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
myae = ae.AutoEncoder(
layers=[
ae.Layer('Tanh', units=128),
ae.Layer('Sigmoid', units=64),
],
learning_rate=0.002,
n_iter=10,
)
for _ in xrange(n_iter):
print '--------------------------------------------------------'
p = np.random.randint(0, N, batch_size)
images = load_image_files(filenames[p], as_grey=True)
X = np.array([resize(im, (356,534)).reshape(-1) for im in images])
y = np.zeros((batch_size, n_param), dtype=np.float)
print 'X:\n{0}\n{1}'.format(X, X.shape)
print 'y:\n{0}\n{1}'.format(y, y.shape)
X = X.astype(np.float) / 255.
print 'X: \n{0}\n{1}'.format(X, X.shape)
myae.fit(X)
print 'dir(myae):\n{0}'.format(dir(myae))
print 'myae.__dict__:\n{0}'.format(myae.__dict__)
print '--------------------------------------------------------'
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
bunch.target_names = datasets.target_names
bunch.description = 'mask rects: (min_x, min_y, max_x, max_y)'
with gzip.open('rects.pkl.gz', 'wb') as f:
pickle.dump(bunch, f)
