当前位置:网站首页>Fashion Gen: the general fashion dataset and challenge paper interpretation & dataset introduction
Fashion Gen: the general fashion dataset and challenge paper interpretation & dataset introduction
2022-07-06 12:03:00 【Caojia xiaoyuanbao】
FashionGEN Dataset use
Interpretation of the thesis
Address of thesis :https://arxiv.org/abs/1806.08317
Data set partitioning
number | train | val | test |
---|---|---|---|
293, 008 | 260, 480 | 32, 528 | 32, 528 |
Category introduction
There are 48 There are two main classes ,121 A subclass .
Here is the training set 、 The proportion of categories in the test set
Picture statistics
The following are the main categories of training set 、 Statistics of the number of pictures of subclasses
Text description
The following is the statistics of text description length
The following is the color distribution extracted from the text
chanllenge
- Generating high-resolution images using P-GANs
- Text-to-Image synthesis
Evaluation methods
- Inception Score
- Human Evaluation( because Inception Score The correlation between text and images is not considered )
Dataset Download
notice FashionBERT The data set in the paper FashionGEN, Want to know , But there is no letter after filling in a form on the official website , The address is :https://fashion-gen.com/ So I found relevant content on the Internet , Find a web address https://github.com/menardai/FashionGenAttnGAN
It has 3 File ( notes : No test set provided , The paper says that no test set will be provided , Integrated into the thesis docker in )
- fashiongen_256_256_train.h5
- fashiongen_256_256_validation.h5
- fashiongen_consume_data_example.pdf
Analysis of the code
Reference resources https://docs.h5py.org/en/stable/quick.html Analyze with the following code
import h5py
import numpy as np
BATCH_SIZE = 32
def get_batch(file_h5, features, batch_number, batch_size=32):
"""Get a batch of the dataset Args: file_h5(str): path of the dataset features(list(str)): list of names of features present in the dataset that should be returned. batch_number(int): the id of the batch to be returned. batch_size(int): the mini-batch size Returns: A list of numpy arrays of the requested features"""
list_of_arrays = []
lb, ub = batch_number * batch_size, (batch_number + 1) * batch_size
for feature in features:
list_of_arrays.append(file_h5[feature][lb: ub])
return list_of_arrays
# open the file
# file_h5 = h5py.File('fashiongen_256_256_train.h5', mode='r')
file_h5 = h5py.File('fashiongen_256_256_validation.h5', mode='r')
# define the features to be retrieved
list_of_features = ['input_image', 'input_description']
dataset_len = len(file_h5['input_image'])
nb_batches = int(dataset_len / BATCH_SIZE)
batch_nb = np.random.randint(0, nb_batches)
# get the first batch of the data
list_of_arrays = get_batch(file_h5, list_of_features, batch_nb, BATCH_SIZE)
# close the file
file_h5.close()
Get the number of training sets 260490、 Number of validation sets 32528
Data sets are similar dict Structure ,keys Respectively
[‘index’, ‘index_2’, ‘input_brand’, ‘input_category’, ‘input_composition’, ‘input_concat_description’, ‘input_department’, ‘input_description’, ‘input_gender’, ‘input_image’, ‘input_msrpUSD’, ‘input_name’, ‘input_pose’, ‘input_productID’, ‘input_season’, ‘input_subcategory’]
The dimension of the picture is :
(256, 256, 3)
content analysis
Take the validation set as an example , Next, analyze the contents one by one
- index
file_h5['index'].shape
# (32528, 1)
file_h5['index'][0:][0:]
# Output the following
[[ 24]
[ 25]
[ 26]
...
