coat_lite_medium_384.in1k的模型卡片

一种CoaT（Co-Scale Conv-Attentional Transformer）图像分类模型。由论文作者在ImageNet-1k上进行训练。

模型详情

• 模型类型：图像分类/特征主干
• 模型统计信息：
  • 参数（M）：44.6
  • GMACs：28.7
  • 激活层数（M）：116.7
  • 图像尺寸：384 x 384
• 论文：
  • Co-Scale Conv-Attentional Image Transformers: https://arxiv.org/abs/2104.06399
• 数据集： ImageNet-1k
• 原始版本： https://github.com/mlpc-ucsd/CoaT

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('coat_lite_medium_384.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)

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(
    'coat_lite_medium_384.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, 145, 512) shaped tensor

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

模型对比

在timm model results 中探索该模型的数据集和运行时指标。

引用

@InProceedings{Xu_2021_ICCV,
  author    = {Xu, Weijian and Xu, Yifan and Chang, Tyler and Tu, Zhuowen},
  title     = {Co-Scale Conv-Attentional Image Transformers},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  year      = {2021},
  pages     = {9981-9990}
}