lcnet_100.ra2_in1k模型卡片

一种LCNet图像分类模型。使用下面描述的配方模板在timm中对ImageNet-1k进行训练。

配方细节:

• RandAugment RA2配方。灵感来自于EfficientNet RandAugment配方，并在 ResNet Strikes Back 中发布为B配方。
• RMSProp（TF 1.0行为）优化器，EMA权重平均。
• Step（指数衰减，带阶梯函数）学习速率计划与预热。

模型细节

• 模型类型：图像分类/特征骨干
• 模型统计信息：
  • 参数（M）：3.0
  • GMACs：0.2
  • 激活函数（M）：2.5
  • 图像大小：224 x 224
• 论文：
  • PP-LCNet：一种轻量级CPU卷积神经网络： https://arxiv.org/abs/2109.15099
  • ResNet反击：timm中的改进训练过程： https://arxiv.org/abs/2110.00476
• 数据集：ImageNet-1k
• 原始作者： https://github.com/huggingface/pytorch-image-models

模型使用

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('lcnet_100.ra2_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(
    'lcnet_100.ra2_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, 32, 112, 112])
    #  torch.Size([1, 64, 56, 56])
    #  torch.Size([1, 128, 28, 28])
    #  torch.Size([1, 256, 14, 14])
    #  torch.Size([1, 512, 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(
    'lcnet_100.ra2_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, 512, 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中探索此模型的数据集和运行时指标 model results 。

引用

@article{cui2021pp,
  title={PP-LCNet: A lightweight CPU convolutional neural network},
  author={Cui, Cheng and Gao, Tingquan and Wei, Shengyu and Du, Yuning and Guo, Ruoyu and Dong, Shuilong and Lu, Bin and Zhou, Ying and Lv, Xueying and Liu, Qiwen and others},
  journal={arXiv preprint arXiv:2109.15099},
  year={2021}
}

@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}
}