def __init__(self):
self.image, self.rect = utils.load_images("mainmenu/title.png")
self.rect.right = 0
self.tweener = pytweener.Tweener()
self.x = - self.rect.width
self.tweener.addTween(self, x=200, tweenTime=1,
tweenType=pytweener.Easing.Elastic.easeOut)
def __init__(self, game):
GameSceneMessage.__init__(self, game)
self.graphic_message, self.rect = utils.load_images('gamescene/pause.png')
self.x = - 100
self.rect.y = 200
self.tweener.addTween(self, x=200, tweenTime=0.3,
tweenType=pytweener.Easing.Elastic.easeOut)
def __init__(self, director):
scene.Scene.__init__(self, director)
self.background, rect = utils.load_images("options/background.png")
self.menu = menu.Menu(
[
("Fullscreen", self.on_toggle),
("Regresar", self.on_return),
])
def __init__(self, start_y, item_height, initial_selected):
self.image, self.rect = utils.load_images("cursor.png")
self.rect.centerx = 320
self.start_y = start_y
self.y = 0
self.item_height = item_height
self.tweener = pytweener.Tweener()
self.set_position(initial_selected)
def __init__(self, director):
scene.Scene.__init__(self, director)
self.background, rect = utils.load_images("creditscene/background.png")
self.font = utils.load_font("FreeSans.ttf", 20)
self.program = ["Hugo Ruscitti", "Juanxo", "Dokan", "lacabra25",
"Juan Carlos", "thepoi", "joksnet"]
self.art = ["Walter Velazquez"]
self.rendered_program = self.render_authors(self.program)
self.rendered_art = self.render_authors(self.art)
def __init__(self, director):
scene.Scene.__init__(self, director)
self.graphic_message = None
self.running = True
self.delay_showing_line_animation = 0
self.current_message = None
self.current_message_rect = None
self.board = board.Board(self)
self.display = display.Display()
self.background, tmp = utils.load_images("gamescene/background.png")
self.pieces = piece.Group()
self.game_speed = 0
self.create_return_message()
self.show_graphic_message(game_scene_messages.AreYouReadyMessage(self))
self.line_animation = None
self.delay_showing_line_animation = 0
decoder_A.load_weights("models/decoder_A.h5")
decoder_B.load_weights("models/decoder_B.h5")
except:
pass
def save_model_weights():
encoder.save_weights("models/encoder.h5")
decoder_A.save_weights("models/decoder_A.h5")
decoder_B.save_weights("models/decoder_B.h5")
print("save model weights")
images_A = get_image_paths("data/trump")
images_B = get_image_paths("data/cage")
images_A = load_images(images_A) / 255.0
images_B = load_images(images_B) / 255.0
images_A += images_B.mean(axis=(0, 1, 2)) - images_A.mean(axis=(0, 1, 2))
print("press 'q' to stop training and save model")
for epoch in range(1000000):
batch_size = 64
warped_A, target_A = get_training_data(images_A, batch_size)
warped_B, target_B = get_training_data(images_B, batch_size)
loss_A = autoencoder_A.train_on_batch(warped_A, target_A)
loss_B = autoencoder_B.train_on_batch(warped_B, target_B)
print(loss_A, loss_B)
#!/usr/bin/env python3
import numpy as np
import tensorflow as tf
from train_model import TrainModel
from utils import load_images, load_csv, generate_triplets
images, filenames = load_images('HBTNaligned', as_array=True)
triplet_names = load_csv('FVTriplets.csv')
A, P, N = generate_triplets(images, filenames, triplet_names)
triplets = [A[:-2], P[:-2], N[:-2]] # to make all batches divisible by 32
tm = TrainModel('models/face_verification.h5', 0.2)
history = tm.train(triplets, epochs=1)
print(history.history)
import sac
import sys
if len(sys.argv) != 2:
print "Usage: ./display_saved_network.py somefile.pickle"
sys.exit(1)
fname = sys.argv[1]
f = open(fname, "r")
solution = pickle.load(f)
utils.save_as_figure((solution.W1 + solution.b1).T, "loadedW1.png")
utils.save_as_figure(solution.W2, "loadedW2.png")
images = utils.load_images("data/train-images-idx3-ubyte")
labels = utils.load_labels("data/train-labels-idx1-ubyte")
utils.save_as_figure(images[:, 0:100], "output/input.png")
patches = images[:, 0:10000]
visible_size = 28*28
hidden_size = 196
options = sac.SparseAutoEncoderOptions(visible_size,
hidden_size,
output_dir="output",
max_iterations = 400)
network = sac.SparseAutoEncoder(options, patches)
def load_data(self):
# load and prepare names
input_image_names = load_image_names(self._config.data_dir,
self._config.match_pattern)
target_image_names = input_image_names if not self._config.target_data_dir else \
load_image_names(self._config.target_data_dir, self._config.match_pattern)
name_size = min(len(input_image_names), len(target_image_names))
if len(input_image_names) != len(target_image_names):
tf.logging.warning(
"Reducing data set to {} (input: {}, target: {})".format(
name_size, len(input_image_names),
len(target_image_names)))
input_image_names = input_image_names[:name_size]
assert self._config.data_dir == self._config.target_data_dir, "should shuffle target images before reducing"
target_image_names = target_image_names[:name_size]
assert not self._config.train_disc_on_extra_targets, "not implemented"
# load images
input_images = load_images(input_image_names,
self._config.data_dir,
self._config.input_type,
flip_lr=self._config.augmentation_flip_lr,
flip_ud=self._config.augmentation_flip_ud)
target_images = load_images(target_image_names,
self._config.target_data_dir
or self._config.data_dir,
self._config.target_type,
flip_lr=self._config.augmentation_flip_lr,
flip_ud=self._config.augmentation_flip_ud)
assert len(input_images) == len(target_images)
# load/prepare test data
test_input_images = None
test_target_images = None
if self._config.test_data_dir:
assert not self._config.target_data_dir, "alternative test target data currently isn't supported"
tf.logging.info("Loading test data")
test_input_image_names = load_image_names(
self._config.test_data_dir, self._config.match_pattern)
test_input_images = load_images(test_input_image_names,
self._config.test_data_dir,
self._config.input_type,
flip_lr=False,
flip_ud=False)
test_target_images = load_images(test_input_image_names,
self._config.test_data_dir,
self._config.target_type,
flip_lr=False,
flip_ud=False)
assert len(test_input_images) == len(test_target_images)
if self._config.test_data_percentage:
tf.logging.warning(
"Using the first {}% of the training data for testing".format(
100 * self._config.test_data_percentage))
split = int(len(target_images) * self._config.test_data_percentage)
test_input_images = input_images[:split]
input_images = input_images[split:]
test_target_images = target_images[:split]
target_images = target_images[split:]
data_set_size = len(target_images)
test_set_size = len(
[] if test_target_images is None else test_target_images)
# set up epoch samples
sample_indexes = np.random.choice(data_set_size,
np.prod(self._epoch_images_shape),
replace=False)
self._epoch_sample_input = tf.convert_to_tensor(
input_images[sample_indexes])
self._epoch_sample_targets = target_images[sample_indexes]
# build data sets
self._data_set = tf.data.Dataset.from_tensor_slices((input_images, target_images))\
.shuffle(data_set_size).batch(self._config.batch_size)
del input_images
del target_images
if test_target_images is not None:
self._test_data_set = tf.data.Dataset.from_tensor_slices((test_input_images, test_target_images))\
.shuffle(test_set_size).batch(self._config.batch_size)
del test_input_images
del test_target_images
else:
tf.logging.warning("Running evaluation without test data!")
