resnext101_32x16d.fb_swsl_ig1b_ft_in1k 模型卡片

一个 ResNeXt-B 图像分类模型。

这个模型特点包括：

• ReLU 激活
• 单层 7x7 卷积和池化
• 1x1 卷积捷径下采样
• 带有分组的 3x3 瓶颈卷积

在 Instagram-1B 标签数据集上采用半弱监督学习预训练，并由论文作者在 ImageNet-1k 上进行微调。

模型细节

• 模型类型：图像分类 / 特征骨干网络
• 模型统计数据：
  • 参数（M）：194.0
  • GMACs：36.3
  • 激活值（M）：51.2
  • 图像尺寸：224 x 224
• 相关论文：
  • 百亿级半监督学习用于图像分类： https://arxiv.org/abs/1905.00546
  • 集成的残差变换用于深度神经网络： https://arxiv.org/abs/1611.05431
  • 深度残差学习用于图像识别： https://arxiv.org/abs/1512.03385
• 原始编号： https://github.com/facebookresearch/semi-supervised-ImageNet1K-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('resnext101_32x16d.fb_swsl_ig1b_ft_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(
    'resnext101_32x16d.fb_swsl_ig1b_ft_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(
    'resnext101_32x16d.fb_swsl_ig1b_ft_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

@misc{yalniz2019billionscale,
    title={Billion-scale semi-supervised learning for image classification},
    author={I. Zeki Yalniz and Hervé Jégou and Kan Chen and Manohar Paluri and Dhruv Mahajan},
    year={2019},
    eprint={1905.00546},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@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}
}

@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}}
}