[342153]
[342154]
[342155]]
- index_2
file_h5['index_2'].shape
# (32528,)
file_h5['index_2'][0:]
# Output the following
[ 0 1 2 ... 32525 32526 32527]
- input_brand
file_h5['input_brand'].shape
# (32528, 1)
file_h5['input_brand'][0:][0:]
# Output the following
array([[b'Diesel'],
[b'Diesel'],
[b'Diesel'],
...,
[b'Calvin Klein 205W39NYC'],
[b'Calvin Klein 205W39NYC'],
[b'Calvin Klein 205W39NYC']], dtype='|S100')
- input_category
file_h5['input_category'].shape
# (32528, 1)
file_h5['input_category'][0:][0:]
# Output the following
array([[b'JACKETS & COATS'],
[b'JACKETS & COATS'],
[b'JACKETS & COATS'],
...,
[b'SHIRTS'],
[b'SHIRTS'],
[b'SHIRTS']], dtype='|S100')
- input_composition
file_h5['input_composition'].shape
# (32528, 1)
file_h5['input_composition'][0:][0:]
# Output the following
array([[b'90% cotton, 8% polyester, 2% elastane.'],
[b'90% cotton, 8% polyester, 2% elastane.'],
[b'90% cotton, 8% polyester, 2% elastane.'],
...,
[b'100% cotton.'],
[b'100% cotton.'],
[b'100% cotton.']], dtype='|S200')
- input_concat_description
file_h5['input_concat_description'].shape
# (32528, 1)
file_h5['input_concat_description'][0:][0:]
# Output the following
array([[b'Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching. Semi-sheer t-shirt in heather white. Crewneck collar. Patch pocket at breast. Tonal stitching.'],
[b'Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching. Semi-sheer t-shirt in heather white. Crewneck collar. Patch pocket at breast. Tonal stitching.'],
[b'Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching. Semi-sheer t-shirt in heather white. Crewneck collar. Patch pocket at breast. Tonal stitching.'],
...,
[b"Long sleeve cotton poplin shirt in 'optic' white. Spread collar featuring carved silver-tone hardware. Button closure at front. Single-button barrel cuffs. Tonal stitching. Slim-fit 'uniform' twill trousers in black. Mid-rise. Four-pocket styling. Central pleat at front and back legs. Grosgrain tape striped in blue and purple at outseams. Zip-fly. Partially lined. Tonal stitching. Long sleeve coated cotton-blend trench coat in beige. Notched lapel collar. Concealed button closure at front. Detachable pin-buckle belt and welt pockets at waist. Buttoned tab at central back vent and cuffs. Epaulets. Storm flap. Unlined. Tonal stitching."],
[b"Long sleeve cotton poplin shirt in 'optic' white. Spread collar featuring carved silver-tone hardware. Button closure at front. Single-button barrel cuffs. Tonal stitching. Slim-fit 'uniform' twill trousers in black. Mid-rise. Four-pocket styling. Central pleat at front and back legs. Grosgrain tape striped in blue and purple at outseams. Zip-fly. Partially lined. Tonal stitching. Long sleeve coated cotton-blend trench coat in beige. Notched lapel collar. Concealed button closure at front. Detachable pin-buckle belt and welt pockets at waist. Buttoned tab at central back vent and cuffs. Epaulets. Storm flap. Unlined. Tonal stitching."],
[b"Long sleeve cotton poplin shirt in 'optic' white. Spread collar featuring carved silver-tone hardware. Button closure at front. Single-button barrel cuffs. Tonal stitching. Slim-fit 'uniform' twill trousers in black. Mid-rise. Four-pocket styling. Central pleat at front and back legs. Grosgrain tape striped in blue and purple at outseams. Zip-fly. Partially lined. Tonal stitching. Long sleeve coated cotton-blend trench coat in beige. Notched lapel collar. Concealed button closure at front. Detachable pin-buckle belt and welt pockets at waist. Buttoned tab at central back vent and cuffs. Epaulets. Storm flap. Unlined. Tonal stitching."]],
dtype='|S800')
- input_department
file_h5['input_department'].shape
# (32528, 1)
file_h5['input_department'][0:][0:]
