def detectAlphabets(imageToRecognize):
args = parse_args()
args.val_path = imageToRecognize
# os.environ["CUDA_VISIBLE_DEVICES"] = "0"
keras.backend.tensorflow_backend.set_session(get_session())
model = keras.models.load_model(os.path.join(dir, '../snapshots/resnet50_csv_wtext.h5'), custom_objects=custom_objects)
test_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
#
# # create a generator for testing data
test_generator = CSVGenerator(
csv_data_file=args.annotations,
csv_class_file=args.classes,
image_data_generator=test_image_data_generator,
batch_size=args.batch_size
)
# index = 0
# load image
image = read_image_bgr(args.val_path)
# copy to draw on
draw = image.copy()
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# preprocess image for network
image = preprocess_image(image)
image, scale = resize_image(image)
# process image
start = time.time()
_, _, detections = model.predict_on_batch(np.expand_dims(image, axis=0))
print("processing time: ", time.time() - start)
print('detections:', detections)
# compute predicted labels and scores
predicted_labels = np.argmax(detections[0, :, 4:], axis=1)
scores = detections[0, np.arange(detections.shape[1]), 4 + predicted_labels]
print("label=", predicted_labels)
# correct for image scale
scaled_detection = detections[0, :, :4] / scale
# visualize detections
recognized = {}
plt.figure(figsize=(15, 15))
plt.axis('off')
for idx, (label, score) in enumerate(zip(predicted_labels, scores)):
if score < 0.35:
continue
b = scaled_detection[idx, :4].astype(int)
cv2.rectangle(draw, (b[0], b[1]), (b[2], b[3]), (0, 0, 255), 1)
caption = test_generator.label_to_name(label)
if caption == "equal":
caption = "="
cv2.putText(draw, caption, (b[0], b[1] - 1), cv2.FONT_HERSHEY_PLAIN, 1, (255, 255, 255), 1)
recognized[caption] = b
print(caption + ", score=" + str(score))
plt.imshow(draw)
plt.show()
return recognized, draw
def create_generators(p): # create image data generator objects train_image_data_generator = keras.preprocessing.image.ImageDataGenerator( horizontal_flip=True, ) val_image_data_generator = keras.preprocessing.image.ImageDataGenerator() train_generator = CSVGenerator( p['annotations'], p['classes'], train_image_data_generator, batch_size = p['batch-size'] ) if p['val-annotations']: validation_generator = CSVGenerator( p['val-annotations'], p['classes'], val_image_data_generator, batch_size = p['batch-size'] ) else: validation_generator = None return train_generator, validation_generator
def evaluate_generator(self,
annotations,
comet_experiment=None,
iou_threshold=0.5,
max_detections=200):
""" Evaluate prediction model using a csv fit_generator
Args:
annotations (str): Path to csv label file, labels are in the format -> path/to/image.png,x1,y1,x2,y2,class_name
iou_threshold(float): IoU Threshold to count for a positive detection (defaults to 0.5)
max_detections (int): Maximum number of bounding box predictions
comet_experiment(object): A comet experiment class objects to track
Return:
mAP: Mean average precision of the evaluated data
"""
#Format args for CSV generator
classes_file = utilities.create_classes(annotations)
arg_list = utilities.format_args(annotations, classes_file, self.config)
args = parse_args(arg_list)
#create generator
validation_generator = CSVGenerator(
args.annotations,
args.classes,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config,
shuffle_groups=False,
)
average_precisions = evaluate(validation_generator,
self.prediction_model,
iou_threshold=iou_threshold,
score_threshold=args.score_threshold,
max_detections=max_detections,
save_path=args.save_path,
comet_experiment=comet_experiment)
# print evaluation
total_instances = []
precisions = []
for label, (average_precision, num_annotations) in average_precisions.items():
print('{:.0f} instances of class'.format(num_annotations),
validation_generator.label_to_name(label),
'with average precision: {:.4f}'.format(average_precision))
total_instances.append(num_annotations)
precisions.append(average_precision)
if sum(total_instances) == 0:
print('No test instances found.')
