def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
'batch_size': args.batch_size,
'phi': args.phi,
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == 'pascal':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator(args.pascal_path,
'trainval',
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
validation_generator = PascalVocGenerator(args.pascal_path,
'val',
skip_difficult=True,
shuffle_groups=False,
**common_args)
elif args.dataset_type == 'csv':
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(args.annotations_path,
args.classes_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args)
if args.val_annotations_path:
validation_generator = CSVGenerator(args.val_annotations_path,
args.classes_path,
shuffle_groups=False,
**common_args)
else:
validation_generator = None
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return train_generator, validation_generator
def main(args=None):
if len(sys.argv) is 3:
model_path = str(sys.argv[1])
dataset_path = str(sys.argv[2])
else:
print(
"Pass model path and dataset path in respectively as command line argument"
)
exit()
from generators.pascal import PascalVocGenerator
from model import efficientdet
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
phi = 4
weighted_bifpn = False
common_args = {
'batch_size': 1,
'phi': phi,
}
test_generator = PascalVocGenerator(dataset_path,
'test',
shuffle_groups=False,
skip_truncated=False,
skip_difficult=True,
**common_args)
model_path = model_path
input_shape = (test_generator.image_size, test_generator.image_size)
anchors = test_generator.anchors
num_classes = test_generator.num_classes()
model, prediction_model = efficientdet(phi=phi,
num_classes=num_classes,
weighted_bifpn=weighted_bifpn)
prediction_model.load_weights(model_path, by_name=True)
average_precisions = evaluate(test_generator,
prediction_model,
visualize=False)
# compute per class average precision
total_instances = []
precisions = []
for label, (average_precision,
num_annotations) in average_precisions.items():
print('{:.0f} instances of class'.format(num_annotations),
test_generator.label_to_name(label),
'with average precision: {:.4f}'.format(average_precision))
total_instances.append(num_annotations)
precisions.append(average_precision)
mean_ap = sum(precisions) / sum(x > 0 for x in total_instances)
print('mAP: {:.4f}'.format(mean_ap))
def create_generators(train=False):
train_generator = PascalVocGenerator(image_dir=cfg.IMAGE_DIR,
annotation_dir=cfg.ANNOTATION_DIR,
text_file=cfg.TRAIN_TEXT,
skip_difficult=True,
classes=cfg.CLASSES,
multi_scale=cfg.MULTI_SCALE,
**cfg.COMMON_ARGS)
validation_generator = PascalVocGenerator(
image_dir=cfg.IMAGE_DIR,
annotation_dir=cfg.ANNOTATION_DIR,
text_file=cfg.VAL_TEXT,
skip_difficult=True,
classes=cfg.CLASSES,
shuffle_groups=False,
**cfg.COMMON_ARGS,
train_data=False)
return train_generator, validation_generator
def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
'batch_size': args.batch_size,
'phi': args.phi,
'detect_text': args.detect_text,
'detect_quadrangle': args.detect_quadrangle
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == 'pascal':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator(
args.pascal_path,
'trainval',
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
image_extension=".png",
**common_args
)
validation_generator = PascalVocGenerator(
args.pascal_path,
'val',
skip_difficult=True,
shuffle_groups=False,
image_extension=".png",
**common_args
)
elif args.dataset_type == 'csv':
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(
args.annotations_path,
args.classes_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args
)
if args.val_annotations_path:
validation_generator = CSVGenerator(
args.val_annotations_path,
args.classes_path,
shuffle_groups=False,
**common_args
)
else:
validation_generator = None
elif args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from generators.coco import CocoGenerator
train_generator = CocoGenerator(
args.coco_path,
'train2017',
misc_effect=misc_effect,
visual_effect=visual_effect,
group_method='random',
**common_args
)
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
shuffle_groups=False,
**common_args
)
else:
