repvgg_b1g4.rvgg_in1k模型卡片

一个RepVGG图像分类模型。由论文作者在ImageNet-1k上进行训练。

此模型架构是使用timm的灵活 BYOBNet (Bring-Your-Own-Blocks Network) 实现的。

BYOBNet允许对以下内容进行配置：

• 块/阶段布局
• 主干布局
• 输出步幅（扩张）
• 激活和规范化层
• 通道和空间/自注意层

... 同时还包括timm中许多其他架构的特性，包括：

• 随机深度
• 梯度检查点
• 分层学习率衰减
• 每个阶段的特征提取

模型细节

• 模型类型：图像分类/特征骨干
• 模型统计信息：
  • 参数（M）：40.0
  • GMACs：8.1
  • 激活值（M）：10.6
  • 图像大小：224 x 224
• 论文：
  • RepVGG：Making VGG-style ConvNets Great Again： https://arxiv.org/abs/2101.03697
• 数据集：ImageNet-1k
• 原始来源： https://github.com/DingXiaoH/RepVGG

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('repvgg_b1g4.rvgg_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(
    'repvgg_b1g4.rvgg_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, 128, 56, 56])
    #  torch.Size([1, 256, 28, 28])
    #  torch.Size([1, 512, 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(
    'repvgg_b1g4.rvgg_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 model results 中探索此模型的数据集和运行时指标。

引用

@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}}
}

@inproceedings{ding2021repvgg,
  title={Repvgg: Making vgg-style convnets great again},
  author={Ding, Xiaohan and Zhang, Xiangyu and Ma, Ningning and Han, Jungong and Ding, Guiguang and Sun, Jian},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={13733--13742},
  year={2021}
}