return
print('mAP using the weighted average of precisions among classes: {:.4f}'.format(
sum([a * b for a, b in zip(total_instances, precisions)]) /
sum(total_instances)))
mAP = sum(precisions) / sum(x > 0 for x in total_instances)
print('mAP: {:.4f}'.format(mAP))
return mAP
def create_models_local(p):
test_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
test_generator = CSVGenerator(p['test_csv'], p['classes_csv'],
test_image_data_generator, 1)
model, training_model, prediction_model = create_models(
num_classes=test_generator.num_classes(), p=p)
return model, training_model, prediction_model, test_generator
def create_generators(args, preprocess_image):
"""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,
'config': args.config,
'image_min_side': args.image_min_side,
'image_max_side': args.image_max_side,
'preprocess_image': preprocess_image,
}
# create random transform generator for augmenting training data
if args.random_transform:
transform_generator = random_transform_generator(
min_rotation=-0.1,
max_rotation=0.1,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
flip_x_chance=0.5,
flip_y_chance=0.5,
)
visual_effect_generator = random_visual_effect_generator(
contrast_range=(0.9, 1.1),
brightness_range=(-.1, .1),
hue_range=(-0.05, 0.05),
saturation_range=(0.95, 1.05))
else:
transform_generator = random_transform_generator(flip_x_chance=0.5)
visual_effect_generator = None
if args.dataset_type == 'csv':
train_generator = CSVGenerator(
args.annotations,
args.classes,
transform_generator=transform_generator,
visual_effect_generator=visual_effect_generator,
**common_args)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
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 create_generators(args, group_queue):
# create image data generator objects
train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True,
vertical_flip=True,
zoom_range=0.15,
rotation_range=25)
# train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
# horizontal_flip=True
# )
val_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from keras_retinanet.preprocessing.coco import CocoGenerator
train_generator = CocoGenerator(args.coco_path,
'train2017',
train_image_data_generator,
batch_size=args.batch_size)
validation_generator = CocoGenerator(args.coco_path,
'val2017',
val_image_data_generator,
batch_size=args.batch_size)
elif args.dataset_type == 'pascal':
train_generator = PascalVocGenerator(args.pascal_path,
'trainval',
train_image_data_generator,
batch_size=args.batch_size)
validation_generator = PascalVocGenerator(args.pascal_path,
'test',
val_image_data_generator,
batch_size=args.batch_size)
elif args.dataset_type == 'csv':
train_generator = CSVGenerator(args.annotations,
args.classes,
args.mean_image,
train_image_data_generator,
batch_size=args.batch_size,
image_min_side=int(args.image_min_side),
image_max_side=int(args.image_max_side),
group_queue=group_queue)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
args.mean_image,
val_image_data_generator,
batch_size=args.batch_size)
else:
validation_generator = None
else:
raise ValueError('Invalid data type received: {}'.format(dataset_type))
return train_generator, validation_generator
def create_generators(args):
# create image data generator objects
train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True,
vertical_flip=True,
rotation_range=180,
width_shift_range=5,
height_shift_range=5,
preprocessing_function=add_noise # Kai - add noise to input
)
val_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
# Kai - may want to add noise to input as well
)
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from keras_retinanet.preprocessing.coco import CocoGenerator
train_generator = CocoGenerator(args.coco_path,
'train2017',
train_image_data_generator,
batch_size=args.batch_size)
validation_generator = CocoGenerator(args.coco_path,
'val2017',
val_image_data_generator,
batch_size=args.batch_size)
elif args.dataset_type == 'pascal':
train_generator = PascalVocGenerator(args.pascal_path,
'trainval',
train_image_data_generator,
batch_size=args.batch_size)
validation_generator = PascalVocGenerator(args.pascal_path,
'test',
val_image_data_generator,
batch_size=args.batch_size)
elif args.dataset_type == 'csv':
train_generator = CSVGenerator(args.annotations,
args.classes,
train_image_data_generator,
batch_size=args.batch_size)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
val_image_data_generator,
batch_size=args.batch_size)
else:
validation_generator = None
else:
raise ValueError('Invalid data type received: {}'.format(dataset_type))
return train_generator, validation_generator
def create_generators(args):
# create image data generator objects
train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True, )