return data_set_size, test_set_size
# Custom object needed for inference and training
custom_objects = {
'BilinearUpSampling2D': BilinearUpSampling2D,
'depth_loss_function': depth_loss_function
}
print('Loading model...')
# Load model into GPU / CPU
model = load_model(args.model, custom_objects=custom_objects, compile=False)
print('\nModel loaded ({0}).'.format(args.model))
# Input images
inputs = load_images(glob.glob(args.input))
ipdb.set_trace()
print('\nLoaded ({0}) images of size {1}.'.format(inputs.shape[0],
inputs.shape[1:]))
for input_image in range(inputs.shape[0]):
img = np.expand_dims(inputs[input_image], axis=0)
outputs = predict(model, img)
save_images('image_' + str(input_image), outputs)
# Compute results
# Display results
# viz = display_images(outputs.copy(), inputs.copy())
# plt.figure(figsize=(10,5))
# plt.imsave('depth_pred.png', viz)
def load_data(self):
# load and prepare names
input_image_names = load_image_names(self._config.data_dir,
self._config.match_pattern)
second_input_image_names = input_image_names if not self._config.second_data_dir else \
load_image_names(self._config.second_data_dir, self._config.match_pattern)
if self._config.use_extra_first_inputs:
assert len(second_input_image_names) < len(input_image_names)
second_input_times = 2
tf.logging.warning(
"Using each second input {} times".format(second_input_times))
second_input_image_names = second_input_image_names * second_input_times
if len(second_input_image_names) < len(input_image_names):
tf.logging.warning(
"There are fewer second input images; shuffling and reducing input images"
)
np.random.shuffle(input_image_names)
input_image_names = input_image_names[:len(second_input_image_names
)]
target_image_names = input_image_names if not self._config.target_data_dir else \
second_input_image_names if self._config.target_data_dir == self._config.second_data_dir else \
load_image_names(self._config.target_data_dir, self._config.match_pattern)
assert len(target_image_names) >= len(input_image_names)
name_size = min(
min(len(input_image_names), len(second_input_image_names)),
len(target_image_names))
if len(input_image_names) != len(target_image_names) or len(
second_input_image_names) != len(target_image_names):
tf.logging.warning(
"Reducing data set to {} (input: {}, second input: {}, target: {})"
.format(name_size, len(input_image_names),
len(second_input_image_names),
len(target_image_names)))
input_image_names = input_image_names[:name_size]
second_input_image_names = second_input_image_names[:name_size]
tf.logging.info(
"Input and target data are different; shuffling targets before reducing"
)
np.random.shuffle(target_image_names)
if self._config.train_disc_on_extra_targets:
extra_target_image_names = target_image_names[name_size:]
extra_target_image_names = extra_target_image_names[:2 * len(
input_image_names)] # select the first X extra images
else:
extra_target_image_names = None
target_image_names = target_image_names[:name_size]
else:
assert not self._config.train_disc_on_extra_targets, "there are no extra targets to train on"
extra_target_image_names = None
# load images
input_images = load_images(input_image_names,
self._config.data_dir,
self._config.input_type,
flip_lr=self._config.augmentation_flip_lr,
flip_ud=self._config.augmentation_flip_ud)
second_input_images = load_images(
second_input_image_names,
self._config.second_data_dir or self._config.data_dir,
self._config.second_input_type,
flip_lr=self._config.augmentation_flip_lr,
flip_ud=self._config.augmentation_flip_ud)
combined_input_images = np.concatenate(
[input_images, second_input_images], axis=-1)
del input_images
del second_input_images
target_images = load_images(target_image_names,
self._config.target_data_dir
or self._config.data_dir,
self._config.target_type,
flip_lr=self._config.augmentation_flip_lr,
flip_ud=self._config.augmentation_flip_ud)
if extra_target_image_names:
extra_target_images = load_images(
extra_target_image_names,
self._config.target_data_dir or self._config.data_dir,
self._config.target_type,
flip_lr=self._config.augmentation_flip_lr,
flip_ud=self._config.augmentation_flip_ud)
tf.logging.warning(
"Adding {} extra targets for the discriminator!".format(
len(extra_target_images)))
self._extra_discriminator_data_set = tf.data.Dataset.from_tensor_slices(extra_target_images)\
.shuffle(len(extra_target_images)).batch(self._config.batch_size)
del extra_target_images
assert len(combined_input_images) == len(target_images)
# load/prepare test data
test_input_images = None
test_target_images = None
if self._config.test_data_dir:
tf.logging.info("Loading test data")
test_input_image_names = load_image_names(
self._config.test_data_dir, self._config.match_pattern)
