Original source of dataset: http://shuoyang1213.me/WIDERFACE/

The Wider Face dataset compatible for use with Torchvision. If you use this dataset, you don't need to download it via the internet into your Kaggle working directory. The dataset is available at: '/kaggle/input/wider-face-torchvision-compatible/'

To use, say:

import torchvision

wf_dataset = torchvision.datasets.WIDERFace(
  root = '/kaggle/input/wider-face-torchvision-compatible/',
  split = "train",
  download = False,
)

image, targets = wf_dataset[0]

Dataset

This dataset was created by TonyChen52

Contents

Dataset Card for "movie_posters-genres-80k-torchvision-transforms"

More Information needed

Context

Used for the APTOS 2019 competition.

Content

torchvision.models.resnet101

torchvision.models.resnet152

torchvision.models.densenet121

torchvision.models.densenet169

torchvision.models.densenet161

torchvision.models.densenet201

torchvision.models.inception_v3

torchvision.models.segmentation.fcn_resnet101

Acknowledgements

https://pytorch.org/docs/stable/torchvision/models.html

CelebA dataset

A copy of celeba dataset. https://mmlab.ie.cuhk.edu.hk/projects/CelebA.html

  How to use

Download data

huggingface-cli download --local-dir /path/to/datasets/celeba --repo-type dataset Yuehao/celeba unzip /path/to/datasets/celeba/img_align_celeba.zip -d /path/to/datasets/celeba

Load data via torchvision.datasets.CelebA

torchvision.datasets.CelebA(root='/path/to/datasets')

Simple pretrained dump of efficientnet weights from the torchvision package.

Obtained by simply running a notebook with the internet switched on and then switching it off.

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding and requires careful hyperparameter tuning. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches optimized to generalize across different models and applied to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations.

We release our dataset as a set of folders indicating the patch target label (e.g., banana), each containing 1000 subfolders as the ImageNet output classes.

An example showing how to use the dataset is shown below.

code for testing robustness of a model

import os.path

from torchvision import datasets, transforms, models import torch.utils.data

class ImageFolderWithEmptyDirs(datasets.ImageFolder): """ This is required for handling empty folders from the ImageFolder Class. """

def find_classes(self, directory):
  classes = sorted(entry.name for entry in os.scandir(directory) if entry.is_dir())
  if not classes:
    raise FileNotFoundError(f"Couldn't find any class folder in {directory}.")
  class_to_idx = {cls_name: i for i, cls_name in enumerate(classes) if
          len(os.listdir(os.path.join(directory, cls_name))) > 0}
  return classes, class_to_idx

extract and unzip the dataset, then write top folder here

dataset_folder = 'data/ImageNet-Patch'

available_labels = { 487: 'cellular telephone', 513: 'cornet', 546: 'electric guitar', 585: 'hair spray', 804: 'soap dispenser', 806: 'sock', 878: 'typewriter keyboard', 923: 'plate', 954: 'banana', 968: 'cup' }

select folder with specific target

target_label = 954

dataset_folder = os.path.join(dataset_folder, str(target_label)) normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) transforms = transforms.Compose([ transforms.ToTensor(), normalizer ])

dataset = ImageFolderWithEmptyDirs(dataset_folder, transform=transforms) model = models.resnet50(pretrained=True) loader = torch.utils.data.DataLoader(dataset, shuffle=True, batch_size=5) model.eval()

batches = 10 correct, attack_success, total = 0, 0, 0 for batch_idx, (images, labels) in enumerate(loader): if batch_idx == batches: break pred = model(images).argmax(dim=1) correct += (pred == labels).sum() attack_success += sum(pred == target_label) total += pred.shape[0]

accuracy = correct / total attack_sr = attack_success / total

print("Robust Accuracy: ", accuracy) print("Attack Success: ", attack_sr)

Dataset

This dataset was created by jionie

Contents

GH200 ARM64 vLLM wheel

We build wheels for GH200 ARM64 from Lambda AI for specific PyTorch version,

torch==2.7.1+cu128 torchaudio==2.7.1 torchvision==0.22.1

Full requirements in requirements.txt, but PyTorch 2.7.1 Cuda 12.8 should be enough, pip3 install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 pytorch-triton==3.3.0 --index-url https://download.pytorch.org/whl/cu128

  Build by yourself

Step to reproduce at build.sh.