val_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from keras_retinanet.preprocessing.coco import CocoGenerator
train_generator = CocoGenerator(args.coco_path,
'train2017',
train_image_data_generator,
batch_size=args.batch_size)
validation_generator = CocoGenerator(args.coco_path,
'val2017',
val_image_data_generator,
batch_size=args.batch_size)
elif args.dataset_type == 'pascal':
train_generator = PascalVocGenerator(args.pascal_path,
'trainval',
train_image_data_generator,
batch_size=args.batch_size)
validation_generator = PascalVocGenerator(args.pascal_path,
'test',
val_image_data_generator,
batch_size=args.batch_size)
elif args.dataset_type == 'csv':
train_generator = CSVGenerator(args.annotations,
args.classes,
train_image_data_generator,
batch_size=args.batch_size,
base_dir="./")
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
val_image_data_generator,
batch_size=args.batch_size,
base_dir="./")
else:
validation_generator = None
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return train_generator, validation_generator
def __create_generator(self, annotation_path, class_path):
train_generator = CSVGenerator(
annotation_path,
class_path,
transform_generator=self._transform_generator,
**(self._common_args))
return train_generator
def create_generators(args):
transform_generator = random_transform_generator(
min_rotation=-0.1, # radians
max_rotation=0.1,
min_translation=(-0.1, -0.1), # could be pixels or percentage
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
flip_x_chance=0.5,
flip_y_chance=0.5,
)
train_generator = AugmentedGenerator(
args.annotations,
args.classes,
transform_generator=transform_generator,
batch_size=args.batch_size,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
batch_size=args.batch_size,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side)
else:
validation_generator = None
return train_generator, validation_generator
def test_csv_generator_anchors():
anchors_dict = get_anchors_params("tests/test-data/anchors.yaml")
train_generator = CSVGenerator("tests/test-data/csv/annotations.csv",
"tests/test-data/csv/classes.csv",
transform_generator=None,
batch_size=1,
image_min_side=512,
image_max_side=512,
**anchors_dict)
inputs, targets = train_generator.next()
regreession_batch, labels_batch = targets
labels = labels_batch[0]
image = inputs[0]
anchors = anchors_for_shape(image.shape, **anchors_dict)
assert len(labels) == len(anchors)
def main():
args = parse_args(sys.argv[1:])
transform_generator = random_transform_generator(
min_rotation=-0.1,
max_rotation=0.1,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
)
generator = CSVGenerator(
args.annotations,
args.classes,
# transform_generator=transform_generator,
base_dir=args.images_dir)
os.makedirs('gen_images', exist_ok=True)
for i in range(5):
batch = next(generator)
img_ar = batch[0].reshape(batch[0].shape[1:]).astype('uint8')
img = Image.fromarray(img_ar)
img.save('gen_images/{}.jpg'.format(i + 1))
def create_generator(args, config):
""" Create generators for evaluation.
"""
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from keras_retinanet.preprocessing.coco import CocoGenerator
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
image_min_side=args.image_min_side,
image_max_side=args.image_max_side)
elif args.dataset_type == 'pascal':
validation_generator = PascalVocGenerator(
args.pascal_path,
'test',
image_min_side=args.image_min_side,
image_max_side=args.image_max_side)
elif args.dataset_type == 'csv':
validation_generator = CSVGenerator(args.annotations,
args.classes,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side)
elif args.dataset_type == 'onthefly':
validation_generator = onthefly.OnTheFlyGenerator(
args.annotations,
batch_size=args.batch_size,
base_dir=config["rgb_tile_dir"],
config=config)
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return validation_generator
def main1():
# for file in glob.glob("./snapshots/*_05.h5"):
file = './snapshots/resnet50_csv_05.h5'
# file = 'C:/Projects/OLD-keras-retinanet-master/snapshots/resnet50_csv_01.h5'
map_total = 0
for i in range(50, 100, 5):
i = i / 100
keras.backend.tensorflow_backend.set_session(get_session())
model = keras.models.load_model(file, custom_objects=custom_objects)
val_generator = CSVGenerator(
csv_data_file='c:/MTSD/Updated/test - copy.csv',
csv_class_file='c:/MTSD/Updated/classes.csv',
base_dir='c:/MTSD/Updated/detection/',
image_min_side=1440,
image_max_side=2560,
min_size=25)
# analyse_images(val_generator)
my_eval = eval.evaluate(val_generator,
model,
score_threshold=0.5,
iou_threshold=0.5,
save_path='C:/video-out/',
ground_truth=False)
print(my_eval)
print(sum(my_eval.values()) / 39)
keras.backend.clear_session()
break
def create_generator(args):
""" Create generators for evaluation.
