def test_split_fixed_sample_unbalanced():
input_dir = os.path.join(os.path.dirname(__file__), "imgs")
output_dir = os.path.join(os.path.dirname(__file__), "output")
shutil.rmtree(output_dir, ignore_errors=True)
with pytest.raises(ValueError):
split_folders.fixed(input_dir, output_dir, fixed=(9, 1), oversample=True)
def split_images(input_directory, output_directory,type,value):
if(type == "ratio"):
# Split with a ratio.
# To only split into training and validation set, set a tuple to `ratio`, i.e, `(.8, .2)`.
split_folders.ratio(input_directory, output_directory, seed=1337, ratio=value) # default values
elif(type == "fixed"):
# Split val/test with a fixed number of items e.g. 100 for each set.
# To only split into training and validation set, use a single number to `fixed`, i.e., `10`.
split_folders.fixed(input_directory, output_directory, seed=1337, fixed=value, oversample=False) # default values
else:
print("Invalid input")
def test_split_fixed_sample():
input_dir = os.path.join(os.path.dirname(__file__), "imgs")
output_dir = os.path.join(os.path.dirname(__file__), "output")
shutil.rmtree(output_dir, ignore_errors=True)
split_folders.fixed(input_dir, output_dir, fixed=(2, 2), oversample=True)
# ensure the number of pics is the same
a = len(list(pathlib.Path(input_dir).glob("**/*.jpg")))
b = len(list(pathlib.Path(output_dir).glob("**/*.jpg")))
assert a != b
def test_split_fixed():
input_dir = os.path.join(os.path.dirname(__file__), 'imgs')
output_dir = os.path.join(os.path.dirname(__file__), 'output')
shutil.rmtree(output_dir, ignore_errors=True)
split_folders.fixed(input_dir, output_dir, fixed=(2, 2))
# ensure the number of pics is the same
a = len(list(pathlib.Path(input_dir).glob('**/*.jpg')))
b = len(list(pathlib.Path(output_dir).glob('**/*.jpg')))
assert a == b
import split_folders
# Split with a ratio.
# To only split into training and validation set, set a tuple to `ratio`, i.e, `(.8, .2)`.
split_folders.ratio('input_folder',
output="output",
seed=1337,
ratio=(.8, .1, .1)) # default values
# Split val/test with a fixed number of items e.g. 100 for each set.
# To only split into training and validation set, use a single number to `fixed`, i.e., `10`.
split_folders.fixed('input_folder',
output="output",
seed=1337,
fixed=(100, 100),
oversample=False) # default values
import split_folders
# Split with a ratio.
# To only split into training and validation set, set a tuple to `ratio`, i.e, `(.8, .2)`.
split_folders.ratio('./img_root/', output="output", seed=1337,
ratio=(.8, .2)) # default values
# Split val/test with a fixed number of items e.g. 100 for each set.
# To only split into training and validation set, use a single number to `fixed`, i.e., `10`.
split_folders.fixed('./img_root/',
output="output",
seed=1337,
fixed=(10),
oversample=False) # default values
# for splitting the dataset into tain,test and validation dataset.
import split_folders
# Split with a ratio.
# To only split into training and validation set, set a tuple to `ratio`, i.e, `(.8, .2)`.
# split_folders.ratio('/home/satvik/Downloads/major/satu/satu', output="output", seed=1337, ratio=(.8, .1, .1)) # default values
# Split val/test with a fixed number of items e.g. 100 for each set.
# To only split into training and validation set, use a single number to `fixed`, i.e., `10`.
split_folders.fixed('/home/satvik/Downloads/major/satu', output="/home/satvik/Downloads/major/dataset", seed=1337, fixed=(50, 50), oversample=False) # default values
import numpy as np
import pandas as pd
import json
from pathlib import Path
import os
from fastai.vision import *
import split_folders
path = Path(r'E:\paintings-dataset\wikiart\train')
output_path = Path(r'E:\paintings-dataset')
split_folders.fixed(path,
output=output_path,
fixed=(100, 20),
oversample=False) # default values
# for dir_class in split_folders.list_dirs(path):
# print(len(split_folders.list_files(dir_class)))
ImageList