test_second_input_image_names = test_input_image_names if not self._config.test_second_data_dir else \
load_image_names(self._config.test_second_data_dir, self._config.match_pattern)
if len(test_second_input_image_names) < len(
test_input_image_names):
tf.logging.warning(
"TEST: There are fewer second input images; shuffling and reducing input images"
)
np.random.shuffle(test_input_image_names)
test_input_image_names = test_input_image_names[:len(
test_second_input_image_names)]
test_target_image_names = test_input_image_names if not self._config.test_target_data_dir else \
test_second_input_image_names if self._config.test_target_data_dir == self._config.test_second_data_dir else \
load_image_names(self._config.test_target_data_dir, self._config.match_pattern)
assert len(test_target_image_names) >= len(test_input_image_names)
name_size = min(
min(len(test_input_image_names),
len(test_second_input_image_names)),
len(test_target_image_names))
if len(test_input_image_names) != len(
test_target_image_names) or len(
test_second_input_image_names) != len(
test_target_image_names):
tf.logging.warning(
"Reducing data set to {} (input: {}, second input: {}, target: {})"
.format(name_size, len(test_input_image_names),
len(test_second_input_image_names),
len(test_target_image_names)))
test_input_image_names = test_input_image_names[:name_size]
test_second_input_image_names = test_second_input_image_names[:
name_size]
tf.logging.info(
"Input and target data are different; shuffling targets before reducing"
)
np.random.shuffle(test_target_image_names)
test_target_image_names = test_target_image_names[:name_size]
test_input_images = load_images(test_input_image_names,
self._config.test_data_dir,
self._config.input_type,
flip_lr=False,
flip_ud=False)
test_second_input_images = load_images(
test_second_input_image_names,
self._config.test_second_data_dir
or self._config.test_data_dir,
self._config.second_input_type,
flip_lr=False,
flip_ud=False)
test_combined_input_images = np.concatenate(
[test_input_images, test_second_input_images], axis=-1)
del test_input_images
del test_second_input_images
test_target_images = load_images(test_target_image_names,
self._config.test_target_data_dir
or self._config.test_data_dir,
self._config.target_type,
flip_lr=False,
flip_ud=False)
assert len(test_combined_input_images) == len(test_target_images)
if self._config.test_data_percentage:
tf.logging.warning(
"Using the first {}% of the training data for testing".format(
100 * self._config.test_data_percentage))
split = int(len(target_images) * self._config.test_data_percentage)
test_combined_input_images = combined_input_images[:split]
combined_input_images = combined_input_images[split:]
test_target_images = target_images[:split]
target_images = target_images[split:]
assert False, "not implemented"
data_set_size = len(target_images)
test_set_size = len(
[] if test_target_images is None else test_target_images)
# set up epoch samples
sample_indexes = np.random.choice(data_set_size,
np.prod(self._epoch_images_shape),
replace=False)
self._epoch_sample_input = tf.convert_to_tensor(
combined_input_images[sample_indexes])
# build data sets
self._data_set = tf.data.Dataset.from_tensor_slices((combined_input_images, target_images))\
.shuffle(data_set_size).batch(self._config.batch_size)
del combined_input_images
del target_images
if test_set_size:
self._test_data_set = tf.data.Dataset.from_tensor_slices((test_combined_input_images, test_target_images))\
.shuffle(test_set_size).batch(self._config.batch_size)
del test_combined_input_images
del test_target_images
else:
tf.logging.warning("Running evaluation without test data!")
return data_set_size, test_set_size
# Get the command line parameter value.
arg_index = sys.argv.index('--patches_file')
patches_file = sys.argv[arg_index + 1]
patches = None
if patches_file is not None:
# If the patches_file command line parameter was provided,
# read it from disk.
pprint("Reading patches file ...")
with open(patches_file, 'rb') as fp:
patches = pickle.load(fp)
else:
# If the patches_file command line parameter was not provided,
# load the images from disk, ...
pprint("Loading images ...")
images, image_files = load_images(images_path, extensions=['.png'],
img_shape=(256, 256))
if create_patches:
# and if the --create_patches was provided generate the patches.
pprint("Extracting patches ...")
patches = extract_patches(images, patch_shape=(16, 16))
if patches_file is not None:
pprint("Saving patches to disk ...")
with open(patches_file, 'wb') as fp:
pickle.dump(patches, fp)
else:
# or, if the --create_patches was not provided, use the images
# themselves as the patches.
patches = images
# Finally, start the learning procedure.
pprint("Starting training ...")
