def main():
# load some VOC2007 images for test
#image = Image.open("000001.jpg")
#boxes = np.array([[48,240,195,371,11],[8,12,352,498,14]])
image = Image.open("000004.jpg")
boxes = np.array([[13,311,84,362,6],[362,330,500,389,6],[235,328,334,375,6],[175,327,252,364,6],[139,320,189,359,6],[108,325,150,353,6],[84,323,121,350,6]])
#image = Image.open("000010.jpg")
#boxes = np.array([[87,97,258,427,12],[133,72,245,284,14]])
classes = boxes[:, -1]
scores = [1.0]*len(classes)
class_names = get_classes('../../configs/voc_classes.txt')
colors = get_colors(class_names)
image_origin = draw_boxes(np.array(image, dtype='uint8'), boxes[:, :4], classes, scores, class_names, colors)
image, boxes = random_rotate(image, boxes, prob=1.0)
image = draw_boxes(np.array(image, dtype='uint8'), boxes[:, :4], classes, scores, class_names, colors)
Image.fromarray(image_origin).show()
Image.fromarray(image).show()
def get_ground_truth_data(annotation_line, input_shape, augment=True, max_boxes=100):
'''random preprocessing for real-time data augmentation'''
line = annotation_line.split()
image = Image.open(line[0])
image_size = image.size
model_input_size = tuple(reversed(input_shape))
boxes = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])
if not augment:
new_image, padding_size, offset = letterbox_resize(image, target_size=model_input_size, return_padding_info=True)
image_data = np.array(new_image)
image_data = normalize_image(image_data)
# reshape boxes
boxes = reshape_boxes(boxes, src_shape=image_size, target_shape=model_input_size, padding_shape=padding_size, offset=offset)
if len(boxes)>max_boxes:
boxes = boxes[:max_boxes]
# fill in box data
box_data = np.zeros((max_boxes,5))
if len(boxes)>0:
box_data[:len(boxes)] = boxes
return image_data, box_data
# random resize image and crop|padding to target size
image, padding_size, padding_offset = random_resize_crop_pad(image, target_size=model_input_size)
# random horizontal flip image
image, horizontal_flip = random_horizontal_flip(image)
# random adjust brightness
image = random_brightness(image)
# random adjust color level
image = random_chroma(image)
# random adjust contrast
image = random_contrast(image)
# random adjust sharpness
image = random_sharpness(image)
# random convert image to grayscale
image = random_grayscale(image)
# random do normal blur to image
#image = random_blur(image)
# random do motion blur to image
#image = random_motion_blur(image, prob=0.2)
# random vertical flip image
image, vertical_flip = random_vertical_flip(image)
# random distort image in HSV color space
# NOTE: will cost more time for preprocess
# and slow down training speed
#image = random_hsv_distort(image)
# reshape boxes based on augment
boxes = reshape_boxes(boxes, src_shape=image_size, target_shape=model_input_size, padding_shape=padding_size, offset=padding_offset, horizontal_flip=horizontal_flip, vertical_flip=vertical_flip)
# random rotate image and boxes
image, boxes = random_rotate(image, boxes)
# random add gridmask augment for image and boxes
image, boxes = random_gridmask(image, boxes)
if len(boxes)>max_boxes:
boxes = boxes[:max_boxes]
# prepare image & box data
image_data = np.array(image)
image_data = normalize_image(image_data)
box_data = np.zeros((max_boxes,5))
if len(boxes)>0:
box_data[:len(boxes)] = boxes
return image_data, box_data