raise ValueError('Invalid data type received: {}'.format(args.dataset_type))
return train_generator, validation_generator
if __name__ == '__main__':
from generators.pascal import PascalVocGenerator
from model import efficientdet
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
phi = 1
weighted_bifpn = False
common_args = {
'batch_size': 1,
'phi': phi,
}
test_generator = PascalVocGenerator('datasets/VOC2007',
'test',
shuffle_groups=False,
skip_truncated=False,
skip_difficult=True,
**common_args)
model_path = 'checkpoints/2019-12-03/pascal_05_0.6283_1.1975_0.8029.h5'
input_shape = (test_generator.image_size, test_generator.image_size)
anchors = test_generator.anchors
num_classes = test_generator.num_classes()
model, prediction_model = efficientdet(phi=phi,
num_classes=num_classes,
weighted_bifpn=weighted_bifpn)
prediction_model.load_weights(model_path, by_name=True)
average_precisions = evaluate(test_generator,
prediction_model,
visualize=False)
# compute per class average precision
total_instances = []
def main():
generator = PascalVocGenerator(cfg.IMAGE_DIR,
cfg.ANNOTATION_DIR,
cfg.TEST_TEXT,
classes=cfg.CLASSES,
skip_difficult=True,
train_data=False)
num_classes = generator.num_classes()
classes = list(generator.classes.keys())
colors = [
np.random.randint(0, 256, 3).tolist() for i in range(num_classes)
]
model = centernet(num_classes,
score_threshold=cfg.SCORE_THRESHOLD,
nms=cfg.NMS,
flip_test=cfg.FLIP_TEST,
training=False)
model.load_weights(model_path, by_name=True, skip_mismatch=True)
for i in range(10):
image = generator.load_image(i)
#cv2.imwrite("./results/{}_o.jpg".format(i), image)
src_image = image.copy()
c = np.array([image.shape[1] / 2., image.shape[0] / 2.],
dtype=np.float32)
s = max(image.shape[0], image.shape[1]) * 1.0
tgt_w = generator.input_size
tgt_h = generator.input_size
image = generator.preprocess_image(image,
c,
s,
tgt_w=tgt_w,
tgt_h=tgt_h)
if cfg.FLIP_TEST:
flipped_image = image[:, ::-1]
inputs = np.stack([image, flipped_image], axis=0)
else:
inputs = np.expand_dims(image, axis=0)
detections = model.predict_on_batch(inputs)[0]
scores = detections[:, 4]
indices = np.where(scores > cfg.SCORE_THRESHOLD)[0]
detections = detections[indices]
detections_copy = detections.copy()
detections = detections.astype(np.float64)
trans = get_affine_transform(c, s, (tgt_w // 4, tgt_h // 4), inv=1)
for j in range(detections.shape[0]):
detections[j, 0:2] = affine_transform(detections[j, 0:2], trans)
detections[j, 2:4] = affine_transform(detections[j, 2:4], trans)
detections[:, [0, 2]] = np.clip(detections[:, [0, 2]], 0,
src_image.shape[1])
detections[:, [1, 3]] = np.clip(detections[:, [1, 3]], 0,
src_image.shape[0])
for detection in detections:
xmin = int(round(detection[0]))
ymin = int(round(detection[1]))
xmax = int(round(detection[2]))
ymax = int(round(detection[3]))
score = '{:.4f}'.format(detection[4])
class_id = int(detection[5])
color = colors[class_id]
class_name = classes[class_id]
label = '-'.join([class_name, score])
ret, baseline = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX,
0.5, 1)
cv2.rectangle(src_image, (xmin, ymin), (xmax, ymax), color, 1)
cv2.rectangle(src_image, (xmin, ymax - ret[1] - baseline),
(xmin + ret[0], ymax), color, -1)
cv2.putText(src_image, label, (xmin, ymax - baseline),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1)
#cv2.imwrite("./results/{}_r.jpg".format(i), src_image)
cv2.imshow('image', src_image)
cv2.waitKey(0)
self.crop_prob = crop_prob
self.translate_prob = translate_prob
def __call__(self, image, boxes):
image, boxes = rotate(image, boxes, prob=self.rotate_prob)
image, boxes = crop(image, boxes, prob=self.crop_prob)
image, boxes = translate(image, boxes, prob=self.translate_prob)
return image, boxes
if __name__ == '__main__':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator('datasets/VOC0712',
'trainval',
skip_difficult=True,
anchors_path='voc_anchors_416.txt',
batch_size=1)
misc_effect = MiscEffect()
for i in range(train_generator.size()):
image = train_generator.load_image(i)
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
annotations = train_generator.load_annotations(i)
boxes = annotations['bboxes']
for box in boxes.astype(np.int32):