#!/usr/local/bin/python
from website import app
from utils import clear, load, load_images, add_zips
import sys
if __name__ == '__main__':
if len(sys.argv) == 1:
app.debug = True
app.run(host='0.0.0.0', port=5000)
elif len(sys.argv) == 2:
if sys.argv[1] == 'clear':
clear()
elif sys.argv[1] == 'load':
load()
elif sys.argv[1] == 'load_images':
load_images()
elif sys.argv[1] == 'add_zips':
add_zips()
else:
print "error starting server: could not interpret argument"
else:
print "error starting server: too many arguments"
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from utils import load_images
from skimage.feature import hog
from sklearn.model_selection import GridSearchCV
# load images
images, labels = load_images()
images = images[0:10000]
labels = labels[0:10000]
hogs = []
for image in images:
hogs.append(hog(image, pixels_per_cell=(7, 7), cells_per_block=(4, 4)))
print("Done")
X_train, X_test, y_train, y_test = train_test_split(hogs,
labels,
test_size=.15)
grid_params = {'n_neighbors': [3, 5, 7, 9], 'weights': ['uniform', 'distance']}
# Fit a KNN classifier on the training set
search = GridSearchCV(KNeighborsClassifier(), grid_params)
search.fit(X_train, y_train)
total = 0
right = 0
print(search.best_params_)
for image, label in zip(X_test, y_test):
if search.predict(image.reshape(1, -1)) == label:
right += 1
total += 1
def main(type,
input_names,
save_folder='./detections',
iou_threshold=0.5,
confidence_threshold=0.5,
class_names_file=_CLASS_NAMES_FILE,
create_csv=False):
# Get class names and number
class_names = load_class_names(class_names_file)
n_classes = len(class_names)
# Tensorflow prep
tf.compat.v1.reset_default_graph()
# Load Yolo_v3 model
model = Yolo_v3(n_classes=n_classes,
model_size=_MODEL_SIZE,
max_output_size=_MAX_OUTPUT_SIZE,
iou_threshold=iou_threshold,
confidence_threshold=confidence_threshold)
if type == 'images':
# Load pictures and set up detection inputs
batch_size = len(input_names)
batch = load_images(input_names, model_size=_MODEL_SIZE)
inputs = tf.compat.v1.placeholder(tf.float32,
[batch_size, *_MODEL_SIZE, 3])
detections = model(inputs, training=False)
saver = tf.compat.v1.train.Saver(
tf.compat.v1.global_variables(scope='yolo_v3_model'))
# Load the weights model.ckpt and run detection on inputs
with tf.compat.v1.Session() as sess:
saver.restore(sess, './weights/model.ckpt')
detection_result = sess.run(detections, feed_dict={inputs: batch})
# Using detection results, draw detection boxes on input pictures and save them
draw_boxes(input_names, detection_result, class_names, _MODEL_SIZE,
save_folder)
print('Detections have been saved successfully.')
elif type == 'video':
# Set yolo_v3 to tensorflow
inputs = tf.compat.v1.placeholder(tf.float32, [1, *_MODEL_SIZE, 3])
detections = model(inputs, training=False)
saver = tf.compat.v1.train.Saver(
tf.compat.v1.global_variables(scope='yolo_v3_model'))
# Run tensorflow session
with tf.compat.v1.Session() as sess:
# Load model
saver.restore(sess, './weights/model.ckpt')
# Create window for output video
win_name = 'Video detection'
cv2.namedWindow(win_name, cv2.WINDOW_NORMAL)
cv2.resizeWindow(win_name, 1280, 720)
# Create OpenCV capture and get video metadata
cap = cv2.VideoCapture(input_names[0])
frame_size = (cap.get(cv2.CAP_PROP_FRAME_WIDTH),
cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fourcc = cv2.VideoWriter_fourcc(*'X264')
fps = cap.get(cv2.CAP_PROP_FPS)
# Set name and save destination for output video
input_name_base = os.path.basename(input_names[0])
video_save_path = save_folder + '/' + os.path.splitext(input_name_base)[0] + '_analysed' + \
os.path.splitext(input_name_base)[1]
if os.path.splitext(input_name_base)[1] in _TO_MP4_FORMAT_LIST:
video_save_path = save_folder + '/' + os.path.splitext(
input_name_base)[0] + '_analysed.mp4'
# Create output video
out = cv2.VideoWriter(video_save_path, fourcc, fps,
(int(frame_size[0]), int(frame_size[1])))
# Create csv file and insert row of time, frame, and classes if create_csv is set to True
if create_csv:
csv_save_path = save_folder + '/' + os.path.splitext(
input_name_base)[0] + '_statistics.csv'
csv_field_names = class_names[:]
csv_field_names.insert(0, "time")
csv_field_names.insert(0, "frame")
print(fps)
sec_counter = 0
with open(csv_save_path, 'w', newline='') as csv_file:
csv_writer = csv.writer(csv_file)
csv_file.write("sep=,")
csv_file.write('\n')
csv_writer.writerow(csv_field_names)
csv_input_dict = {"frame": cap.get(cv2.CAP_PROP_POS_FRAMES)}
try:
while True:
ret, frame = cap.read()
if not ret:
break
# Resize frame to fit model and run detection
resized_frame = cv2.resize(frame,
dsize=_MODEL_SIZE[::-1],
interpolation=cv2.INTER_NEAREST)
detection_result = sess.run(
detections, feed_dict={inputs: [resized_frame]})
# In one second intervals, insert the maximum number of detections per class to a new row in csv
if create_csv:
csv_input_dict["frame"] = cap.get(
cv2.CAP_PROP_POS_FRAMES)
csv_input_dict["time"] = cap.get(cv2.CAP_PROP_POS_MSEC)
for cls in range(len(class_names)):
number_of_obj = len(detection_result[0][cls])
if number_of_obj != 0:
print(class_names[cls] + str(number_of_obj))
if class_names[cls] in csv_input_dict:
csv_input_dict[class_names[cls]] = max(
number_of_obj,
csv_input_dict[class_names[cls]])
else:
csv_input_dict[
class_names[cls]] = number_of_obj
if cap.get(
cv2.CAP_PROP_POS_MSEC) / 1000 >= sec_counter:
with open(csv_save_path, 'a',
newline='') as csv_file:
csv_writer = csv.DictWriter(
csv_file, fieldnames=csv_field_names)
csv_writer.writerow(csv_input_dict)
sec_counter += 1
for cls in range(len(class_names)):
csv_input_dict.pop(class_names[cls], None)
print(sec_counter)
# Draw detection boxes on the frame being handled
draw_frame(frame, frame_size, detection_result,
class_names, _MODEL_SIZE)
# Show the current output frame on window
cv2.imshow(win_name, frame)
# Poll for key inputs, if 'q' is pressed, break to end processing video
key = cv2.waitKey(1) & 0xFF
if key == ord('q'):
break
# Write the current frame to the output file
out.write(frame)
finally:
cv2.destroyAllWindows()
cap.release()
print('Detections have been saved successfully.')