Dataset

This dataset was created by rkstgr

Contents

Dataset Card for "SemEval_traindata_emotions"

Как был получен from datasets import load_dataset import datasets from torchvision.io import read_video import json import torch import os from torch.utils.data import Dataset, DataLoader import tqdm

dataset_path = "./SemEval-2024_Task3/training_data/Subtask_2_train.json"

dataset = json.loads(open(dataset_path).read()) print(len(dataset))

all_conversations = []

for item in dataset: all_conversations.extend(item["conversation"])… See the full description on the dataset page: https://huggingface.co/datasets/dim/SemEval_training_data_emotions.

Example usage. You will have to use a shape batching dataset when training in batches from datasets import load_dataset from diffusers import AutoencoderDC import torch import torchvision.transforms as transforms from PIL import Image

ds = load_dataset("SwayStar123/imagenet1k_dcae-f64-latents_train")

with torch.inference_mode(): device = "cuda" ae = AutoencoderDC.from_pretrained("mit-han-lab/dc-ae-f64c128-mix-1.0-diffusers", cache_dir="ae", torch_dtype=torch.bfloat16).to(device).eval()… See the full description on the dataset page: https://huggingface.co/datasets/SwayStar123/imagenet1k_dcae-f64-latents.

Dataset

This dataset was created by morg

Contents

Dataset

This dataset was created by denred0

Contents

FFHQ Dataset (pravsels/FFHQ_1024) encoded using the dc-ae-f128c512-mix-1.0 auto encoder. Example usage import sys sys.path.append('../dcae') # https://github.com/vladmandic/dcae from dcae import DCAE

from datasets import load_dataset import torch import torchvision

dataset = load_dataset("SwayStar123/FFHQ_1024_DC-AE_f128", split="train") dc_ae = DCAE("dc-ae-f128c512-mix-1.0", device="cuda", dtype=torch.bfloat16).eval() # Must be bfloat. with float16 it produces terrible outputs.

def… See the full description on the dataset page: https://huggingface.co/datasets/SwayStar123/FFHQ_1024_DC-AE_f128.

ViTTiny1022

The dataset for Scaling Up Parameter Generation: A Recurrent Diffusion Approach.

  Requirement





  Install torch and other dependencies

conda install pytorch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 pytorch-cuda=12.1 -c pytorch -c nvidia pip install timm einops seaborn openpyxl

  Usage





  Test one checkpoint

cd ViTTiny1022 python test.py ./chechpoint_test/0000_acc0.9613_class0314_condition_cifar10_vittiny.pth

python test.py… See the full description on the dataset page: https://huggingface.co/datasets/MTDoven/ViTTiny1022.

About

Helper codes used in TORCHVISION OBJECT DETECTION FINETUNING TUTORIAL

original -> GitHub Page

Dataset Card for Video Summarization For Retail Dataset

This dataset contains short videos of shoppers in a retail setting along with the corresponding textual descriptions of each video.

  Dataset Details

Curated by: Parker Lischwe Language(s) (NLP): English License: cc-by-sa-4.0

  Uses

Navigate to Downloads directory where the zip file and python script have been downloaded to and run following commands in terminal: pip install torch torchvision… See the full description on the dataset page: https://huggingface.co/datasets/Intel/Video_Summarization_For_Retail.

Dataset

This dataset was created by kuokuo

Contents

Content

Pre-trained inception v3 model on ImageNet data provided by torchvision.

Acknowledgements

Data provided by torchvision under BSD licence. For details visit their website.