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
import time
import skimage.io as io
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))
stream=sys.stdout)
import cPickle as pickle
import gzip
import os
import numpy as np
from sknn import ae, mlp
from sklearn.preprocessing import normalize
from sklearn.cross_validation import train_test_split
from skimage.transform import resize
from dip.load_data import load_raw_images, load_image_files
datasets = load_raw_images()
filenames = datasets.filenames
filenames_train, filenames_test = train_test_split(filenames)
batch_size = 30
N = len(filenames)
n_param = 5
n_iter = 10
myae = ae.AutoEncoder(
layers=[
ae.Layer('Tanh', units=128),
