HuggingFace镜像/deit3_small_patch16_224.fb_in22k_ft_in1k
模型介绍文件和版本分析
下载使用量0

deit3_small_patch16_224.fb_in22k_ft_in1k 模型卡片

一个 DeiT-III 图像分类模型。由论文作者在 ImageNet-22k 上进行预训练,并在 ImageNet-1k 上进行微调。

模型详情

  • 模型类型: 图像分类 / 特征骨干网络
  • 模型统计:
    • 参数(M):22.1
    • GMACs:4.6
    • 激活值(M):11.9
    • 图像尺寸:224 x 224
  • 相关论文:
    • DeiT III: Revenge of the ViT: https://arxiv.org/abs/2204.07118
  • 原始来源: https://github.com/facebookresearch/deit
  • 数据集: ImageNet-1k
  • 预训练数据集: ImageNet-22k

模型使用

图像分类

import torch 
import timm
import argparse
from PIL import Image
from openmind import is_torch_npu_available

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default=None,
    )
    args = parser.parse_args()
    return args

if __name__ == "__main__":
    args = parse_args()
    model_path = args.model_name_or_path
    img_path = model_path + '/img/beignets-task-guide.png'
    img = Image.open(img_path)

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"

    model_name = 'deit3_small_patch16_224.fb_in22k_ft_in1k'
    checkpoint_path=model_path + '/pytorch_model.bin'
    model = timm.create_model(model_name, pretrained=False, checkpoint_path=checkpoint_path).to(device)
    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).to(device))  # unsqueeze single image into batch of 1
    img.close()

    top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
    print(top5_probabilities)
    print(top5_class_indices)

模型对比

在 timm 的模型结果中探索此模型的数据集和运行时指标。

引用

@article{Touvron2022DeiTIR,
  title={DeiT III: Revenge of the ViT},
  author={Hugo Touvron and Matthieu Cord and Herve Jegou},
  journal={arXiv preprint arXiv:2204.07118},
  year={2022},
}
@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}}
}