tf_efficientnet_b8.ra_in1k模型卡片

一种高效网络图像分类模型。在TensorFlow中使用ImageNet-1k和随机数据增强训练，由论文作者在Ross Wightman的PyTorch中实现。

模型细节

• 模型类型：图像分类/特征骨干网络
• 模型统计信息：
  • 参数（百万）：87.4
  • GMACs：63.5
  • 激活数（百万）：442.9
  • 图像尺寸：672 x 672
• 论文：
  • EfficientNet：重新思考卷积神经网络的模型缩放： https://arxiv.org/abs/1905.11946
  • RandAugment：具有减少搜索空间的实用自动化数据增强： https://arxiv.org/abs/1909.13719v2
• 数据集：ImageNet-1k
• 原始论文： https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet

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('tf_efficientnet_b8.ra_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(
    'tf_efficientnet_b8.ra_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, 32, 336, 336])
    #  torch.Size([1, 56, 168, 168])
    #  torch.Size([1, 88, 84, 84])
    #  torch.Size([1, 248, 42, 42])
    #  torch.Size([1, 704, 21, 21])

    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(
    'tf_efficientnet_b8.ra_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, 2816, 21, 21) shaped tensor

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

模型比较

在timm中探索该模型的数据集和运行时指标： model results

引用

@inproceedings{tan2019efficientnet,
  title={Efficientnet: Rethinking model scaling for convolutional neural networks},
  author={Tan, Mingxing and Le, Quoc},
  booktitle={International conference on machine learning},
  pages={6105--6114},
  year={2019},
  organization={PMLR}
}

@article{Cubuk2019RandaugmentPA,
  title={Randaugment: Practical automated data augmentation with a reduced search space},
  author={Ekin Dogus Cubuk and Barret Zoph and Jonathon Shlens and Quoc V. Le},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2019},
  pages={3008-3017}
}

@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}}
}