cv2.rectangle(image, (box[0], box[1]), (box[2], box[3]),
(0, 0, 255), 2)
src_image = image.copy()
cv2.namedWindow('src_image', cv2.WINDOW_NORMAL)
cv2.imshow('src_image', src_image)
image, boxes = misc_effect(image, boxes)
from generators.pascal import PascalVocGenerator
from model import efficientdet
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
phi = 1
weighted_bifpn = False
common_args = {
'batch_size': 1,
'phi': phi,
}
test_generator = PascalVocGenerator(
'datasets/VOC2007',
'test',
shuffle_groups=False,
skip_truncated=False,
skip_difficult=True,
**common_args
)
model_path = 'checkpoints/2019-12-03/pascal_05_0.6283_1.1975_0.8029.h5'
input_shape = (test_generator.image_size, test_generator.image_size)
anchors = test_generator.anchors
num_classes = test_generator.num_classes()
model, prediction_model = efficientdet(phi=phi, num_classes=num_classes, weighted_bifpn=weighted_bifpn)
prediction_model.load_weights(model_path, by_name=True)
average_precisions = evaluate(test_generator, prediction_model, visualize=False)
# compute per class average precision
total_instances = []
precisions = []
for label, (average_precision, num_annotations) in average_precisions.items():
print('{:.0f} instances of class'.format(num_annotations), test_generator.label_to_name(label),
border_value=self.border_value)
image, boxes = flipx(image, boxes, prob=self.flip_prob)
image, boxes = crop(image, boxes, prob=self.crop_prob)
image, boxes = translate(image,
boxes,
prob=self.translate_prob,
border_value=self.border_value)
return image, boxes
if __name__ == '__main__':
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator('datasets/VOC0712',
'trainval',
skip_difficult=True,
batch_size=1,
shuffle_groups=False)
misc_effect = MiscEffect()
for i in range(train_generator.size()):
image = train_generator.load_image(i)
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
annotations = train_generator.load_annotations(i)
boxes = annotations['bboxes']
for box in boxes.astype(np.int32):
cv2.rectangle(image, (box[0], box[1]), (box[2], box[3]),
(0, 0, 255), 2)
src_image = image.copy()
# cv2.namedWindow('src_image', cv2.WINDOW_NORMAL)
cv2.imshow('src_image', src_image)
# image, boxes = misc_effect(image, boxes)
from generators.pascal import PascalVocGenerator
from models.resnet import centernet
import cv2
import os
import numpy as np
import time
from generators.utils import affine_transform, get_affine_transform
import os.path as osp
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
generator = PascalVocGenerator(
'datasets/VOC2007',
'test',
shuffle_groups=False,
skip_truncated=False,
skip_difficult=True,
)
model_path = 'checkpoints/2019-11-10/pascal_81_1.5415_3.0741_0.6860_0.7057_0.7209_0.7290.h5'
num_classes = generator.num_classes()
classes = list(generator.classes.keys())
flip_test = True
nms = True
keep_resolution = False
score_threshold = 0.1
colors = [np.random.randint(0, 256, 3).tolist() for i in range(num_classes)]
model, prediction_model, debug_model = centernet(
num_classes=num_classes,
nms=nms,
flip_test=flip_test,
freeze_bn=True,
score_threshold=score_threshold)
hm_pred, wh_pred, reg_pred, hm_true, wh_true, reg_true, reg_mask, indices = args
hm_loss = focal_loss(hm_pred, hm_true)
wh_loss = 0.1 * reg_l1_loss(wh_pred, wh_true, indices, reg_mask)
reg_loss = reg_l1_loss(reg_pred, reg_true, indices, reg_mask)
total_loss = hm_loss + wh_loss + reg_loss
return total_loss
if __name__ == '__main__':
from generators.pascal import PascalVocGenerator
from models.resnet import centernet
import numpy as np
generator = PascalVocGenerator('datasets/VOC0712',
'train',
skip_difficult=True,
shuffle_groups=False,
batch_size=1)
model, prediction_model, debug_model = centernet(num_classes=20)
debug_model.load_weights(
'checkpoints/2019-11-06/pascal_31_1.0370_10.7204.h5',
by_name=True,
skip_mismatch=True)
sess = tf.Session()
for inputs, targets in generator:
image_input, hm_true, wh_true, reg_true, reg_mask, indices = inputs
hm_pred, wh_pred, reg_pred = debug_model.predict(image_input)
np.save('debug/1106/hm_true', hm_true)
np.save('debug/1106/wh_true', wh_true)
np.save('debug/1106/reg_true', reg_true)
def create_generators(args):
"""
Create generators for training and validation.
