eca_nfnet_l2.ra3_in1k 模型卡片

ECA-NFNet-Lite（轻量级 ECA 注意力的 NFNet）图像分类模型。由 Ross Wightman 在 timm 中训练。

标准化自由网络（Normalization Free Networks）是（预激活的）类 ResNet 模型，没有任何标准化层。它们使用缩放的权重标准化，并根据信号传播分析在残差路径和非线性方面特别放置标量增益，而不是使用批标准化或替代方法。

Lightweight NFNets 是 timm 的特定变体，将 SE 和瓶颈比例从 0.5 改为 0.25（降低宽度），并在保持相同深度的同时使用更小的分组大小。使用 SiLU 激活函数代替 GELU。

此 NFNet 变体还使用了 ECA（高效通道注意力），而不是 SE（Squeeze-and-Excitation）。

模型细节

• 模型类型：图像分类 / 特征骨干
• 模型统计信息：
  • 参数数量（百万）：56.7
  • GMACs：21.0
  • 激活数量（百万）：47.4
  • 图像尺寸：训练 = 320 x 320，测试 = 384 x 384
• 论文：
  • High-Performance Large-Scale Image Recognition Without Normalization: https://arxiv.org/abs/2102.06171
  • Characterizing signal propagation to close the performance gap in unnormalized ResNets: https://arxiv.org/abs/2101.08692
• 原始论文： https://github.com/huggingface/pytorch-image-models
• 数据集： ImageNet-1k

模型用法

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('eca_nfnet_l2.ra3_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(
    'eca_nfnet_l2.ra3_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, 64, 160, 160])
    #  torch.Size([1, 256, 80, 80])
    #  torch.Size([1, 512, 40, 40])
    #  torch.Size([1, 1536, 20, 20])
    #  torch.Size([1, 3072, 10, 10])

    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(
    'eca_nfnet_l2.ra3_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, 3072, 10, 10) 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{brock2021high,
  author={Andrew Brock and Soham De and Samuel L. Smith and Karen Simonyan},
  title={High-Performance Large-Scale Image Recognition Without Normalization},
  journal={arXiv preprint arXiv:2102.06171},
  year={2021}
}

@inproceedings{brock2021characterizing,
  author={Andrew Brock and Soham De and Samuel L. Smith},
  title={Characterizing signal propagation to close the performance gap in
  unnormalized ResNets},
  booktitle={9th International Conference on Learning Representations, {ICLR}},
  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}}
}