# Not in use currently
elif type == 'webcam':
inputs = tf.compat.v1.placeholder(tf.float32, [1, *_MODEL_SIZE, 3])
detections = model(inputs, training=False)
saver = tf.compat.v1.train.Saver(
tf.compat.v1.global_variables(scope='yolo_v3_model'))
with tf.compat.v1.Session() as sess:
saver.restore(sess, './weights/model.ckpt')
win_name = 'Webcam detection'
cv2.namedWindow(win_name)
cap = cv2.VideoCapture(0)
frame_size = (cap.get(cv2.CAP_PROP_FRAME_WIDTH),
cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fourcc = cv2.VideoWriter_fourcc(*'X264')
fps = cap.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter('./detections/detections.mp4', fourcc, fps,
(int(frame_size[0]), int(frame_size[1])))
try:
while True:
ret, frame = cap.read()
if not ret:
break
resized_frame = cv2.resize(frame,
dsize=_MODEL_SIZE[::-1],
interpolation=cv2.INTER_NEAREST)
detection_result = sess.run(
detections, feed_dict={inputs: [resized_frame]})
draw_frame(frame, frame_size, detection_result,
class_names, _MODEL_SIZE)
cv2.imshow(win_name, frame)
key = cv2.waitKey(1) & 0xFF
if key == ord('q'):
break
out.write(frame)
finally:
cv2.destroyAllWindows()
cap.release()
print('Detections have been saved successfully.')
else:
raise ValueError(
"Inappropriate data type. Please choose either 'video' or 'images'."
)
parser.add_argument('--mindepth', type=float, default=10.0, help='Minimum of input depths')
parser.add_argument('--maxdepth', type=float, default=1000.0, help='Maximum of input depths')
args = parser.parse_args()
# Custom object needed for inference and training
custom_objects = {'BilinearUpSampling2D': BilinearUpSampling2D, 'depth_loss_function': None}
print('Loading model...')
# Load model into GPU / CPU
model = load_model(args.model, custom_objects=custom_objects, compile=False)
print('\nModel loaded ({0}).'.format(args.model))
# Input images
inputs = load_images( glob.glob(args.input) )
print('\nLoaded ({0}) images of size {1}.'.format(inputs.shape[0], inputs.shape[1:]))
# Compute results
outputs = predict(model, inputs, minDepth=args.mindepth, maxDepth=args.maxdepth, batch_size=args.bs)
#matplotlib problem on ubuntu terminal fix
#matplotlib.use('TkAgg')
# Display results
if args.input_depth=='examples/eye/*.png':
inputs_depth = load_images( glob.glob(args.input_depth))
viz = display_images(outputs.copy(), inputs.copy(), inputs_depth.copy())
else:
viz = display_images(outputs.copy(), inputs.copy())
try:
encoder .load_weights( "models/encoder.h5" )
decoder_A.load_weights( "models/decoder_A.h5" )
decoder_B.load_weights( "models/decoder_B.h5" )
except:
pass
def save_model_weights():
encoder .save_weights( "models/encoder.h5" )
decoder_A.save_weights( "models/decoder_A.h5" )
decoder_B.save_weights( "models/decoder_B.h5" )
print( "save model weights" )
images_A = get_image_paths( "data/trump" )
images_B = get_image_paths( "data/cage" )
images_A = load_images( images_A ) / 255.0
images_B = load_images( images_B ) / 255.0
images_A += images_B.mean( axis=(0,1,2) ) - images_A.mean( axis=(0,1,2) )
print( "press 'q' to stop training and save model" )
for epoch in range(1000000):
batch_size = 64
warped_A, target_A = get_training_data( images_A, batch_size )
warped_B, target_B = get_training_data( images_B, batch_size )
loss_A = autoencoder_A.train_on_batch( warped_A, target_A )
loss_B = autoencoder_B.train_on_batch( warped_B, target_B )
print( loss_A, loss_B )
from keras.preprocessing.image import ImageDataGenerator from model import ai_model # Import each method individually for clarity purposes. from utils import load_images, save_model, save_the_images from utils import prepare_accuracy_visualisation_images, train # Prepare an array for images to be loaded into X = [] # Load a number of images from a specified folder into the X array. # 1: Batch size to load # 2: The array to save the images in. # 3: (Optional) Folder with the images (default: "Train/") batch_size = 700 load_images(batch_size, X) # Convert standard array to numpy array X = np.array(X) #, dtype=float) #float gives error, use 1.0/255 instead. # Split the loaded dataset into training and testing part # as per the given percentage (80% by default) training_percentage = 0.9 split = int(training_percentage * len(X)) # use the given percentage for training Xtrain = X[:split] #normalise the data (divide it by 255), while keeping it as float Xtrain = 1.0 / 255 * Xtrain
X, y, X_val, y_val, model_type, m, params = args
model = ModelFactory.create_model(model_type, m, **params)
model.fit(X, y)
return (model.score(X_val, y_val), model, params)
def choose_best_model(X, X_val, y, y_val, model_type, params):
p = Pool(processes=NUM_PROCESSES)
scores = p.map(_choose_slave, [(X, y, X_val, y_val, model_type, X_train.shape[0], dict(zip(params.keys(), ps))) for ps in itertools.product(*params.values())])
best_acc, best_model, best_params = max(scores)
return best_params, best_acc, best_model
if __name__ == '__main__':
