Rdnet Tiny.nv In1k

🚀 rdnet_tiny.nv_in1k 模型卡片

RDNet 是一个图像分类模型，在 ImageNet-1k 数据集上进行训练，使用了原始的 torchvision 权重。

🚀 快速开始

本模型可用于图像分类、特征图提取和图像嵌入等任务。以下是使用示例：

💻 使用示例

基础用法

from urllib.request import urlopen
from PIL import Image
import timm
import torch

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('rdnet_tiny.nv_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)

高级用法

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(
    'rdnet_tiny.nv_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, 256, 56, 56])
    # torch.Size([1, 440, 28, 28])
    # torch.Size([1, 744, 14, 14])
    # torch.Size([1, 1040, 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(
    'rdnet_tiny.nv_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, 1040, 7, 7) shaped tensor

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

📚 详细文档

模型详情

引用

@misc{kim2024densenets,
    title={DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs}, 
    author={Donghyun Kim and Byeongho Heo and Dongyoon Han},
    year={2024},
    eprint={2403.19588},
    archivePrefix={arXiv},
}

📄 许可证

本模型使用的许可证为 BSD 3 条款许可证（BSD-3-Clause）。