- 博客(0)
- 资源 (12)
空空如也
In-shop Clothes Retrieval Benchmark
In-shop Clothes Retrieval Benchmark evaluates the performance of in-shop Clothes Retrievel. This is a large subset of DeepFashion, containing large pose and scale variations. It also has large diversities, large quantities, and rich annotations, including
7,982 number of clothing items;
52,712 number of in-shop clothes images, and ~200,000 cross-pose/scale pairs;
Each image is annotated by bounding box, clothing type and pose type.
2018-11-30
Fashion Synthesis Benchmark
Fashion Synthesis Benchmark facilitates the studies of generating new clothing images. It includes 78,979 images selected from the In-shop Clothes Benchmark. Each image is associated with several sentences as captions and a segmentation map. If you use the images, captions, and segmentations, please appropriately cite the papers of DeepFashion and FashionGAN.
The 78,979 images can be downloaded from Google Drive or Baidu Drive.
The captions and segmentations for these images can be downloaded from FashionGAN.
Images with high resolutions are released upon request.
2018-11-30
Fashion Landmark Detection Benchmark
Fashion Landmark Detection Benchmark evaluates the performance of fashion landmark detection. This is a large subset of DeepFashion, with diverse and large pose/zoom-in variations. It contains
123,016 number of clothes images;
8 fashion landmarks (both location and visibility) for each image;
Each image is also annotated by bounding box, clothing type and variation type.
More details can be found in "Fashion Landmark Detection in the Wild, ECCV 2016".
2018-11-30
Consumer-to-shop Clothes Retrieval Benchmark
Consumer-to-shop Clothes Retrieval Benchmark evaluates the performance of consumer-to-shop Clothes Retrievel. This is a large subset of DeepFashion, containing cross-domain correspondences and variations in the wild. It contains
33,881 number of clothing items;
239,557 number of consumer/shop clot
2018-11-30
Category and Attribute Prediction Benchmark
2016-08-08 The data and labels of the attribute prediction benchmark are released without encription (password). If Dropbox are not accessable, please download the dataset using Google Drive or Baidu Drive
2018-11-30
jester数据集
Dataset 1: Over 4.1 million continuous ratings (-10.00 to +10.00) of 100 jokes from 73,421 users: collected between April 1999 - May 2003.
Dataset 2: Over 1.7 million continuous ratings (-10.00 to +10.00) of 150 jokes from 59,132 users: collected between November 2006 - May 2009.
Dataset 2+: An updated version of Dataset 2 with over 500,000 new ratings from 79,681 total users: data collected from November 2006 - Nov 2012
下载链接:http://eigentaste.berkeley.edu/dataset/
2018-11-30
flask-keras-cnn-image-retrieval-master
需要的环境:keras 2.0.1 及 2.0.5 版本均经过测试可用。推荐Python 2.7,支持Python 3.6.
此外需要numpy, matplotlib, os, h5py, argparse. 推荐使用anaconda安装
2018-10-19
场景分类places365
Places365是Places2数据库的最新子集。 Places365有两个版本:Places365-Standard和Places365-Challenge。 Places365-Standard的列车集有来自365个场景类别的约180万张图像,每个类别最多有5000张图像。 我们已经在Places365-Standard上培训了各种基线CNN,并将其发布如下。 与此同时,一系列的Places365-Challenge列车还有620万张图片以及Places365-Standard的所有图片(总共约800万张图片),每个类别最多有40,000张图片。 Places365-Challenge将用于2016年的Places2挑战赛,与2016年ECCV的ILSVRC和COCO联合研讨会一起举行。
2018-10-19
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人