若要实现细粒度的200种label,请在__getitem__( )返回值中添加label,并修改64行format的第一个变量为具体的细粒度label. #!/usr/bin/env python3# -*- coding: utf-8 -*-'''@Time:2023/2/1910:50@Author:rumi_summer@Description:transfer datasetfromCUB form to Yolo form'''importosimportcv2classMana...
定义读取CUB_200_2011数据集的Dataset python 复制代码 import osimport cv2from torch.utils.data import Datasetclass CUB(Dataset):def __init__(self, path, train=True, transform=None, target_transform=None):self.root = pathself.is_train = trainself.transform = transformself.target_transform = tar...
The Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset is the most widely-used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds, 5,994 for training and 5,794 for testing. Each image ha
Introduced by Wah et al. inThe Caltech-UCSD Birds-200-2011 Dataset Caltech-UCSD BIRDS-200-2011(CUB-200-2011)数据集是用于细粒度可视化分类任务的最广泛的数据集。它包含了属于鸟类的200个亚类的11,788幅图像,其中5,994幅用于训练,5,794幅用于测试。每个图像都有详细的注释:1个子类别标签,15个零件位置...
类别的数量:200 图像的数量:11,788 === BibTeX === @techreport{WahCUB_200_2011, Title = {{The Caltech-UCSD Birds-200-2011 Dataset}}, Author = {Wah, C. and Branson, S. and Welinder, P. and Perona, P. and Belongie, S.}, Year = {2011} Institution = {California Institute...
The current state-of-the-art on CUB-200-2011 is Two Branch Network (Text - Bert + Image - Nts-Net). See a full comparison of 1 papers with code.
CUB_200_2011.zip 1.1 GB 压缩文件内容 文件名文件大小 CUB_200_2011/attributes.txt 8.8 KB CUB_200_2011/CUB_200_2011/attributes/certainties.txt 49.0 B CUB_200_2011/CUB_200_2011/attributes/class_attribute_labels_continuous.txt 570.7 KB CUB_200_2011/CUB_200_2011/attributes/image_attribute_labels...
cub-200-2011/Caltech-UCSD Birds-200-2011/CUB_200_2011/attributes/class_attribute_labels_continuous.txt 584393 2011-07-26 07:48:14 cub-200-2011/Caltech-UCSD Birds-200-2011/CUB_200_2011/attributes/image_attribute_labels.txt 73132180 2011-07-26 07:47:52 cub-200-2011/Caltech-UCSD Birds-200...
=== The Caltech-UCSD Birds-200-2011 Dataset === For more information about the dataset, visit the project website: http://www.vision.caltech.edu/visipedia If you use the dataset in a publication, please cite the dataset in the style described on the dataset website (see url above). ...
In this tutorial we are going to train a classification model using theCUB-200-2011 dataset. This dataset contains 200 species of birds, each with roughly 30 training images and 30 testing images, and has become a staple for testing new ideas for fine-grained visual classification. ...