"""
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from ..preprocessing.coco import CocoGenerator
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config)
elif args.dataset_type == 'pascal':
validation_generator = PascalVocGenerator(
args.pascal_path,
'test',
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config)
elif args.dataset_type == 'csv':
validation_generator = CSVGenerator(args.annotations,
args.classes,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config)
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return validation_generator
def create_generators(self, args, transform_generator=None):
train_generator = CSVGenerator(args.annotations,
args.classes,
transform_generator=transform_generator,
batch_size=args.batch_size)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes,
batch_size=args.batch_size)
else:
validation_generator = None
return {
"train_generator": train_generator,
"validation_generator": validation_generator
}
def __getitem__(self, index):
inputs, targets = CSVGenerator.__getitem__(self, index)
# for i,x in enumerate(inputs):
# temp = x
# temp = sk.exposure.rescale_intensity(temp,in_range=(0,255))
# temp = sk.util.random_noise(temp, var= random.uniform(0,.0005))
# temp = sk.exposure.adjust_gamma(temp,gamma=random.uniform(.5,1.5))
# inputs[i] = np.array(temp)
return inputs, targets
def create_generator():
# create image data generator objects
train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True, )
train_generator = CSVGenerator(boring_annotations_path,
boring_classes_path,
train_image_data_generator,
batch_size=batch_size)
return train_generator
def create_generator(annotations, classes):
""" Create generators for evaluation.
"""
validation_generator = CSVGenerator(
annotations,
classes,
image_min_side=800,
image_max_side=1333,
config=None,
shuffle_groups=False,
)
return validation_generator
def create_generators(train_annotations, val_annotations, class_mapping, preprocess_image, batch_size,
data_augmentation=False, base_dir=None):
if data_augmentation:
transform_generator = kr_train.random_transform_generator(
min_rotation=-0.1,
max_rotation=0.1,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
flip_x_chance=0.5,
flip_y_chance=0.5,
)
else:
transform_generator = kr_train.random_transform_generator(flip_x_chance=0.5)
# create the generators
train_generator = CSVGenerator(
train_annotations,
class_mapping,
transform_generator=transform_generator,
base_dir=base_dir,
preprocess_image=preprocess_image,
batch_size=batch_size
)
if val_annotations:
validation_generator = CSVGenerator(
val_annotations,
class_mapping,
base_dir=base_dir,
preprocess_image=preprocess_image,
batch_size=batch_size
)
else:
validation_generator = None
return train_generator, validation_generator
def create_generator(args, preprocess_image):
""" Create generators for evaluation.
"""
common_args = {
'preprocess_image': preprocess_image,
}
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from keras_retinanet.preprocessing.coco import CocoGenerator
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config,
shuffle_groups=False,
**common_args)
elif args.dataset_type == 'pascal':
validation_generator = PascalVocGenerator(
args.pascal_path,
'test',
image_extension=args.image_extension,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config,
shuffle_groups=False,
**common_args)
elif args.dataset_type == 'csv':
validation_generator = CSVGenerator(args.annotations,
args.classes,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side,
config=args.config,
shuffle_groups=False,
**common_args)
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return validation_generator
def evaluate_model(concepts, model_path, min_examples, download_data=False):
classmap = get_classmap(concepts)
if download_data:
folders = []
folders.append(test_examples)
for dir in folders:
if os.path.exists(dir):
shutil.rmtree(dir)
os.makedirs(dir)
download_annotations(min_examples, concepts, classmap, good_users, img_folder, train_annot_file, valid_annot_file, split=0)
'''
Initializing model for eval
'''
model = load_model(model_path, backbone_name='resnet50')
model = convert_model(model)
temp = pd.DataFrame(list(zip(classmap.values(), classmap.keys())))
temp.to_csv('classmap.csv',index=False, header=False)
test_generator = CSVGenerator(
valid_annot_file,
'classmap.csv',
shuffle_groups=False,
batch_size=batch_size
)
best_f1, best_thresh = f1_evaluation(test_generator, model, save_path=test_examples)
total_f1 = 0
for concept, f1 in best_f1.items():
print("Concept: " + classmap[concept])
print("F1 Score: " + str(f1))
print("Confidence Threshold: " + str(best_thresh[concept]))
print("")
total_f1 += f1
print("Average F1: " + str(total_f1/len(best_f1)))
print("Find evaluation examples in: " + test_examples)
'''
weights = None
imagenet_weights = True
batch_size = 1
image_min_side = 225
image_max_side = 300
backbone_model = models.backbone('resnet50')
freeze_backbone = False
common_args = {
'batch_size': batch_size,
'image_min_side': image_min_side,
'image_max_side': image_max_side,
'preprocess_image': backbone_model.preprocess_image,
}
train_generator = CSVGenerator(annotations_path, classes_path, **common_args)
if validations_path != '':
validation_generator = CSVGenerator(validations_path, classes_path,
**common_args)
else:
validation_generator = None
if snapshot is not None:
print('Loading model, this may take a second...')
