darknetaa53.c2ns_in1k模型卡片

一种用于DarkNet图像分类的模型。在timm中使用ImageNet-1k数据集进行训练，使用下面描述的模板进行训练。

训练详情:

• 基于没有重复增强和更强的mixup的 ResNet Strikes Back 个C级别的配方
• 使用SGD（具有Nesterov）优化器和AGC（自适应梯度裁剪）
• 此ns变体的配方中未使用随机深度
• 采用余弦学习率衰减和预热

模型细节

• 模型类型：图像分类/特征骨干
• 模型统计数据：
  • 参数数目（百万级）：36.0
  • GMACs：8.0
  • 激活数目（百万级）：12.4
  • 图像大小：训练=256 x 256，测试=288 x 288
• 论文引用：
  • YOLOv3：一种渐进式改进： https://arxiv.org/abs/1804.02767
  • ResNet再次发威：timm中的改进训练流程： https://arxiv.org/abs/2110.00476
• 原始版本： https://github.com/huggingface/pytorch-image-models

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('darknetaa53.c2ns_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(
    'darknetaa53.c2ns_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, 32, 256, 256])
    #  torch.Size([1, 64, 128, 128])
    #  torch.Size([1, 128, 64, 64])
    #  torch.Size([1, 256, 32, 32])
    #  torch.Size([1, 512, 16, 16])
    #  torch.Size([1, 1024, 8, 8])

    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(
    'darknetaa53.c2ns_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, 1024, 8, 8) 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

@article{Redmon2018YOLOv3AI,
  title={YOLOv3: An Incremental Improvement},
  author={Joseph Redmon and Ali Farhadi},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.02767}
}

@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}}
}