nest_small_jx.goog_in1k 模型卡片

一个 NesT 图像分类模型。由论文作者在 JAX 上使用 ImageNet-1k 进行训练。由 Alexander Soare 移植到 PyTorch。

模型详情

• 模型类型：图像分类/特征主干
• 模型统计信息：
  • 参数量 (M)：38.4
  • GMACs：10.4
  • 激活数量 (M)：40.0
  • 图像尺寸：224 x 224
• 相关论文：
  • Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding: https://arxiv.org/abs/2105.12723
• 数据集：ImageNet-1k
• 原始论文： https://github.com/google-research/nested-transformer

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('nest_small_jx.goog_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(
    'nest_small_jx.goog_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, 96, 56, 56])
    #  torch.Size([1, 192, 28, 28])
    #  torch.Size([1, 384, 14, 14])

    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(
    'nest_small_jx.goog_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, 384, 14, 14) 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指标 model results 。

引用

@inproceedings{zhang2021aggregating,
  title={Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding},
  author={Zizhao Zhang and Han Zhang and Long Zhao and Ting Chen and and Sercan Ö. Arık and Tomas Pfister},
  booktitle={AAAI Conference on Artificial Intelligence (AAAI)},
  year={2022}
}