model = models.load_model(snapshot, backbone_name=backbone)
training_model = model
prediction_model = retinanet_bbox(model=model)
else:
weights = weights
# default to imagenet if nothing else is specified
if weights is None and imagenet_weights:
def create_generator():
validation_generator = CSVGenerator(
"./wurenji/helmet/pre/test.csv",
"./wurenji/helmet/pre/class.csv",
)
return validation_generator
def create_generators(args, preprocess_image):
""" 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,
'config': args.config,
'image_min_side': args.image_min_side,
'image_max_side': args.image_max_side,
'preprocess_image': preprocess_image,
}
# create random transform generator for augmenting training data
if args.random_transform:
transform_generator = random_transform_generator(
min_rotation=-0.1,
max_rotation=0.1,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
min_shear=-0.1,
max_shear=0.1,
min_scaling=(0.9, 0.9),
max_scaling=(1.1, 1.1),
flip_x_chance=0.5,
flip_y_chance=0.5,
)
else:
transform_generator = random_transform_generator(flip_x_chance=0.5)
if args.dataset_type == 'csv':
train_generator = CSVGenerator(args.annotations,
args.classes,
transform_generator=transform_generator,
**common_args)
if args.val_annotations:
validation_generator = CSVGenerator(args.val_annotations,
args.classes, **common_args)
else:
validation_generator = None
#region +mk@sail
elif args.dataset_type == 'sail':
if 'steps' in dir(args):
train_generator = SAIL_Generator(args.annotations,
args.classes,
transform_generator=None,
force_steps_per_epoch=args.steps,
dataset_type='train',
**common_args)
else:
train_generator = SAIL_Generator(args.annotations,
args.classes,
transform_generator=None,
dataset_type='train',
**common_args)
if args.val_annotations:
if 'val_steps' in dir(args):
validation_generator = SAIL_Generator(args.val_annotations,
args.classes,
val_steps=args.val_steps,
dataset_type='val',
transform_generator=None,
**common_args)
else:
validation_generator = SAIL_Generator(args.val_annotations,
args.classes,
dataset_type='val',
transform_generator=None,
**common_args)
else:
validation_generator = None
#endregion +mk@sail
else:
raise ValueError('Invalid data type received: {}'.format(
args.dataset_type))
return train_generator, validation_generator
# parse arguments
args = parse_args()
train_path = os.path.abspath(args.train_path)
classes = os.path.abspath(args.classes_path)
val_path = os.path.abspath(args.val_path)
# create image data generator objects
train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True, )
# create a generator for training data
train_generator = CSVGenerator(
csv_data_file=train_path,
csv_class_file=classes,
image_data_generator=train_image_data_generator,
batch_size=args.batch_size,
image_min_side=args.min_side,
image_max_side=args.max_side)
test_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
# create a generator for testing data
test_generator = CSVGenerator(
csv_data_file=val_path,
csv_class_file=classes,
image_data_generator=test_image_data_generator,
batch_size=args.batch_size,
image_min_side=args.min_side,
image_max_side=args.max_side)
default=0.1,
type=float)
return parser.parse_args()
if __name__ == '__main__':
# parse arguments
args = parse_args()
# make sure keras is the minimum required version
check_keras_version()
# optionally choose specific GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# create the model
print('Loading model, this may take a second...')
