Convnextv2 Atto.fcmae

🚀 convnextv2_atto.fcmae模型卡

ConvNeXt-V2是一個自監督特徵表示模型，使用全卷積掩碼自編碼器框架（FCMAE）進行預訓練。該模型沒有預訓練的頭部，僅適用於微調或特徵提取。

🚀 快速開始

本模型可用於圖像分類、特徵圖提取和圖像嵌入等任務。以下是詳細的使用示例。

✨ 主要特性

• 基於ConvNeXt-V2架構，通過自監督學習進行預訓練。
• 適用於圖像分類和特徵提取任務。
• 模型參數少，計算量小，適合資源受限的場景。

📦 安裝指南

若要使用本模型，需安裝timm庫，可使用以下命令進行安裝：

pip install timm

💻 使用示例

基礎用法

圖像分類

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('convnextv2_atto.fcmae', 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)

特徵圖提取

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(
    'convnextv2_atto.fcmae',
    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, 40, 56, 56])
    #  torch.Size([1, 80, 28, 28])
    #  torch.Size([1, 160, 14, 14])
    #  torch.Size([1, 320, 7, 7])

    print(o.shape)

圖像嵌入

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(
    'convnextv2_atto.fcmae',
    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, 320, 7, 7) shaped tensor

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

📚 詳細文檔

模型詳情

模型比較

可在timm 模型結果中查看本模型的數據集和運行時指標。所有計時數據均來自在RTX 3090上使用AMP的PyTorch 1.13的急切模型。

🔧 技術細節

本模型基於ConvNeXt-V2架構，使用全卷積掩碼自編碼器框架（FCMAE）進行預訓練。FCMAE框架通過掩碼自編碼器的方式學習圖像的特徵表示，能夠在無監督的情況下學習到圖像的高級語義信息。

📄 許可證

本模型採用CC BY-NC 4.0許可證。

引用

@article{Woo2023ConvNeXtV2,
  title={ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders},
  author={Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon and Saining Xie},
  year={2023},
  journal={arXiv preprint arXiv:2301.00808},
}

@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}}
}