def _main_(args):
config_path = args.conf
weights_path = args.weights
image_path = args.input
use_camera = args.real_time
videos_format = [".mp4", "avi"]
keras.backend.tensorflow_backend.set_session(get_session())
with open(config_path) as config_buffer:
config = json.load(config_buffer)
if weights_path == '':
weights_path = config['train']['pretrained_weights"']
###################
# Make the model
###################
yolo = YOLO(backend=config['model']['backend'],
input_size=(config['model']['input_size_h'],
config['model']['input_size_w']),
labels=config['model']['labels'],
anchors=config['model']['anchors'],
gray_mode=config['model']['gray_mode'])
#########################
# Load trained weights
#########################
yolo.load_weights(weights_path)
###########################
# Predict bounding boxes
###########################
if use_camera:
video_reader = cv2.VideoCapture(int(image_path))
pbar = tqdm()
while True:
pbar.update(1)
ret, frame = video_reader.read()
if not ret:
break
boxes = yolo.predict(frame)
frame = draw_boxes(frame, boxes, config['model']['labels'])
cv2.imshow("frame", frame)
key = cv2.waitKey(1)
if key == ord("q") or key == 27:
break
pbar.close()
elif os.path.splitext(image_path)[1] in videos_format:
file, ext = os.path.splitext(image_path)
video_out = '{}_detected.avi'.format(file)
video_reader = cv2.VideoCapture(image_path)
nb_frames = int(video_reader.get(cv2.CAP_PROP_FRAME_COUNT))
frame_h = int(video_reader.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_w = int(video_reader.get(cv2.CAP_PROP_FRAME_WIDTH))
print(video_out)
video_writer = cv2.VideoWriter(video_out,
cv2.VideoWriter_fourcc(*'XVID'), 50.0,
(frame_w, frame_h))
for _ in tqdm(range(nb_frames)):
_, image = video_reader.read()
boxes = yolo.predict(
image,
iou_threshold=config['valid']['iou_threshold'],
score_threshold=config['valid']['score_threshold'])
image = draw_boxes(image, boxes, config['model']['labels'])
video_writer.write(np.uint8(image))
video_reader.release()
video_writer.release()
else:
if os.path.isfile(image_path):
image = cv2.imread(image_path)
boxes = yolo.predict(
image,
iou_threshold=config['valid']['iou_threshold'],
score_threshold=config['valid']['score_threshold'])
image = draw_boxes(image, boxes, config['model']['labels'])
print(len(boxes), 'boxes are found')
cv2.imwrite(image_path[:-4] + '_detected' + image_path[-4:], image)
else:
detected_images_path = os.path.join(image_path, "detected")
if not os.path.exists(detected_images_path):
os.mkdir(detected_images_path)
images = list(list_images(image_path))
for fname in tqdm(images):
image = cv2.imread(fname)
boxes = yolo.predict(image)
image = draw_boxes(image, boxes, config['model']['labels'])
fname = os.path.basename(fname)
cv2.imwrite(os.path.join(image_path, "detected", fname), image)
def _main_(args):
config_path = args.conf
with open(config_path) as config_buffer:
config = json.loads(config_buffer.read())
if config['backup']['create_backup']:
config = create_backup(config)
keras.backend.tensorflow_backend.set_session(get_session())
#path for the training and validation dataset
datasetTrainPath = os.path.join(args.folder,"train")
datasetValPath = os.path.join(args.folder,"val")
for folder in [datasetTrainPath, datasetValPath]:
if not os.path.isdir(folder):
raise Exception("{} doesn't exist!".format(folder))
classesTrain = next(os.walk(datasetTrainPath))[1]
classesVal = next(os.walk(datasetValPath))[1]
if not classesVal == classesTrain:
raise Exception("The training and validation classes must be the same!")
else:
folders = classesTrain
#training configuration
epochs = config['train']['nb_epochs']
batchSize = config['train']['batch_size']
width = config['model']['input_size_w']
height = config['model']['input_size_h']
depth = 3 if config['model']['gray_mode'] == False else 1
#config keras generators
if len(folders) == 2: #if just have 2 classes, the model will have a binary output
classes = 1
else:
classes = len(folders)
#count all samples
imagesTrainPaths = []
imagesValPaths = []
for folder in folders:
imagesTrainPaths+=list(list_images(os.path.join(datasetTrainPath, folder)))
imagesValPaths+=list(list_images(os.path.join(datasetValPath, folder)))
generator_config = {
'IMAGE_H' : height,
'IMAGE_W' : width,
'IMAGE_C' : depth,
'BATCH_SIZE' : batchSize
}
#callbacks
model_name = config['train']['saved_weights_name']
checkPointSaverBest=ModelCheckpoint(model_name, monitor='val_acc', verbose=1,
save_best_only=True, save_weights_only=False, mode='auto', period=1)
ckp_model_name = os.path.splitext(model_name)[1]+"_ckp.h5"
checkPointSaver=ModelCheckpoint(ckp_model_name, verbose=1,
save_best_only=False, save_weights_only=False, period=10)
tb=TensorBoard(log_dir=config['train']['tensorboard_log_dir'], histogram_freq=0, batch_size=batchSize, write_graph=True,
write_grads=False, write_images=False, embeddings_freq=0, embeddings_layer_names=None, embeddings_metadata=None)
#create the classification model
# make the feature extractor layers
if depth == 1:
input_size = (height, width, 1)
input_image = Input(shape=input_size)
else:
input_size = (height, width, 3)
input_image = Input(shape=input_size)
feature_extractor = import_feature_extractor(config['model']['backend'], input_size)
train_generator = BatchGenerator(imagesTrainPaths,
generator_config,
norm=feature_extractor.normalize,
jitter=True)
val_generator = BatchGenerator(imagesValPaths,
generator_config,
norm=feature_extractor.normalize,
jitter=False)
features = feature_extractor.extract(input_image)
# make the model head
output = Conv2D(classes, (1, 1), padding="same")(features)
output = BatchNormalization()(output)
output = LeakyReLU(alpha=0.1)(output)
output = GlobalAveragePooling2D()(output)
output = Activation("sigmoid")(output) if classes == 1 else Activation("softmax")(output)
if config['train']['pretrained_weights'] != "":
model = load_model(config['model']['pretrained_weights'] )
else:
model = Model(input_image, output)
opt = Adam()
model.compile(loss="binary_crossentropy" if classes == 1 else "categorical_crossentropy",
optimizer=opt,metrics=["accuracy"])
model.summary()
model.fit_generator(
train_generator,
steps_per_epoch=len(imagesTrainPaths)//batchSize,
epochs=epochs,
validation_data=val_generator,
validation_steps=len(imagesValPaths)//batchSize,
callbacks=[checkPointSaverBest,checkPointSaver,tb],
workers=12,
max_queue_size=40)
"""
this callback has the purpose to do a very specific job that imgaug can't do easily, for example in this example
the callback changes the background imagem from the original one, using a random picture from kitti dataset
"""
from sys import path
path.append("..")
from keras_yolov2.utils import list_images
import cv2
IMAGES_PATH = "C:\\datasets\\kitti\\data_object_image_2\\training\\image_2"
images = list(list_images(IMAGES_PATH))
counter = 0
def aug_callback(image, instance):
"""
instance dict structure:
{
'object': [
{'xmin': int, 'xmax': int, 'ymin': int, 'ymax': int, 'name': str},
.
.
.
{'xmin': int, 'xmax': int, 'ymin': int, 'ymax': int, 'name': str},
],
'filename': str,
'width': int,
'height': int
}
:param image: [np.array]
:param instance: [dict]