model = keras.models.load_model(args.model, custom_objects=custom_objects)
# create image data generator object
test_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
# create a generator for testing data
test_generator = CSVGenerator(args.csv, args.cls_file,
test_image_data_generator)
evaluate_csv(test_generator, model, args.score_threshold)
def create_generators(args, preprocess_image):
""" 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,
'image_min_side' : args.image_min_side,
'image_max_side' : args.image_max_side,
'preprocess_image' : preprocess_image,
}
# create random transform generator for augmenting training data
if args.random_transform:
transform_generator = random_transform_generator(
min_rotation=-0.05,
max_rotation=0.05,
min_translation=(-0.1, -0.1),
max_translation=(0.1, 0.1),
#min_shear=-0.1,
#max_shear=0.1,
min_scaling=(0.8, 0.8),
max_scaling=(1.2, 1.2),
flip_x_chance=0.5,
#flip_y_chance=0.5,
)
else:
transform_generator = random_transform_generator(flip_x_chance=0.5)
if args.dataset_type == 'coco':
# import here to prevent unnecessary dependency on cocoapi
from ..preprocessing.coco import CocoGenerator
train_generator = CocoGenerator(
args.coco_path,
'train2017',
transform_generator=transform_generator,
**common_args
)
validation_generator = CocoGenerator(
args.coco_path,
'val2017',
**common_args
)
elif args.dataset_type == 'pascal':
train_generator = PascalVocGenerator(
args.pascal_path,
'trainval',
transform_generator=transform_generator,
**common_args
)
validation_generator = PascalVocGenerator(
args.pascal_path,
'test',
**common_args
)
elif args.dataset_type == 'csv':
train_generator = CSVGenerator(
args.annotations,
args.classes,
transform_generator=transform_generator,
**common_args
)
if args.val_annotations:
validation_generator = CSVGenerator(
args.val_annotations,
args.classes,
**common_args
)
else:
validation_generator = None
elif args.dataset_type == 'oid':
train_generator = OpenImagesGenerator(
args.main_dir,
subset='train',
version=args.version,
labels_filter=args.labels_filter,
annotation_cache_dir=args.annotation_cache_dir,
parent_label=args.parent_label,
transform_generator=transform_generator,
**common_args
)
validation_generator = OpenImagesGenerator(
args.main_dir,
subset='validation',
version=args.version,
labels_filter=args.labels_filter,
annotation_cache_dir=args.annotation_cache_dir,
parent_label=args.parent_label,
**common_args
)
elif args.dataset_type == 'kitti':
train_generator = KittiGenerator(
args.kitti_path,
subset='train',
transform_generator=transform_generator,
**common_args
)
validation_generator = KittiGenerator(
args.kitti_path,
subset='val',
**common_args
)
else:
raise ValueError('Invalid data type received: {}'.format(args.dataset_type))
return train_generator, validation_generator
# parse arguments
args = parse_args()
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# create image data generator objects
train_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True, )
# create a generator for training data
train_generator = CSVGenerator(
csv_data_file=args.train_path,
csv_class_file=args.classes,
image_data_generator=train_image_data_generator,
batch_size=args.batch_size)
if args.val_path:
test_image_data_generator = keras.preprocessing.image.ImageDataGenerator(
)
# create a generator for testing data
test_generator = CSVGenerator(
csv_data_file=args.val_path,
csv_class_file=args.classes,
image_data_generator=test_image_data_generator,
batch_size=args.batch_size)
else:
test_generator = None
max_rotation=0.1,
min_translation=(-0.2, -0.2),
max_translation=(0.2, 0.2),
min_shear=-0.2,
max_shear=0.2,
min_scaling=(0.75, 0.75),
max_scaling=(-1.5, 1.5),
flip_x_chance=0.3,
flip_y_chance=0.3,
)
train_generator = CSVGenerator(
TRAIN_DATA,
LABELS,
base_dir='/input/deepfashion_data',
batch_size=1,
image_max_side=img_max_side,
image_min_side=img_min_side,
# transform_generator=transform_generator
)
validation_generator = CSVGenerator(
VAL_DATA,
LABELS,
base_dir='/input/deepfashion_data',
batch_size=1,
image_min_side=img_min_side,
image_max_side=img_max_side
)
weights = download_imagenet('resnet50')
