def data_generator(annotation_lines,
batch_size,
input_shape,
anchors,
num_classes,
random=False):
'''data generator for fit_generator'''
n = len(annotation_lines)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
if i == 0:
np.random.shuffle(annotation_lines)
# box contains (x1,y1,x2,y2,class_label)
image, box = get_random_data(annotation_lines[i],
input_shape,
random=random)
image_data.append(image)
box_data.append(box)
i = (i + 1) % n
image_data = np.array(image_data)
# Collects boxes for a whole batch
box_data = np.array(box_data)
# box needs to be converted to model output format
# y_true shape = (batch_size, 14, 14, 3, 55) for first detection layer
# y_true is an array of true_outputs of 3 detection layers
y_true = preprocess_true_boxes(box_data, input_shape, anchors,
num_classes)
yield [image_data, *y_true], np.zeros(batch_size)
def data_generator(annotation_lines, batch_size, input_shape, anchors,
num_classes):
"""
Data generator for fit_generator function
:param annotation_lines:
:param batch_size:
:param input_shape:
:param anchors:
:param num_classes:
:return:
"""
n = len(annotation_lines)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
if i == 0:
np.random.shuffle(annotation_lines)
image, box = get_random_data(annotation_lines[i],
input_shape,
random=True)
image_data.append(image)
box_data.append(box)
i = (i + 1) % n
image_data = np.array(image_data)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors,
num_classes)
yield [image_data, *y_true], np.zeros(batch_size)
def bottleneck_generator(annotation_lines, batch_size, input_shape, anchors, num_classes, bottlenecks):
n = len(annotation_lines)
i = 0
while True:
box_data = []
b0=np.zeros((batch_size,bottlenecks[0].shape[1],bottlenecks[0].shape[2],bottlenecks[0].shape[3]))
b1=np.zeros((batch_size,bottlenecks[1].shape[1],bottlenecks[1].shape[2],bottlenecks[1].shape[3]))
b2=np.zeros((batch_size,bottlenecks[2].shape[1],bottlenecks[2].shape[2],bottlenecks[2].shape[3]))
for b in range(batch_size):
_, box = get_random_data(annotation_lines[i], input_shape, random=False, proc_img=False)
box_data.append(box)
b0[b]=bottlenecks[0][i]
b1[b]=bottlenecks[1][i]
b2[b]=bottlenecks[2][i]
i = (i+1) % n
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
yield [b0, b1, b2, *y_true], np.zeros(batch_size)
def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes, random=True, verbose=False):
'''data generator for fit_generator'''
n = len(annotation_lines)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
if i==0 and random:
np.random.shuffle(annotation_lines)
image, box = get_random_data(annotation_lines[i], input_shape, random=random)
image_data.append(image)
box_data.append(box)
i = (i+1) % n
image_data = np.array(image_data)
if verbose:
print("Progress: ",i,"/",n)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
yield [image_data, *y_true], np.zeros(batch_size)
def data_generator(annotation, batch_size, input_shape, anchors, n_classes):
'''data generator for fit_generator'''
n = len(annotation)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
if i == 0:
np.random.shuffle(annotation)
image, box = get_random_data(annotation[i],
input_shape,
random=True)
image_data.append(image)
box_data.append(box)
i = (i + 1) % n
image_data = np.array(image_data)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors,
n_classes)
yield [image_data,
*y_true], np.zeros(batch_size) # produce a sequence of values