Args
args: parseargs object containing configuration for generators.
preprocess_image: Function that preprocesses an image for the network.
"""
common_args = {
"batch_size": args.batch_size,
"phi": args.phi,
"detect_text": args.detect_text,
"detect_quadrangle": args.detect_quadrangle,
}
# create random transform generator for augmenting training data
if args.random_transform:
misc_effect = MiscEffect()
visual_effect = VisualEffect()
else:
misc_effect = None
visual_effect = None
if args.dataset_type == "pascal":
from generators.pascal import PascalVocGenerator
train_generator = PascalVocGenerator(
args.pascal_path,
"trainval",
skip_difficult=True,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args,
)
validation_generator = PascalVocGenerator(
args.pascal_path,
"val",
skip_difficult=True,
shuffle_groups=False,
**common_args,
)
elif args.dataset_type == "csv":
from generators.csv_ import CSVGenerator
train_generator = CSVGenerator(
args.annotations_path,
args.classes_path,
misc_effect=misc_effect,
visual_effect=visual_effect,
**common_args,
)
if args.val_annotations_path:
validation_generator = CSVGenerator(
args.val_annotations_path,
args.classes_path,
shuffle_groups=False,
**common_args,
)
else:
validation_generator = None
elif args.dataset_type == "coco":
# import here to prevent unnecessary dependency on cocoapi
from generators.coco import CocoGenerator
train_generator = CocoGenerator(
args.coco_path,
"train2017",
misc_effect=misc_effect,
visual_effect=visual_effect,
group_method="random",
**common_args,
)
validation_generator = CocoGenerator(args.coco_path,
"val2017",
shuffle_groups=False,
**common_args)
else:
raise ValueError("Invalid data type received: {}".format(
args.dataset_type))
return train_generator, validation_generator
from generators.pascal import PascalVocGenerator
from models.resnet import centernet
import cv2
import os
import numpy as np
import time
from generators.utils import affine_transform, get_affine_transform
import os.path as osp
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
generator = PascalVocGenerator(
r'D:\datasets\voc_dataset',
'trainval',
shuffle_groups=False,
skip_truncated=False,
skip_difficult=True,
)
model_path = r'C:\work\keras-CenterNet\checkpoints\2021-04-21\pascal_01_153.2941_16.5124.h5'
num_classes = generator.num_classes()
classes = list(generator.classes.keys())
flip_test = True
nms = True
keep_resolution = False
score_threshold = 0.1
colors = [np.random.randint(0, 256, 3).tolist() for i in range(num_classes)]
model, prediction_model, debug_model = centernet(num_classes=num_classes,
nms=nms,
flip_test=flip_test,
freeze_bn=True,
score_threshold=score_threshold)
prediction_model.load_weights(model_path, by_name=True, skip_mismatch=True)
from generators.csv import CSVGenerator
from model import efficientdet
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
phi = 1
weighted_bifpn = False
common_args = {
'batch_size': 1,
'phi': phi,
}
test_generator = PascalVocGenerator(
'datasets/config_folder/dataset/test.csv',
'datasets/config_folder/dataset/classes.csv',
base_dir="D:/Study\Masters Data/Masters Thesis/HSU/EfficientDet-master",
detect_quadrangle=False,
detect_text=False,
**kwargs)
model_path = 'checkpoints/2020-06-21 (MD B1)/csv_100_0.1140_0.7599.h5'
input_shape = (test_generator.image_size, test_generator.image_size)
anchors = test_generator.anchors
num_classes = test_generator.num_classes()
model, prediction_model = efficientdet(phi=phi,
num_classes=num_classes,
weighted_bifpn=weighted_bifpn)
prediction_model.load_weights(model_path, by_name=True)
average_precisions = evaluate(test_generator,
prediction_model,
visualize=False)
# compute per class average precision