Fashion Gen: the general fashion dataset and challenge paper interpretation & dataset introduction

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

1. index

file_h5['index'].shape
# (32528, 1)
file_h5['index'][0:][0:]
#  Output the following 
[[    24]
 [    25]
 [    26]
 ...
 [342153]
 [342154]
 [342155]]

2. index_2

file_h5['index_2'].shape
# (32528,)
file_h5['index_2'][0:]
#  Output the following 
[    0     1     2 ... 32525 32526 32527]

3. 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')

4. 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')

5. 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')

6. 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')

7. 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')

8. 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')

9. 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')

10. input_image

file_h5['input_image'].shape
# (32528, 256, 256, 3)
file_h5['input_image'][0].shape
# (256, 256, 3)

11. 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)

12. 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')

13. ‘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')

14. 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)

15. 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')

16. 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 ～