Context

https://github.com/pytorch/examples/tree/master/imagenet

Acknowledgements

https://github.com/pytorch/examples/tree/master/imagenet

This dataset is used in the Pytorch example Transfer Learning for Computer Vision Tutorial

Dataset Summary

This is a copy of the full Winter21 release of ImageNet in webdataset tar format with JPEG images. This release consists of 19167 classes, 2674 fewer classes than the original 21841 class Fall11 release of the full ImageNet. The classes were removed due to these concerns: https://www.image-net.org/update-sep-17-2019.php

  Data Splits

The full ImageNet dataset has no defined splits. This release follows that and leaves everything in the train split.… See the full description on the dataset page: https://huggingface.co/datasets/timm/imagenet-w21-wds.

ResNet-34

Deep Residual Learning for Image Recognition

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity.

An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.

The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Authors: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
https://arxiv.org/abs/1512.03385

Architecture visualization: http://ethereon.github.io/netscope/#/gist/db945b393d40bfa26006

https://imgur.com/nyYh5xH.jpg" alt="Resnet">

What is a Pre-trained Model?

A pre-trained model has been previously trained on a dataset and contains the weights and biases that represent the features of whichever dataset it was trained on. Learned features are often transferable to different data. For example, a model trained on a large dataset of bird images will contain learned features like edges or horizontal lines that you would be transferable your dataset.

Why use a Pre-trained Model?

Pre-trained models are beneficial to us for many reasons. By using a pre-trained model you are saving time. Someone else has already spent the time and compute resources to learn a lot of features and your model will likely benefit from it.

Dataset Summary

ILSVRC 2012, commonly known as 'ImageNet' is an image dataset organized according to the WordNet hierarchy. Each meaningful concept in WordNet, possibly described by multiple words or word phrases, is called a "synonym set" or "synset". There are more than 100,000 synsets in WordNet, majority of them are nouns (80,000+). ImageNet aims to provide on average 1000 images to illustrate each synset. Images of each concept are quality-controlled and human-annotated. 💡… See the full description on the dataset page: https://huggingface.co/datasets/timm/imagenet-1k-wds.

Example

https://www.kaggle.com/ttahara/training-birdsong-baseline-resnest50-fast

Content

• source code for ResNeSt
• pre-trained weights for ResNeSt50-fast-xxxx

License

Contents are originally distributed by authors in the Apache License 2.0. [GitHub] https://github.com/zhanghang1989/ResNeSt/blob/master/LICENSE

Reference

ResNeSt: Split-Attention Networks [arXiv 2004.08955]

　Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Zhi Zhang, Haibin Lin, Yue Sun, Tong He, Jonas Muller, R. Manmatha, Mu Li and Alex Smola

Dataset Summary

This is a copy of the full ImageNet dataset consisting of all of the original 21841 clases. It also contains labels in a separate field for the '12k' subset described at at (https://github.com/rwightman/imagenet-12k, https://huggingface.co/datasets/timm/imagenet-12k-wds) This dataset is from the original fall11 ImageNet release which has been replaced by the winter21 release which removes close to 3000 synsets containing people, a number of these are of an offensive… See the full description on the dataset page: https://huggingface.co/datasets/timm/imagenet-22k-wds.

Taken from the README of the google-research/big_transfer repo:

Big Transfer (BiT): General Visual Representation Learning

by Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby

Introduction

In this repository we release multiple models from the Big Transfer (BiT): General Visual Representation Learning paper that were pre-trained on the ILSVRC-2012 and ImageNet-21k datasets. We provide the code to fine-tuning the released models in the major deep learning frameworks TensorFlow 2, PyTorch and Jax/Flax.

We hope that the computer vision community will benefit by employing more powerful ImageNet-21k pretrained models as opposed to conventional models pre-trained on the ILSVRC-2012 dataset.

We also provide colabs for a more exploratory interactive use: a TensorFlow 2 colab, a PyTorch colab, and a Jax colab.

Installation

Make sure you have Python>=3.6 installed on your machine.

To setup Tensorflow 2, PyTorch or Jax, follow the instructions provided in the corresponding repository linked here.

In addition, install python dependencies by running (please select tf2, pytorch or jax in the command below): pip install -r bit_{tf2|pytorch|jax}/requirements.txt

How to fine-tune BiT

First, download the BiT model. We provide models pre-trained on ILSVRC-2012 (BiT-S) or ImageNet-21k (BiT-M) for 5 different architectures: ResNet-50x1, ResNet-101x1, ResNet-50x3, ResNet-101x3, and ResNet-152x4.

For example, if you would like to download the ResNet-50x1 pre-trained on ImageNet-21k, run the following command: wget https://storage.googleapis.com/bit_models/BiT-M-R50x1.{npz|h5} Other models can be downloaded accordingly by plugging the name of the model (BiT-S or BiT-M) and architecture in the above command. Note that we provide models in two formats: npz (for PyTorch and Jax) and h5 (for TF2). By default we expect that model weights are stored in the root folder of this repository.

Then, you can run fine-tuning of the downloaded model on your dataset of interest in any of the three frameworks. All frameworks share the command line interface python3 -m bit_{pytorch|jax|tf2}.train --name cifar10_`date +%F_%H%M%S` --model BiT-M-R50x1 --logdir /tmp/bit_logs --dataset cifar10 Currently. all frameworks will automatically download CIFAR-10 and CIFAR-100 datasets. Other public or custom datasets can be easily integrated: in TF2 and JAX we rely on the extensible tensorflow datasets library. In PyTorch, we use torchvision’s data input pipeline.

Note that our code uses all available GPUs for fine-tuning.

We also support training in the low-data regime: the `--examples_per_class

Example

https://www.kaggle.com/rafazz/starter-how-to-use-tinyimagenet-normalized

Context

The dataset is the 64x64 tiny counterpart for the ImageNet challenge (ILSVRC). This dataset is suitable for in-house experimentation, without hundreds of gigabytes of downloaded images.

Note

This dataset requires the https://github.com/z-a-f/zaf_funcs functions to be used.

Content

The dataset is a pickled dataset class and a dataloader. The images are normalized to 255.0 and to mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]. The images are converted to PyTorch tensors permuted into NCHW layout. The run-time transformation (in train mode) includes horizontal flipping with p=0.5.

Acknowledgements

The raw images could be downloaded from https://tiny-imagenet.herokuapp.com/, and all the credit goes to the CS231n peeps.

Usage

Check my tutorial notebook. By utilizing my custom class, you can use models naturally through timm.
https://www.kaggle.com/ttahara/usage-of-custom-cswin-transformer-for-timm

Example

WIP

Content

• official source code for CSWin-Transformer
• additional python file (custom_cswin_for_timm.py)
• pre-trained weights:

License

Contents are originally distributed by authors in the MIT License. [GitHub] https://github.com/microsoft/CSWin-Transformer/blob/main/LICENSE

Copyright (c) Microsoft Corporation.

Reference

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows [arXiv:2107.00652]

　Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, Baining Guo
The header image is cited from the paper, which illustrates the key mechanism: Cross-Shaped Window self-attention.