eca_nfnet_l0.ra2_in1k的模型卡片

一种ECA-NFNet-Lite（带有ECA注意力的轻量级NFNet）图像分类模型。由Ross Wightman在timm中训练。

无标准化网络是（预激活）ResNet-like模型，没有任何标准化层。它们使用了缩放的权重标准化，以及基于信号传播分析的在残差路径和非线性函数中特定位置的标量增益，而不是使用批标准化或替代方法。

轻量级NFNets是timm中的特定变体，将SE和瓶颈比从0.5 -> 0.25（减少宽度）并使用较小的组大小，同时保持相同的深度。使用SiLU激活代替GELU。

此NFNet变种还使用ECA（Efficient Channel Attention）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：
  • 参数（M）：24.1
  • GMACs：4.4
  • 激活值（M）：10.5
  • 图像尺寸：训练=224 x 224，测试=288 x 288
• 论文：
  • 无标准化的高性能大规模图像识别： https://arxiv.org/abs/2102.06171
  • 通过信号传播表征关闭未标准化ResNet性能差距： https://arxiv.org/abs/2101.08692
• 原始论文： https://github.com/huggingface/pytorch-image-models
• 数据集：ImageNet-1k

模型用途

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_l0.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(
    'eca_nfnet_l0.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, 64, 112, 112])
    #  torch.Size([1, 256, 56, 56])
    #  torch.Size([1, 512, 28, 28])
    #  torch.Size([1, 1536, 14, 14])
    #  torch.Size([1, 2304, 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(
    'eca_nfnet_l0.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, 2304, 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{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}}
}