timm 库介绍

最新推荐文章于 2024-12-18 15:35:35 发布

原创

最新推荐文章于 2024-12-18 15:35:35 发布 · 1.2k 阅读

14 ·

CC 4.0 BY-SA版权

文章标签：

#transformer #深度学习 #人工智能

原文链接：https://zhuanlan.zhihu.com/p/350837279

为了尊重原作者，这边只放一个链接，只做简单介绍，感兴趣的请去原文博客。

PyTorchImageModels，简称 timm，是一个巨大的 PyTorch 代码集合，旨在将各种 SOTA 模型整合在一起，并具有复现 ImageNet 训练结果的能力。虽然模型架构是 timm 的重点，但它还包括许多数据增强 (data augmentations)、正则化技术 (regularization techniques)、优化器 (optimizers) 和学习率策略 (learning rate schedulers) 的实现。

timm作者是，Ross Wightman ，他的github留言挺好的“Always learning, constantly curious. Building ML/AI systems, watching loss curves.”

PyTorch Image Models

All model architecture families include variants with pretrained weights. There are specific model variants without any weights, it is NOT a bug. Help training new or better weights is always appreciated.

Aggregating Nested Transformers - https://arxiv.org/abs/2105.12723
BEiT - https://arxiv.org/abs/2106.08254
Big Transfer ResNetV2 (BiT) - https://arxiv.org/abs/1912.11370
Bottleneck Transformers - https://arxiv.org/abs/2101.11605
CaiT (Class-Attention in Image Transformers) - https://arxiv.org/abs/2103.17239
CoaT (Co-Scale Conv-Attentional Image Transformers) - https://arxiv.org/abs/2104.06399
CoAtNet (Convolution and Attention) - https://arxiv.org/abs/2106.04803
ConvNeXt - https://arxiv.org/abs/2201.03545
ConvNeXt-V2 - http://arxiv.org/abs/2301.00808
ConViT (Soft Convolutional Inductive Biases Vision Transformers)- https://arxiv.org/abs/2103.1