regnety_1280.seer的模型卡片

一个RegNetY-128GF的特征/骨干模型。根据SEER: 在“20亿个随机互联网图像”上使用SwAV进行自监督学习进行预训练。

SEER使用SEER许可证，版权所有©Meta Platforms, Inc. license 是一种限制非商业使用和分发的许可证。

timm的RegNet实现包括其他实现中没有的一些增强功能，包括：

• 随机深度
• 梯度检查点
• 逐层LR衰减
• 配置输出步幅（扩张）
• 配置激活和规范化层
• 在RegNetV变体中使用的预激活瓶颈块选项
• 仅知道有预训练权重的RegNetZ模型定义

模型细节

• 模型类型：图像分类/特征骨干
• 模型统计数据：
  • 参数（M）：637.4
  • GMACs：127.7
  • 激活（M）：71.6
  • 图像大小：224 x 224
• 论文：
  • 在野外自我监督预训练视觉特征： https://arxiv.org/abs/2103.01988v2
  • 设计网络设计空间： https://arxiv.org/abs/2003.13678
• 原始链接： https://github.com/facebookresearch/vissl
• 预训练数据集：RandomInternetImages-2B

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('regnety_1280.seer', 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(
    'regnety_1280.seer',
    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, 528, 56, 56])
    #  torch.Size([1, 1056, 28, 28])
    #  torch.Size([1, 2904, 14, 14])
    #  torch.Size([1, 7392, 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(
    'regnety_1280.seer',
    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, 7392, 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 。

对于以下比较摘要，ra_in1k、ra3_in1k、ch_in1k、sw_*和lion_*标记的权重是在timm中训练的。

引用

@article{goyal2022vision,
  title={Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision}, 
  author={Priya Goyal and Quentin Duval and Isaac Seessel and Mathilde Caron and Ishan Misra and Levent Sagun and Armand Joulin and Piotr Bojanowski},
  year={2022},
  eprint={2202.08360},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@InProceedings{Radosavovic2020,
  title = {Designing Network Design Spaces},
  author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{'a}r},
  booktitle = {CVPR},
  year = {2020}
}

@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}}
}