t = time.time()
X, y = utils.load_hog(PPC, TRAIN_TOTAL) if HOG else utils.load_images(TRAIN_TOTAL)
print 'Done loading', str(time.time() - t)
t = time.time()
# split data
X_train, X_val, y_train, y_val = cross_validation.train_test_split(X, y, test_size=VALSIZE)
print 'Done splitting train', str(time.time() - t)
t = time.time()
# sweep hyperparameters field and pick best model
params, acc, model = choose_best_model(X_train, X_val, y_train, y_val, MODEL, PARAMS[MODEL])
# if not SVM:
# reg, acc, model = find_regularization(X_train, X_val, y_train, y_val, REGS_HOG if HOG else REGS)
# print "Best regularization strength is: " + str(reg)
# else:
# params, acc, model = choose_best_model(X_train, X_val, y_train, y_val, MODEL, PARAMS[MODEL])
def get_prediction_from_path(self,
sess,
x_data,
compatibility_multiplier=32,
tgt_size=None,
method=None,
full_prediction=False,
keep_prob=1.0):
""" Prediction of the neural network graph. """
# Load images
x_data = utils.load_images(x_data, tgt_size=tgt_size, method=method)
# Do it one by one if different sizes
if method is None:
pred = []
for x in x_data:
# Pad if required
x, pads = utils.match_size_with_pad(x,
compatibility_multiplier)
x = np.expand_dims(x, axis=0)
# Run for full mask
p = sess.run(tf.nn.softmax(self.full_mask_logits_tf),
feed_dict={
self.x_tf: x,
self.keep_prob_tf: keep_prob
})
if self.multi_head and full_prediction:
# Run for borders and untouching mask
b = sess.run(tf.nn.softmax(self.borders_logits_tf),
feed_dict={
self.x_tf: x,
self.keep_prob_tf: keep_prob
})
p = np.concatenate([p[0, :, :, 1:], b[0, :, :, 1:]], -1)
else:
p = p[0, :, :, 1]
# Unpad
pred.append(utils.unpad_image_to_original_size(p, pads))
# Do it for all the batch
else:
pred = sess.run(tf.nn.softmax(self.full_mask_logits_tf),
feed_dict={
self.x_tf: x_data,
self.keep_prob_tf: keep_prob
})
if self.multi_head and full_prediction:
borders = sess.run(tf.nn.softmax(self.borders_logits_tf),
feed_dict={
self.x_tf: x_data,
self.keep_prob_tf: keep_prob
})
pred = np.concatenate(
[pred[:, :, :, 1:], borders[:, :, :, 1:]], -1)
else:
pred = pred[:, :, :, 1:]
return pred
def load_images(self, path):
image, rect = utils.load_images(path, True)
w = rect.w / 4
h = rect.h
self.frames = [image.subsurface(x * w, 0, w, h) for x in range(0, 4)]
# -*- coding: utf-8 -*-
import os
import numpy as np
from tqdm import tqdm
import tensorflow as tf
from model import NeuralStyleTransferModel
import settings
import utils
# 创建模型
model = NeuralStyleTransferModel()
# 加载内容图片
content_image = utils.load_images(settings.CONTENT_IMAGE_PATH)
# 风格图片
style_image = utils.load_images(settings.STYLE_IMAGE_PATH)
# 计算出目标内容图片的内容特征备用
target_content_features = model([
content_image,
])['content']
# 计算目标风格图片的风格特征
target_style_features = model([
style_image,
])['style']
M = settings.WIDTH * settings.HEIGHT
N = 3
def main(type, iou_threshold, confidence_threshold, input_names):
class_names = load_class_names(_CLASS_NAMES_FILE)
n_classes = len(class_names)
model = Yolo_v3(n_classes=n_classes, model_size=_MODEL_SIZE,
max_output_size=_MAX_OUTPUT_SIZE,
iou_threshold=iou_threshold,
confidence_threshold=confidence_threshold)
if type == 'images':
batch_size = len(input_names)
batch = load_images(input_names, model_size=_MODEL_SIZE)
inputs = tf.compat.v1.placeholder(tf.float32, [batch_size, *_MODEL_SIZE, 3])
detections = model(inputs, training=False)
saver = tf.compat.v1.train.Saver(tf.compat.v1.global_variables(scope='yolo_v3_model'))
with tf.compat.v1.Session() as sess:
saver.restore(sess, './weights/model.ckpt')
detection_result = sess.run(detections, feed_dict={inputs: batch})
draw_boxes(input_names, detection_result, class_names, _MODEL_SIZE)
print('Detections have been saved successfully.')
elif type == 'video':
inputs = tf.compat.v1.placeholder(tf.float32, [1, *_MODEL_SIZE, 3])
detections = model(inputs, training=False)
saver = tf.compat.v1.train.Saver(tf.compat.v1.global_variables(scope='yolo_v3_model'))
with tf.compat.v1.Session() as sess:
saver.restore(sess, './weights/model.ckpt')
win_name = 'Video detection'
cv2.namedWindow(win_name)
cap = cv2.VideoCapture(input_names[0])
frame_size = (cap.get(cv2.CAP_PROP_FRAME_WIDTH),
cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fourcc = cv2.VideoWriter_fourcc(*'X264')
fps = cap.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter('./detections/detections.mp4', fourcc, fps,
(int(frame_size[0]), int(frame_size[1])))
try:
while True:
ret, frame = cap.read()
if not ret:
break
resized_frame = cv2.resize(frame, dsize=_MODEL_SIZE[::-1],
interpolation=cv2.INTER_NEAREST)
detection_result = sess.run(detections,
feed_dict={inputs: [resized_frame]})
draw_frame(frame, frame_size, detection_result,
class_names, _MODEL_SIZE)
cv2.imshow(win_name, frame)
key = cv2.waitKey(1) & 0xFF
if key == ord('q'):
break
out.write(frame)
finally:
cv2.destroyAllWindows()
cap.release()
print('Detections have been saved successfully.')
