
您可以通过更改分类器（最后一层）来微调任何预训练模型。
>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)要针对您自己的数据集进行微调，您必须编写一个训练循环或调整 timm 的训练脚本 以使用您的数据集。
如何训练此模型？
您可以按照 timm 食谱脚本 从头开始训练新的模型。
引用
@article{DBLP:journals/corr/abs-1905-02244,
author = {Andrew Howard and
Mark Sandler and
Grace Chu and
Liang{-}Chieh Chen and
Bo Chen and
Mingxing Tan and
Weijun Wang and
Yukun Zhu and
Ruoming Pang and
Vijay Vasudevan and
Quoc V. Le and
Hartwig Adam},
title = {Searching for MobileNetV3},
journal = {CoRR},
volume = {abs/1905.02244},
year = {2019},
url = {http://arxiv.org/abs/1905.02244},
archivePrefix = {arXiv},
eprint = {1905.02244},
timestamp = {Tue, 12 Jan 2021 15:30:06 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-02244.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}