mobilenetv3_large_100.ra_in1k 模型卡片

MobileNet-v3 是一种用于图像分类的模型。使用以下描述的 timm 模板在 ImageNet-1k 数据集上进行训练。

设计细节:

• 使用 RandAugment（RA）方法进行增强。从 EfficientNet RandAugment 方法中演化而来。作为 B 方法发布在 ResNet Strikes Back 文章中。
• 使用 RMSProp（TF 1.0 行为）优化器，具有 EMA 权重平均化
• 使用阶梯式指数衰减（Step LR）调度进行学习率衰减，并包含预热期

模型细节

• 模型类型：图像分类/特征主干网络
• 模型统计信息：
  • 参数数量（M）：5.5
  • GMACs：0.2
  • 激活数量（M）：4.4
  • 图像尺寸：224 x 224
• 相关论文：
  • Searching for MobileNetV3: https://arxiv.org/abs/1905.02244
  • ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
• 数据集：ImageNet-1k
• 原始文章： https://github.com/huggingface/pytorch-image-models

模型使用方法

图像分类

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_large_100.ra_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)

特征图提取

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_large_100.ra_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, 24, 56, 56])
    #  torch.Size([1, 40, 28, 28])
    #  torch.Size([1, 112, 14, 14])
    #  torch.Size([1, 960, 7, 7])

    print(o.shape)

图像嵌入

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_large_100.ra_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, 960, 7, 7) shaped tensor

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

模型比较

在 timm model results 中探索该模型的数据集和运行时指标。

引用文献

@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}
}

@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}}
}

@inproceedings{wightman2021resnet,
  title={ResNet strikes back: An improved training procedure in timm},
  author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
  booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}