def generate_X_y(non_lens_glob, lens_glob) :
'''Reads in data that will be features and targets, outputs as numpy array data'''
non_lens_filenames = glob.glob(non_lens_glob)
lens_filenames = glob.glob(lens_glob)
filenames = non_lens_filenames + lens_filenames
X = image_processing.load_images(filenames)
y = [0] * len(non_lens_filenames) + [1] * len(lens_filenames)
return X, y, filenames
def generate_X_y(non_lens_glob, lens_glob):
'''Reads in data that will be features and targets, outputs as numpy array data'''
non_lens_filenames = glob.glob(non_lens_glob)
lens_filenames = glob.glob(lens_glob)
filenames = non_lens_filenames + lens_filenames
X = image_processing.load_images(filenames)
y = [0] * len(non_lens_filenames) + [1] * len(lens_filenames)
return X, y, filenames
def handle_query(directory, palette, canvas):
"""
Parameters
directory: folder containing images
palette: maps color ids to functions
canvas: list of color ids
Return value
list of strings (file names)
"""
split_dim = 4
from image_processing import load_images, sortImagesByMatchRevised
imgs = load_images(directory)
result = sortImagesByMatchRevised(imgs, canvas, split_dim, palette)
# result_imgs = []
# for filename in result:
# result_imgs.append(Image.open(os.path.join(directory, filename)))
return result
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('non_lens_glob')
parser.add_argument('lens_glob')
args = vars(parser.parse_args())
# Load the data. X is a list of numpy arrays
# which are the images.
non_lens_filenames = glob.glob(args['non_lens_glob'])
lens_filenames = glob.glob(args['lens_glob'])
filenames = non_lens_filenames + lens_filenames
X = image_processing.load_images(filenames)
y = [0] * len(non_lens_filenames) + [1] * len(lens_filenames)
# Train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8)
print "len(X_train) =", len(X_train)
print "len(y_train) =", len(y_train)
print "len(X_test) =", len(X_test)
print "len(y_test) =", len(y_test)
print
# Create the pipeline which consists of image
# processing and a classifier
image_processors = [('median_smooth', image_processing.MedianSmooth(5)),
('hog',
image_processing.HOG(orientations=8,
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('non_lens_glob')
parser.add_argument('lens_glob')
args = vars(parser.parse_args())
# Load the data. X is a list of numpy arrays
# which are the images.
non_lens_filenames = glob.glob(args['non_lens_glob'])
lens_filenames = glob.glob(args['lens_glob'])
filenames = non_lens_filenames + lens_filenames
X = image_processing.load_images(filenames)
y = [0] * len(non_lens_filenames) + [1] * len(lens_filenames)
# Train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size = 0.8)
print "len(X_train) =", len(X_train)
print "len(y_train) =", len(y_train)
print "len(X_test) =", len(X_test)
print "len(y_test) =", len(y_test)
print
# Create the pipeline which consists of image
# processing and a classifier
image_processors = [('median_smooth', image_processing.MedianSmooth(5)),
('hog', image_processing.HOG(orientations = 8,
pixels_per_cell = (16, 16),
import time
import numpy as np
from keras.applications import vgg19
from keras.optimizers import SGD
from pycocotools.coco import COCO
from image_processing import load_images, categories, ann_file
from vgg import compute_nn_features
from text_processing import create_caption_dataframe
from word2vec import compute_textual_features
coco = COCO(ann_file)
X_visual, _, visual_img_ids = load_images(categories, coco=coco)
np.save('X_visual.npy', X_visual)
X_visual = np.load('X_visual.npy')
X_visual = X_visual[:X_visual.shape[0] // 2]
net = vgg19.VGG19()
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
net.compile(optimizer=sgd, loss='categorical_crossentropy')
from tqdm import tqdm
V = np.zeros((X_visual.shape[0], 4096))
for i in tqdm(range(X_visual.shape[0] // 10 + 1)):
start_index = (i) * 10
end_index = (i + 1) * 10
