eca_halonext26ts.c1_in1k

eca_halonext26ts.c1_in1k项目介绍

项目概述

eca_halonext26ts.c1_in1k是一个基于HaloNet架构的图像分类模型。这个模型结合了高效通道注意力机制（Efficient Channel Attention，ECA）和ResNeXt架构的特点，由Ross Wightman在timm库中训练完成。该模型在ImageNet-1k数据集上进行了训练，旨在提供一个高效且性能优秀的图像分类解决方案。

模型特点

这个模型具有以下几个显著特点：

灵活的架构：使用了timm库中的BYOBNet（Bring-Your-Own-Blocks Network）框架，允许灵活配置网络结构、注意力机制等组件。
高效注意力机制：采用了高效通道注意力机制，提高了模型的性能和效率。
优化的训练策略：基于"ResNet Strikes Back"论文中的C类配方，使用了SGD优化器（带Nesterov动量）和自适应梯度裁剪（AGC）技术。
先进的学习率调度：采用了带有预热的余弦退火学习率调度策略。
多项高级特性：包括随机深度、梯度检查点、分层学习率衰减和每阶段特征提取等timm库的常用功能。

模型详情

eca_halonext26ts.c1_in1k模型具有以下统计数据：

参数量：10.8百万
GMACs：2.4
激活量：11.5百万
输入图像尺寸：256 x 256

这些数据表明，该模型在保持较小规模的同时，仍能提供出色的性能。

应用场景

这个模型主要应用于以下场景：

图像分类：可以直接用于识别和分类各种图像。
特征提取：作为backbone网络，可以提取图像的多尺度特征，用于下游任务如目标检测、图像分割等。
图像嵌入：可以生成图像的高维向量表示，用于图像检索、相似度计算等任务。

使用方法

模型的使用非常简便，通过timm库可以轻松加载预训练模型并进行推理。用户可以根据需求选择图像分类、特征图提取或图像嵌入等不同的使用方式。

总结

eca_halonext26ts.c1_in1k是一个结合了多项先进技术的图像分类模型，它在保持模型规模较小的同时，通过优化的架构设计和训练策略，实现了高效的性能。无论是直接用于图像分类任务，还是作为特征提取器用于其他计算机视觉任务，这个模型都展现出了很好的应用潜力。

Model card for eca_halonext26ts.c1_in1k

A HaloNet image classification model (with Efficient channel attention, based on ResNeXt architecture). Trained on ImageNet-1k in timm by Ross Wightman.

NOTE: this model did not adhere to any specific paper configuration, it was tuned for reasonable training times and reduced frequency of self-attention blocks.

Recipe details:

Based on ResNet Strikes Back C recipes
SGD (w/ Nesterov) optimizer and AGC (adaptive gradient clipping).
Cosine LR schedule with warmup

This model architecture is implemented using timm's flexible BYOBNet (Bring-Your-Own-Blocks Network).

BYOB (with BYOANet attention specific blocks) allows configuration of:

block / stage layout
block-type interleaving
stem layout
output stride (dilation)
activation and norm layers
channel and spatial / self-attention layers

...and also includes timm features common to many other architectures, including:

stochastic depth
gradient checkpointing
layer-wise LR decay
per-stage feature extraction

Model Details

Model Type: Image classification / feature backbone
Model Stats:
- Params (M): 10.8
- GMACs: 2.4
- Activations (M): 11.5
- Image size: 256 x 256
Papers:
- Scaling Local Self-Attention for Parameter Efficient Visual Backbones: https://arxiv.org/abs/2103.12731
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
Dataset: ImageNet-1k

Model Usage

Image Classification

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('eca_halonext26ts.c1_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)

Feature Map Extraction

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(
    'eca_halonext26ts.c1_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, 64, 128, 128])
    #  torch.Size([1, 256, 64, 64])
    #  torch.Size([1, 512, 32, 32])
    #  torch.Size([1, 1024, 16, 16])
    #  torch.Size([1, 2048, 8, 8])

    print(o.shape)

Image Embeddings

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(
    'eca_halonext26ts.c1_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, 2048, 8, 8) shaped tensor

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

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

@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}}
}

@article{Vaswani2021ScalingLS,
  title={Scaling Local Self-Attention for Parameter Efficient Visual Backbones},
  author={Ashish Vaswani and Prajit Ramachandran and A. Srinivas and Niki Parmar and Blake A. Hechtman and Jonathon Shlens},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={12889-12899}
}

@inproceedings{wightman2021resnet,
  title={ResNet strikes back: An improved training procedure in timm},
  author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
  booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}