英文

maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k 模型卡片

一种特定于 timm 的 MaxViT 模型(带有基于 Swin-V2 的 MLP Log-CPB(连续的对数坐标相对位置偏差)),用于图像分类。在 ImageNet-12k(ImageNet-22k 的一个子集,包含 11821 个类别)上通过 timm 进行预训练,并由 Ross Wightman 在 ImageNet-1k 上进行微调。

ImageNet-12k 的预训练和 ImageNet-1k 的微调在 8x GPU Lambda Labs 云实例上执行。

maxxvit.py 中的模型变体

MaxxViT 包含了几种相关的模型架构,它们共享相同的结构,包括:

  • CoAtNet - 在早期阶段将 MBConv(深度可分离)卷积块与后期的自注意力转换块相结合。
  • MaxViT - 所有阶段均采用统一的块,每个块包含一个 MBConv(深度可分离)卷积块,后面是两个具有不同分区方案(窗口后跟网格)的自注意力块。
  • CoAtNeXt - timm 特定的架构,用 ConvNeXt 块替代 CoAtNet 中的 MBConv 块。所有归一化层都是 LayerNorm(没有 BatchNorm)。
  • MaxxViT - timm 特定的架构,用 ConvNeXt 块替代 MaxViT 中的 MBConv 块。所有归一化层都是 LayerNorm(没有 BatchNorm)。
  • MaxxViT-V2 - MaxxViT 的一个变体,去掉了窗口块自注意力,仅保留 ConvNeXt 块和具有更大宽度的网格注意力以进行补偿。

除了上述主要变种外,从模型到模型之间还有一些细微的变化。包含 rw 字符串的任何模型名称都是 timm 特定的配置,调整了建模以支持 PyTorch eager 使用。这些模型是在训练初始复现模型时创建的,因此存在一些变化。所有包含 tf 字符串的模型都与原始论文作者基于 Tensorflow 的模型完全匹配,其中的权重已转换为 PyTorch。这包括一些 MaxViT 模型。官方的 CoAtNet 模型从未发布过。

模型详细信息

  • 模型类型:图像分类 / 特征主干
  • 模型统计信息:
    • 参数(百万):116.1
    • GMACs:71.0
    • 激活数(百万):318.9
    • 图像大小:384 x 384
  • 论文:
  • 数据集:ImageNet-1k
  • 预训练数据集:ImageNet-12k

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('maxvit_rmlp_base_rw_384.sw_in12k_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(
    'maxvit_rmlp_base_rw_384.sw_in12k_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, 192, 192])
    #  torch.Size([1, 96, 96, 96])
    #  torch.Size([1, 192, 48, 48])
    #  torch.Size([1, 384, 24, 24])
    #  torch.Size([1, 768, 12, 12])

    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(
    'maxvit_rmlp_base_rw_384.sw_in12k_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, 768, 12, 12) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

模型比较

按 Top-1

model top1 top5 samples / sec Params (M) GMAC Act (M)
12310321 88.53 98.64 21.76 475.77 534.14 1413.22
12311321 88.32 98.54 42.53 475.32 292.78 668.76
12312321 88.20 98.53 50.87 119.88 138.02 703.99
12313321 88.04 98.40 36.42 212.33 244.75 942.15
12314321 87.98 98.56 71.75 212.03 132.55 445.84
12315321 87.92 98.54 104.71 119.65 73.80 332.90
12316321 87.81 98.37 106.55 116.14 70.97 318.95
12317321 87.47 98.37 149.49 116.09 72.98 213.74
12318321 87.39 98.31 160.80 73.88 47.69 209.43
12319321 86.89 98.02 375.86 116.14 23.15 92.64
12320321 86.64 98.02 501.03 116.09 24.20 62.77
12321321 86.60 97.92 50.75 119.88 138.02 703.99
12322321 86.57 97.89 631.88 73.87 15.09 49.22
12323321 86.52 97.88 36.04 212.33 244.75 942.15
12324321 86.49 97.90 620.58 73.88 15.18 54.78
12325321 86.29 97.80 101.09 119.65 73.80 332.90
12326321 86.23 97.69 70.56 212.03 132.55 445.84
12327321 86.10 97.76 88.63 69.13 67.26 383.77
12328321 85.67 97.58 144.25 31.05 33.49 257.59
12329321 85.54 97.46 188.35 69.02 35.87 183.65
12330321 85.11 97.38 293.46 30.98 17.53 123.42
12331321 84.93 96.97 247.71 211.79 43.68 127.35
12332321 84.90 96.96 1025.45 41.72 8.11 40.13
12333321 84.85 96.99 358.25 119.47 24.04 95.01
12334321 84.63 97.06 575.53 66.01 14.67 58.38
12335321 84.61 96.74 625.81 73.88 15.18 54.78
12336321 84.49 96.76 693.82 64.90 10.75 49.30
12337321 84.43 96.83 647.96 68.93 11.66 53.17
12338321 84.23 96.78 807.21 29.15 6.77 46.92
12339321 83.62 96.38 989.59 41.72 8.04 34.60
12340321 83.50 96.50 1100.53 29.06 5.11 33.11
12341321 83.41 96.59 1004.94 30.92 5.60 35.78
12342321 83.36 96.45 1093.03 41.69 7.85 35.47
12343321 83.11 96.33 1276.88 23.70 6.26 23.05
12344321 83.03 96.34 1341.24 16.78 4.37 26.05
12345321 82.96 96.26 1283.24 15.50 4.47 31.92
12346321 82.93 96.23 1218.17 15.45 4.46 30.28
12347321 82.39 96.19 1600.14 27.44 4.67 22.04
12348321 82.39 95.84 1831.21 27.44 4.43 18.73
12349321 82.05 95.87 2109.09 15.15 2.62 20.34
12350321 81.95 95.92 2525.52 14.70 2.47 12.80
12351321 81.70 95.64 2344.52 15.14 2.41 15.41
12352321 80.53 95.21 1594.71 7.52 1.85 24.86

