hardcorenas_a.miil_green_in1k 模型卡片

一种采用 HardCoReNAS 框架进行图像分类的模型。使用作者的“绿色”训练配方在 ImageNet-1k 数据集上进行训练。

模型详情

• 模型类型：图像分类 / 特征骨干
• 模型统计：
  • 参数数量（百万）：5.3
  • GMACs：0.2
  • 激活数量（百万）：4.4
  • 图像大小：224 x 224
• 论文：
  • HardCoRe-NAS: 硬约束可微分神经结构搜索： https://arxiv.org/abs/2102.11646
• 数据集：ImageNet-1k
• 原始论文： https://github.com/Alibaba-MIIL/HardCoReNAS

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('hardcorenas_a.miil_green_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(
    'hardcorenas_a.miil_green_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, 16, 112, 112])
    #  torch.Size([1, 24, 56, 56])
    #  torch.Size([1, 40, 28, 28])
    #  torch.Size([1, 112, 14, 14])
    #  torch.Size([1, 960, 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(
    'hardcorenas_a.miil_green_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, 960, 7, 7) shaped tensor

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

引用

@misc{nayman2021hardcorenas,
  title={HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search},
  author={Niv Nayman and Yonathan Aflalo and Asaf Noy and Lihi Zelnik-Manor},
  year={2021},
  eprint={https://arxiv.org/abs/2102.11646},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}