# Output the following
array([[b'CLOTHING'],
[b'CLOTHING'],
[b'CLOTHING'],
...,
[b'CLOTHING'],
[b'CLOTHING'],
[b'CLOTHING']], dtype='|S100')
- input_description
file_h5['input_description'].shape
# (32528, 1)
file_h5['input_description'][0:][0:]
# Output the following
array([[b'Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching.'],
[b'Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching.'],
[b'Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching.'],
...,
[b"Long sleeve cotton poplin shirt in 'optic' white. Spread collar featuring carved silver-tone hardware. Button closure at front. Single-button barrel cuffs. Tonal stitching."],
[b"Long sleeve cotton poplin shirt in 'optic' white. Spread collar featuring carved silver-tone hardware. Button closure at front. Single-button barrel cuffs. Tonal stitching."],
[b"Long sleeve cotton poplin shirt in 'optic' white. Spread collar featuring carved silver-tone hardware. Button closure at front. Single-button barrel cuffs. Tonal stitching."]],
dtype='|S400')
- input_gender
file_h5['input_gender'].shape
# (32528, 1)
file_h5['input_gender'][0:][0:]
# Output the following
array([[b'Men'],
[b'Men'],
[b'Men'],
...,
[b'Men'],
[b'Men'],
[b'Men']], dtype='|S30')
- input_image
file_h5['input_image'].shape
# (32528, 256, 256, 3)
file_h5['input_image'][0].shape
# (256, 256, 3)
- input_msrpUSD
file_h5['input_msrpUSD'].shape
(32528, 1)
file_h5['input_msrpUSD'][0:][0:]
# Output the following
array([[335.],
[335.],
[335.],
...,
[990.],
[990.],
[990.]], dtype=float32)
- input_name
file_h5['input_name'].shape
# (32528, 1)
file_h5['input_name'][0:][0:]
# Output the following
array([[b'Blue Faded Elshar Jogg Jacket'],
[b'Blue Faded Elshar Jogg Jacket'],
[b'Blue Faded Elshar Jogg Jacket'],
...,
[b'White Pointed Collar Shirt'],
[b'White Pointed Collar Shirt'],
[b'White Pointed Collar Shirt']], dtype='|S100')
- ‘input_pose
file_h5['input_pose'].shape
# (32528, 1)
file_h5['input_pose'][0:][0:]
# Output the following
array([[b'id_gridfs_1'],
[b'id_gridfs_2'],
[b'id_gridfs_3'],
...,
[b'id_gridfs_3'],
[b'id_gridfs_4'],
[b'id_gridfs_5']], dtype='|S40')
- input_productID
file_h5['input_productID'].shape
# (32528, 1)
file_h5['input_productID'][0:][0:]
# Output the following
array([[ 86605],
[ 86605],
[ 86605],
...,
[2938688],
[2938688],
[2938688]], dtype=int32)
- input_season
file_h5['input_season'].shape
(32528, 1)
file_h5['input_season'][0:][0:]
# Output the following
array([[b'SS2014'],
[b'SS2014'],
[b'SS2014'],
...,
[b'SS2018'],
[b'SS2018'],
[b'SS2018']], dtype='|S10')
- input_subcategory
file_h5['input_subcategory'].shape
# (32528, 1)
file_h5['input_subcategory'][0:][0:]
# Output the following
array([[b'DENIM JACKETS'],
[b'DENIM JACKETS'],
[b'DENIM JACKETS'],
...,
[b'SHIRTS'],
[b'SHIRTS'],
[b'SHIRTS']], dtype='|S100')
Visualization data
keys | 1 | 2 | 3 |
---|---|---|---|
index | 24,25,26,27 | 73,74,75,76 | 93,94,95,96 |
index_2 | 0, 1, 2, 3 | 4, 5, 6, 7 | 8, 9, 10, 11 |
input_brand | b’Diesel’ | b’Dsquared2’ | b’Diesel Black Gold’ |
input_category | b’JACKETS & COATS’ | b’JEANS’ | b’JACKETS & COATS’ |
input_composition | b’90% cotton, 8% polyester, 2% elastane.’ | b’98% cotton, 2% elastane.’ | b’Body: 100% lambskin. Contrast: 100% goatskin. Lining: 51% cotton, 49% rayon. Sleeve lining: 54% acetate, 46% polyester.’ |