elif type == 'webcam':
inputs = tf.compat.v1.placeholder(tf.float32, [1, *_MODEL_SIZE, 3])
detections = model(inputs, training=False)
saver = tf.compat.v1.train.Saver(tf.compat.v1.global_variables(scope='yolo_v3_model'))
with tf.compat.v1.Session() as sess:
saver.restore(sess, './weights/model.ckpt')
win_name = 'Webcam detection'
cv2.namedWindow(win_name)
cap = cv2.VideoCapture(0)
frame_size = (cap.get(cv2.CAP_PROP_FRAME_WIDTH),
cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fourcc = cv2.VideoWriter_fourcc(*'X264')
fps = cap.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter('./detections/detections.mp4', fourcc, fps,
(int(frame_size[0]), int(frame_size[1])))
try:
while True:
ret, frame = cap.read()
if not ret:
break
resized_frame = cv2.resize(frame, dsize=_MODEL_SIZE[::-1],
interpolation=cv2.INTER_NEAREST)
detection_result = sess.run(detections,
feed_dict={inputs: [resized_frame]})
draw_frame(frame, frame_size, detection_result,
class_names, _MODEL_SIZE)
cv2.imshow(win_name, frame)
key = cv2.waitKey(1) & 0xFF
if key == ord('q'):
break
out.write(frame)
finally:
cv2.destroyAllWindows()
cap.release()
print('Detections have been saved successfully.')
else:
raise ValueError("Inappropriate data type. Please choose either 'video' or 'images'.")
def runUFRESH():
directory_x = 'Testing_Images/FRESH_upscaled/Set5'
pattern = '.bmp'
directory_y = 'Testing_Images/GT/Set5'
XpathCell = myglob(directory_x, pattern)
Xcell = load_images(XpathCell)
YpathCell = myglob(directory_y, pattern)
Ycell = load_images(YpathCell)
blocksize = [5, 5]
Psnr = np.zeros([len(Xcell)])
prepsnr = np.zeros([len(Xcell)])
for imgIdx in range(0, len(Xcell)):
t1 = time.time()
print('--------------------------------------------------------')
print('Processing image ', str(imgIdx + 1), ' of total ',
str(len(Xcell)))
Xtest = Xcell[imgIdx]
Ytest = Ycell[imgIdx]
mse = np.square((Xtest - Ytest).ravel()).mean(axis=0)
prepsnr[imgIdx] = 10 * np.log10(1 / mse)
print('PSNR before processing = ', prepsnr[imgIdx])
for stage in [1, 2]:
heir = sp.io.loadmat('pyHeirarchy4096.mat')
heirarchy = heir['heirarchy'].astype(float32)
index = heir['index'].astype(float32)
mymap = sp.io.loadmat('pyMap4096cell96.mat')
C = np.squeeze(mymap['Map'])
# Map = np.empty((C.shape[0], C[0].shape[0], C[0].shape[1]))
# for i in range(Map.shape[0]):
Map = [np.ndarray([C[0].shape[0], C[0].shape[1]])] * C.shape[0]
for i in range(len(Map)):
Map[i] = C[i].astype(float)
Xrec = np.zeros([len(Xtest), len(Xtest[0]), 4])
for rot in range(0, 4):
print(rot)
Xtestrot = np.rot90(Xtest, rot)
# Xtestrot = sp.ndimage.rotate(Xtest, 90*rot)
X = ufresh(Xtestrot, blocksize, heirarchy, index, Map)
X = backprojection_2X(X, np.rot90(Ytest, rot))
X = np.rot90(X, 4 - rot)
# X = sp.ndimage.rotate(X, 360-90*rot)
Xrec[:, :, rot] = X
Xtest = np.mean(Xrec, axis=2)
Xtest = backprojection_2X(Xtest, Ytest)
mse = np.square((Xtest - Ytest).ravel()).mean(axis=0)
Psnr[imgIdx] = 10 * np.log10(1 / mse)
print('PSNR after processing = ', Psnr[imgIdx])
t2 = time.time()
print('Elapsed time is ', str(t2 - t1))
# plt.figure()
# plt.imshow(Xtest, cmap='gray')
# plt.title('Xtest')
# plt.figure()
# plt.imshow(Ytest, cmap='gray')
# plt.title('Ytest')
# plt.show()
print('========================================================')
print('Average PSNR across all runs = ', str(Psnr.mean(axis=0)))
print('Average improvement in PSNR = ', str(
(Psnr - prepsnr).mean(axis=0)))
import test_lib
import utils
from vgg19 import Vgg19
model = np.load(test_lib.model_vgg19).item()
print("The VGG model is loaded.")
imgs_path = ["./img-airplane-224x224.jpg",
"./img-guitar-224x224.jpg",
"./img-puzzle-224x224.jpg",
"./img-tatoo-plane-224x224.jpg",
"./img-dog-224x224.jpg",
"./img-paper-plane-224x224.jpg",
"./img-pyramid-224x224.jpg",
"./img-tiger-224x224.jpg"]
imgs = utils.load_images(*imgs_path)
print("The input image(s) is loaded.")
for i, img in enumerate(imgs_path):
print("%d %s" % (i, img))
print("")
# Design the graph.
graph = tf.Graph()
with graph.as_default():
nn = Vgg19(model=model)
# Run the graph in the session.
with tf.Session(graph=graph) as sess:
tf.initialize_all_variables().run()
print("Tensorflow initialized all variables.")
