模型卡 - convmixer_768_32.in1k

一个ConvMixer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 / 特征骨干
• 模型统计信息：
  • 参数数目（M）：21.1
  • GMACs：19.5
  • 激活数目（M）：26.0
  • 图像尺寸：224 x 224
• 论文：
  • Patches Are All You Need?： https://arxiv.org/abs/2201.09792
• 数据集：ImageNet-1k
• 原始论文： https://github.com/locuslab/convmixer

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('convmixer_768_32.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(
    'convmixer_768_32.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, 32, 32) shaped tensor

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

模型比较

在timm中探索此模型的数据集和运行时度量。 model results

引用

@article{Chen2021CrossViTCM,
  title={CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification},
  author={Chun-Fu Chen and Quanfu Fan and Rameswar Panda},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021},
  pages={347-356}
}