按吞吐量(样本 / 秒)

model top1 top5 samples / sec Params (M) GMAC Act (M)
12350321 81.95 95.92 2525.52 14.70 2.47 12.80
12351321 81.70 95.64 2344.52 15.14 2.41 15.41
12349321 82.05 95.87 2109.09 15.15 2.62 20.34
12348321 82.39 95.84 1831.21 27.44 4.43 18.73
12347321 82.39 96.19 1600.14 27.44 4.67 22.04
12352321 80.53 95.21 1594.71 7.52 1.85 24.86
12344321 83.03 96.34 1341.24 16.78 4.37 26.05
12345321 82.96 96.26 1283.24 15.50 4.47 31.92
12343321 83.11 96.33 1276.88 23.70 6.26 23.05
12346321 82.93 96.23 1218.17 15.45 4.46 30.28
12340321 83.50 96.50 1100.53 29.06 5.11 33.11
12342321 83.36 96.45 1093.03 41.69 7.85 35.47
12332321 84.90 96.96 1025.45 41.72 8.11 40.13
12341321 83.41 96.59 1004.94 30.92 5.60 35.78
12339321 83.62 96.38 989.59 41.72 8.04 34.60
12338321 84.23 96.78 807.21 29.15 6.77 46.92
12336321 84.49 96.76 693.82 64.90 10.75 49.30
12337321 84.43 96.83 647.96 68.93 11.66 53.17
12322321 86.57 97.89 631.88 73.87 15.09 49.22
12335321 84.61 96.74 625.81 73.88 15.18 54.78
12324321 86.49 97.90 620.58 73.88 15.18 54.78
12334321 84.63 97.06 575.53 66.01 14.67 58.38
12320321 86.64 98.02 501.03 116.09 24.20 62.77
12319321 86.89 98.02 375.86 116.14 23.15 92.64
12333321 84.85 96.99 358.25 119.47 24.04 95.01
12330321 85.11 97.38 293.46 30.98 17.53 123.42
12331321 84.93 96.97 247.71 211.79 43.68 127.35
12329321 85.54 97.46 188.35 69.02 35.87 183.65
12318321 87.39 98.31 160.80 73.88 47.69 209.43
12317321 87.47 98.37 149.49 116.09 72.98 213.74
12328321 85.67 97.58 144.25 31.05 33.49 257.59
12316321 87.81 98.37 106.55 116.14 70.97 318.95
12315321 87.92 98.54 104.71 119.65 73.80 332.90
12325321 86.29 97.80 101.09 119.65 73.80 332.90
12327321 86.10 97.76 88.63 69.13 67.26 383.77
12314321 87.98 98.56 71.75 212.03 132.55 445.84
12326321 86.23 97.69 70.56 212.03 132.55 445.84
12312321 88.20 98.53 50.87 119.88 138.02 703.99
12321321 86.60 97.92 50.75 119.88 138.02 703.99
12311321 88.32 98.54 42.53 475.32 292.78 668.76
12313321 88.04 98.40 36.42 212.33 244.75 942.15
12323321 86.52 97.88 36.04 212.33 244.75 942.15
12310321 88.53 98.64 21.76 475.77 534.14 1413.22

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}}
}
@article{tu2022maxvit,
  title={MaxViT: Multi-Axis Vision Transformer},
  author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
  journal={ECCV},
  year={2022},
}        
@article{dai2021coatnet,
  title={CoAtNet: Marrying Convolution and Attention for All Data Sizes},
  author={Dai, Zihang and Liu, Hanxiao and Le, Quoc V and Tan, Mingxing},
  journal={arXiv preprint arXiv:2106.04803},
  year={2021}
}