seresnext101_32x8d.ah_in1k模型卡片

一个带有Squeeze-and-Excitation通道注意力的SE-ResNeXt-B图像分类模型。

该模型具有以下特点：

• ReLU激活函数
• 单层7x7卷积池化
• 1x1卷积快捷下采样
• 分组的3x3瓶颈卷积
• Squeeze-and-Excitation通道注意力

该模型在timm中使用下面描述的模板进行了ImageNet-1k训练。

配方详情：

• 基于 ResNet Strikes Back A1配方
• LAMB优化器
• 无CutMix。比论文A1配方更强的dropout、随机深度和RandAugment
• 余弦学习率衰减与预热

模型详情

• 模型类型：图像分类/特征骨干
• 模型统计信息：
  • 参数数目（M）：93.6
  • GMACs：16.5
  • 激活（M）：31.2
  • 图像大小：训练 = 224 x 224，测试 = 288 x 288
• 论文信息：
  • ResNet strikes back: An improved training procedure in timm： https://arxiv.org/abs/2110.00476
  • Aggregated Residual Transformations for Deep Neural Networks： https://arxiv.org/abs/1611.05431
  • Deep Residual Learning for Image Recognition： https://arxiv.org/abs/1512.03385
  • Squeeze-and-Excitation Networks： https://arxiv.org/abs/1709.01507
• 原始信息： https://github.com/huggingface/pytorch-image-models

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('seresnext101_32x8d.ah_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(
    'seresnext101_32x8d.ah_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, 1024, 14, 14])
    #  torch.Size([1, 2048, 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(
    'seresnext101_32x8d.ah_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, 2048, 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中探索该模型的数据集和运行时指标 model results 。

引用

@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}
}

@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}}
}

@article{Xie2016,
  title={Aggregated Residual Transformations for Deep Neural Networks},
  author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
  journal={arXiv preprint arXiv:1611.05431},
  year={2016}
}

@article{He2015,
  author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
  title = {Deep Residual Learning for Image Recognition},
  journal = {arXiv preprint arXiv:1512.03385},
  year = {2015}
}

@inproceedings{hu2018senet,
  title={Squeeze-and-Excitation Networks},
  author={Jie Hu and Li Shen and Gang Sun},
  journal={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2018}
}