def get_dataset():
cache_file = 'dataset_cache.pkl.gz')
if os.path.exists(cache_file):
with open(cache_file, 'rb') as f:
dataset = pickle.load(f)
return dataset['data'], dataset['target']
raw_dataset = load_raw_images()
data = load_image_files(raw_dataset.filenames)
data = np.array(list(data))
mask_dataset = load_mask_images()
masks = load_image_files(mask_dataset.filenames)
target = convert_masks_to_target(masks, negative=True)
with open(cache_file, 'wb') as f:
dataset = {'data': data, 'target': target}
pickle.dump(dataset, f)
return data, target
from skimage.transform import resize
from dip.load_data import load_raw_images, load_mask_images
parser = argparse.ArgumentParser()
parser.add_argument('--shape0', type=int, default=1424)
parser.add_argument('--shape1', type=int, default=2136)
args = parser.parse_args()
shape = (args.shape0, args.shape1)
raw_dataset = load_raw_images()
for i, f in enumerate(raw_dataset.filenames):
print(f)
img = io.imread(f)
if i == 0:
print('resize: {0} -> {1}'.format(img.shape[:2], shape))
resized = resize(img, output_shape=shape)
io.imsave(f, resized)
mask_dataset = load_mask_images()
for i, f in enumerate(mask_dataset.filenames):
print(f)
img = io.imread(f)
if i == 0:
print('resize: {0} -> {1}'.format(img.shape[:2], shape))
resized = resize(img, output_shape=shape)
io.imsave(f, resized)
from __future__ import print_function
import collections
import cPickle as pickle
from future_builtins import zip
import gzip
import numpy as np
from skimage import io
from sklearn.datasets.base import Bunch
from dip.load_data import load_image_files, load_mask_images
from dip.mask import bounding_rect_of_mask
datasets = load_mask_images()
data = []
for f, mask in zip(
datasets.filenames,
load_image_files(datasets.filenames),
):
# rect: (min_x, max_x, min_y, max_x)
rect = bounding_rect_of_mask(mask, negative=True)
data.append(list(rect))
print('{0}: {1}'.format(f, rect))
bunch = Bunch(name='mask rects')
bunch.data = np.array(data)
bunch.filenames = datasets.filenames
bunch.target = datasets.target
