Dataset

This dataset was created by Hoshe Lee

Released under Apache 2.0

Contents

ImageNet trained PyTorch models are evaluated under various simple image transformations.

by Ritobrata Ghosh

Context

If this dataset is added as additional data, then it can be used as the base model that can be fine-tuned for a particular task using transfer learning.

Content

Contains a .pth file which is pretrained on the ImageNet model. Can be used with torch.load() method.

Acknowledgements

https://arxiv.org/abs/1512.03385

Inspiration

ResNet-50 is a widely used and successful architecture that uses Convolutions.

Context

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

Acknowledgements

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

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.

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.

Residual Neural Network-34 for Image classification pre-trained on ImageNet. ResNet-34 has 34 layer convolutional neural network and is compatible with Pytorch library in python.

Dataset Summary

This is a subset of the full Winter21, filtered according to https://github.com/Alibaba-MIIL/ImageNet21K. This instance contains 10450 classes with a train and validation split.

  Processing

I performed some processing while sharding this dataset:

Synsets were filtered according to ImageNet-21-P scripts Images were re-encoded in WEBP

  Additional Information





  Dataset Curators

Authors of [1] and [2]:

Olga Russakovsky Jia Deng Hao Su… See the full description on the dataset page: https://huggingface.co/datasets/timm/imagenet-w21-p.

LGV models used as surrogate in the original paper.

Those resnet50 models were collected along the SGD trajectory with a high learning rate. The zip file contains three random seeds in respective subfolders. Each one contains a subfolder with the original pretrained model from which the model collection started. These pretrained models were trained by Ashukha, A., et al. Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning (2020).

Dataset

This dataset was created by Christopher Sham

Contents

Content

• source code for ResNeSt
• pre-trained weights for ResNeSt50-Fast, ResNeSt50, ResNeSt101, ResNeSt200, ResNeSt269

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.

Tiny Cosmos-Tokenized Imagenet

Similar fashion to Simo's Imagenet.int8, here we provide Cosmos-tokenized imagenet for rapid prototyping. Noticeably, the discrete tokenizer is able to compress entire imagenet into shocking 2.45 GB of data!

  How to use

This time, we dumped it all on simple pytorch safetensor format. import torch import torch.nn as nn from safetensors.torch import safe_open

for continuous tokenizerwith… See the full description on the dataset page: https://huggingface.co/datasets/fal/cosmos-imagenet.

Softmax output when passing ImageNet-1K data (train & test sets) to PyTorch's pretrained classification models.

✅ AlexNet

v1: {'acc@1': 0.56522, 'acc@5': 0.79066, 'num_params': 61.10M}

✅ DenseNet (121, 161, 169, 201)

v1: {'acc@1': 0.74434, 'acc@5': 0.91972, 'num_params': 7.98M}
v1: {'acc@1': 0.77138, 'acc@5': 0.93560, 'num_params': 28.68M}
v1: {'acc@1': 0.75600, 'acc@5': 0.92806, 'num_params': 14.15M}
v1: {'acc@1': 0.76896, 'acc@5': 0.93370, 'num_params': 20.01M}

✅ VGG (11, 13, 16, 19)

v1: {'acc@1': 0.69020, 'acc@5': 0.88628, 'num_params': 132.86M}
v1: {'acc@1': 0.69928, 'acc@5': 0.89246, 'num_params': 133.05M}
v1: {'acc@1': 0.71592, 'acc@5': 0.90382, 'num_params': 138.36M}
v1: {'acc@1': 0.72376, 'acc@5': 0.90876, 'num_params': 143.67M}

ImageNet SDXL Quantized

This repository provides the ImageNet-1K dataset pre-encoded with the Stable Diffusion XL VAE encoder and quantized to uint8, allowing for faster training of latent diffusion models by eliminating the need for on-the-fly encoding.

  Key Features

Reduces quantization error by 2dB PSNR compared to a linear encoding scheme Provided in both 256 and 512 resolutions Compatible with NumPy, JAX, and PyTorch

  Usage





  Loading the dataset… See the full description on the dataset page: https://huggingface.co/datasets/jon-kyl/imagenet-sdxl-quantized.

Dataset

This dataset was created by Pronkin Aleksei

Contents

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.

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

Pytorch Image Models (timm)

timm is a deep-learning library created by Ross Wightman and is a collection of SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations and also training/validating scripts with ability to reproduce ImageNet training results.

https://github.com/rwightman/pytorch-image-models

# Installation
!python -m pip install /kaggle/input/timm067py3/timm-0.6.7-py3-none-any.whl

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