#!/usr/bin/env python3
from align import FaceAlign
import matplotlib.pyplot as plt
import numpy as np
import os
from utils import load_images, save_images
fa = FaceAlign('models/landmarks.dat')
images, filenames = load_images('HBTN', as_array=False)
x = [[0.194157, 0.16926692], [0.7888591, 0.15817115], [0.4949509, 0.5144414]]
anchors = np.array(x, dtype=np.float32)
aligned = []
alin = 0
for image in images:
aligned.append(fa.align(image, np.array([36, 45, 33]), anchors, 96))
print("alin = {}".format(alin))
alin = alin + 1
aligned = np.array(aligned)
print(aligned.shape)
if not os.path.isdir('HBTNaligned'):
print(save_images('HBTNaligned', aligned, filenames))
os.mkdir('HBTNaligned')
print(save_images('HBTNaligned', aligned, filenames))
print(os.listdir('HBTNaligned'))
image = plt.imread('HBTNaligned/KirenSrinivasan.jpg')
plt.imshow(image)
plt.show()
# Get the command line parameter value.
arg_index = sys.argv.index('--bsp_out_dir')
bsp_out_dir = sys.argv[arg_index + 1]
# Check whether the --asp_out_dir command line parameter was
# provided.
asp_out_dir = None
if '--asp_out_dir' in sys.argv:
# Get the command line parameter value.
arg_index = sys.argv.index('--asp_out_dir')
asp_out_dir = sys.argv[arg_index + 1]
if bsp_columns_file is None and asp_columns_file is None:
sys.exit('One or both of the --bsp_columns_file'
' --asp_columns_file must be provided.')
images, _ = load_images(imgs_dir, extensions=('.jpg',),
img_shape=(256, 256))
patches = extract_patches(images, (16, 16), images.shape[0]*256,
randomize=False)
if asp_columns_file is not None:
with open(asp_columns_file, 'rb') as fp:
asp_columns = pickle.load(fp)
asp_activations =\
reconstruct_images(alg='asp', images=patches, columns=asp_columns,
connect_threshold=0.2,
desired_activity_mult=0.05, min_overlap=3,
img_shape=(256, 256), out_dir=asp_out_dir)
calculate_print_stats(asp_activations, alg='ASP')
save_activations(asp_activations, asp_columns_file)
if bsp_columns_file is not None:
def remove_distortion(images):
out = calibrate(images)
matrix = out['camera_matrix']
dist = out['distortion_coefficient']
undistorted_images = []
for (image, color_image) in images:
size = image.shape[::-1]
new_matrix, roi = cv.getOptimalNewCameraMatrix(matrix, dist, size,
1, size)
img = cv.undistort(color_image, matrix, dist, None, new_matrix)
undistorted_images.append(img)
return undistorted_images
if __name__ == '__main__':
args_parser = argparse.ArgumentParser()
args_parser.add_argument('folder', help='a folder wit himages\
to be processed')
args_parser.add_argument('-s', '--scale', type=float, default=0.45,
help='display scale to control window size')
args = args_parser.parse_args()
DISPLAY_SCALE = args.scale
images = load_images(args.folder)
undistorted_images = remove_distortion(images)
display_images(undistorted_images, DISPLAY_SCALE)
def launch():
seed = 1234
np.random.seed(seed)
light = Light()
light.initials()
light.file_snapshot()
light.set_seed(seed)
w, h = 28, 28
fast_test = False
test_ratio = 0.25
valid_ratio = 0.25
light.set("w", w)
light.set("h", h)
light.set("test_ratio", test_ratio)
light.set("valid_ratio", valid_ratio)
images = load_images(w=w, h=h)
X = images.reshape((-1, w*h))
# prepare
X = shuffle(X)
if fast_test is True:
max_evaluations_hp = 1
default_params = dict(
max_epochs=2
)
X = X[0:100]
else:
default_params = dict()
max_evaluations_hp = 20
default_params["batch_size"] = 128
#default_params["nb_layers"] = 1
eval_function = lambda model, X_v, _: float(model.get_reconstruction_error(X_v))
X_train_full, X_test = train_test_split(X, test_size=test_ratio)
X_train, X_valid = train_test_split(X_train_full, test_size=valid_ratio)
# show original data
#X_ = X.reshape((X.shape[0], im[0], im[1]))
#X_ = X_[0:10]
#grid_plot(X_, imshow_options={"cmap": "gray"})
#plt.savefig(dirname+"/orig.png")
#plt.show()
all_hp, all_scores = find_all_hp(
AA,
minimize_fn_with_hyperopt,
X_train,
X_valid,
None,
None,
max_evaluations=max_evaluations_hp,
default_params=default_params,
not_allowed_params=["batch_size"],
eval_function=eval_function
)
argmin = min(range(len(all_hp)), key=lambda i:all_scores[i])
best_hp, best_score = all_hp[argmin], all_scores[argmin]
best_hp.update(default_params)
aa = AA(**best_hp)
aa.fit(X_train_full, X_test)
best_model = aa
light.set("best_hp", best_hp)
light.set("best_score", best_score)
light.set("all_hp", all_hp)
light.set("all_scores", all_scores)
#light.set("best_model", light.insert_blob(best_model))
names = best_model.capsule.batch_optimizer.stats[0].keys()
stats = dict()
for name in names:
stats[name] = get_stat(name, best_model.capsule.batch_optimizer.stats)
light.set("layer_weights", light.insert_blob([layer.W.get_value() for layer in (best_model.all_layers[1:-1])]))
light.set("best_model_stats", stats)
light.set("nb_layers", aa.nb_layers * 2 - 1)
# reconstructions
R = np.arange(20)
X_test_hat = best_model.capsule.predict(X_test[R]).tolist()
light.set("reconstructions", light.insert_blob(X_test_hat))
light.endings()
import utils
import sac
import sys
if len(sys.argv) != 2:
print "Usage: ./display_saved_network.py somefile.pickle"
sys.exit(1)
fname = sys.argv[1]
f = open(fname, "r")
solution = pickle.load(f)
utils.save_as_figure((solution.W1 + solution.b1).T, "loadedW1.png")
utils.save_as_figure(solution.W2, "loadedW2.png")
images = utils.load_images("data/train-images-idx3-ubyte")
labels = utils.load_labels("data/train-labels-idx1-ubyte")
utils.save_as_figure(images[:, 0:100], "output/input.png")
patches = images[:, 0:10000]
visible_size = 28 * 28
hidden_size = 196
options = sac.SparseAutoEncoderOptions(visible_size,
hidden_size,
output_dir="output",
max_iterations=400)
network = sac.SparseAutoEncoder(options, patches)
theta = network.flatten(solution.W1, solution.W2, solution.b1, solution.b2)