input_concat_description | b’Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching. Semi-sheer t-shirt in heather white. Crewneck collar. Patch pocket at breast. Tonal stitching.’ | b’Slim-fit jeans in light grey. Distressing and fading throughout. Seven-pocket styling. Textured black leather logo patch at back waist. Tonal stitching. Red logo tab at button-fly. Short sleeve t-shirt in deep slate blue. Crewneck collar. Tonal stitching.’ | b’Long sleeve suede jacket in black. Tonal grained leather paneling throughout. Stand collar. Zip closure and zippered welt pockets at front. Zippered vents at back hem. Welt pockets at interior. Fully lined. Tonal stitching. Zippered expansion panels at sleeve cuffs. Long sleeve coated denim shirt in indigo blue. Irregular overdye effect throughout in black. Spread collar. Flap pockets at breast, one with metallic logo piece. Press-stud closure at front. Tonal stitching. Three press-studs at barrel cuffs. Slim-fit cropped pleated wool trousers in black. Four-pocket styling. Tonal stitching. Button-fly.’ |
input_department | b’CLOTHING’ | b’CLOTHING’ | b’CLOTHING’ |
input_description | b’Denim-like jogg jacket in blue. Fading and whiskering throughout. Spread collar. Copper tone button closures at front. Flap pockets at chest with metallic logo plaque. Seam pockets at sides. Cinch tabs at back waistband. Single button sleeve cuffs. Tone on tone stitching.’ | b’Slim-fit jeans in light grey. Distressing and fading throughout. Seven-pocket styling. Textured black leather logo patch at back waist. Tonal stitching. Red logo tab at button-fly.’ | b’Long sleeve suede jacket in black. Tonal grained leather paneling throughout. Stand collar. Zip closure and zippered welt pockets at front. Zippered vents at back hem. Welt pockets at interior. Fully lined. Tonal stitching. Zippered expansion panels at sleeve cuffs.’ |
input_gender | b’Men’ | b’Men’ | b’Men’ |
input_image1 | |||
input_image2 | |||
input_image3 | |||
input_image4 | |||
input_msrpUSD | 335. | 630. | 1215. |
input_pose | b’id_gridfs_1’,b’id_gridfs_2’,b’id_gridfs_3’,b’id_gridfs_4’ | b’id_gridfs_1’,b’id_gridfs_2’,b’id_gridfs_3’,b’id_gridfs_4’ | b’id_gridfs_1’,b’id_gridfs_2’,b’id_gridfs_3’,b’id_gridfs_4’ |
input_productID | 86605 | 86773 | 86711 |
input_season | b’SS2014’ | b’SS2014’ | b’SS2014’ |
input_subcategory | b’DENIM JACKETS’ | b’JEANS’ | b’LEATHER JACKETS’ |
The content of subsequent data sets will be updated … Please advise me if you have any questions ~
边栏推荐
- ESP8266通过arduino IED连接巴法云(TCP创客云)
- Missing value filling in data analysis (focus on multiple interpolation method, miseforest)
- There are three iPhone se 2022 models in the Eurasian Economic Commission database
- STM32型号与Contex m对应关系
- Feature of sklearn_ extraction. text. CountVectorizer / TfidVectorizer
- AMBA、AHB、APB、AXI的理解
- OSPF message details - LSA overview
- uCOS-III 的特点、任务状态、启动
- Stage 4 MySQL database
- 使用LinkedHashMap实现一个LRU算法的缓存
猜你喜欢
Vert. x: A simple login access demo (simple use of router)
共用体(union)详解【C语言】
5G工作原理详解(解释&图解)
Stage 4 MySQL database
MySQL数据库面试题
Correspondence between STM32 model and contex M
E-commerce data analysis -- User Behavior Analysis
机器学习--决策树(sklearn)
uCOS-III 的特点、任务状态、启动
Characteristics, task status and startup of UCOS III
随机推荐
MySQL START SLAVE Syntax
Raspberry pie tap switch button to use
MySQL数据库面试题
Kaggle competition two Sigma connect: rental listing inquiries (xgboost)
【ESP32学习-1】Arduino ESP32开发环境搭建
R & D thinking 01 ----- classic of embedded intelligent product development process
JS object and event learning notes
XML file explanation: what is XML, XML configuration file, XML data file, XML file parsing tutorial
MySQL realizes read-write separation
A possible cause and solution of "stuck" main thread of RT thread
Internet protocol details
Kaggle竞赛-Two Sigma Connect: Rental Listing Inquiries(XGBoost)
JS array + array method reconstruction
gcc 编译选项
Apprentissage automatique - - régression linéaire (sklearn)
Variable star user module
Word typesetting (subtotal)
encoderMapReduce 随手记
Those commonly used tool classes and methods in hutool
Time slice polling scheduling of RT thread threads