def create_model(
input_shape,
anchors,
num_classes,
load_pretrained=True,
freeze_body=2,
weights_path="keras_yolo3/model_data/yolo_weights.h5",
):
"""create the training model"""
K.clear_session() # get a new session
image_input = Input(shape=(None, None, 3))
h, w = input_shape
num_anchors = len(anchors)
y_true = [
Input(
shape=(
h // {0: 32, 1: 16, 2: 8}[l],
w // {0: 32, 1: 16, 2: 8}[l],
num_anchors // 3,
num_classes + 5,
)
)
for l in range(3)
]
model_body = yolo_body(image_input, num_anchors // 3, num_classes)
print(
"Create YOLOv3 model with {} anchors and {} classes.".format(
num_anchors, num_classes
)
)
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print("Load weights {}.".format(weights_path))
if freeze_body in [1, 2]:
# Freeze darknet53 body or freeze all but 3 output layers.
num = (185, len(model_body.layers) - 3)[freeze_body - 1]
for i in range(num):
model_body.layers[i].trainable = False
print(
"Freeze the first {} layers of total {} layers.".format(
num, len(model_body.layers)
)
)
model_loss = Lambda(
yolo_loss,
output_shape=(1,),
name="yolo_loss",
arguments={
"anchors": anchors,
"num_classes": num_classes,
"ignore_thresh": 0.5,
},
)([*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
weights_path='keras_yolo3/model_data/yolo_weights.h5'):
'''create the training model
Parameters:
input_shape = [416,416]
num_class = 1 '''
K.clear_session() # get a new session
image_input = Input(shape=(None, None, 3))
h, w = input_shape
num_anchors = len(anchors)
y_true = [Input(shape=(h // {0: 32, 1: 16, 2: 8}[l], w // {0: 32, 1: 16, 2: 8}[l], \
num_anchors // 3, num_classes + 5)) for l in range(3)]
model_body = yolo_body(image_input, num_anchors // 3, num_classes) # get yolo body
print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print('Load weights {}.'.format(weights_path))
if freeze_body in [1, 2]:
# Freeze darknet53 body or freeze all but 3 output layers.
num = (185, len(model_body.layers) - 3)[freeze_body - 1]
for i in range(num): model_body.layers[i].trainable = False
print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))
model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
[*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model
def create_model(is_tiny,
input_shape,
anchors,
n_classes,
load_pretrained=True,
freeze_body=2,
weights_path='model/keras_yolo3/model_data/yolo_weights.h5'):
K.clear_session() # get a new session
img = Input(shape=(None, None, 3))
h, w = input_shape
n_anchors = len(anchors)
if not is_tiny:
y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
n_anchors//3, n_classes+5)) for l in range(3)]
model_body = yolo_body(img, n_anchors // 3, n_classes)
ignore_thresh = 0.5
else: # 'tiny'
y_true = [Input(shape=(h//{0:32, 1:16}[l], w//{0:32, 1:16}[l],\
n_anchors//2, n_classes+5)) for l in range(2)]
model_body = tiny_yolo_body(img, n_anchors // 2, n_classes)
ignore_thresh = 0.7
print(
f'Create YOLOv3 model with {n_anchors} anchors and {n_classes} classes'
)
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print(f'Load weights from {weights_path}')
if freeze_body in [1, 2]:
# Freeze darknet53 body or freeze all but 3 output layers.
if not is_tiny:
num = (185, len(model_body.layers) - 3)[freeze_body - 1]
else:
num = (20, len(model_body.layers) - 2)[freeze_body - 1]
for i in range(num):
model_body.layers[i].trainable = False
print(
f'Freeze the first {num} layers of total {model_body.layers} layers.'
)
model_loss = Lambda(yolo_loss,
output_shape=(1, ),
name='yolo_loss',
arguments={
'anchors': anchors,
'num_classes': n_classes,
'ignore_thresh': ignore_thresh
})([*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model
def generate(self):
model_path = self.model_path
assert model_path.endswith(
'.h5'), 'Keras model or weights must be a .h5 file.'
# Load model, or construct model and load weights.
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
is_tiny_version = num_anchors == 6 # default setting
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = tiny_yolo_body(Input(shape=(None, None, 3)), num_anchors // 2, num_classes) \
if is_tiny_version else yolo_body(Input(shape=(None, None, 3)), num_anchors // 3, num_classes)
self.yolo_model.load_weights(
self.model_path) # make sure model, anchors and classes match
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors / len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
np.random.seed(10101) # Fixed seed for consistent colors across runs.
np.random.shuffle(
self.colors) # Shuffle colors to decorrelate adjacent classes.
np.random.seed(None) # Reset seed to default.
# Generate output tensor targets for filtered bounding boxes.
self.input_image_shape = K.placeholder(shape=(2, ))
if self.gpu_num >= 2:
self.yolo_model = multi_gpu_model(self.yolo_model,
gpus=self.gpu_num)
boxes, scores, classes = yolo_eval(self.yolo_model.output,
self.anchors,
len(self.class_names),
self.input_image_shape,
score_threshold=self.score,
iou_threshold=self.iou)
return boxes, scores, classes
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
weights_path='model_data/yolo_weights.h5'):
'''create the training model'''
K.clear_session() # get a new session
image_input = Input(shape=(None, None, 3))
h, w = input_shape
num_anchors = len(anchors)
y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
num_anchors//3, num_classes+5)) for l in range(3)]
model_body = yolo_body(image_input, num_anchors//3, num_classes)
print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print('Load weights {}.'.format(weights_path))
if freeze_body in [1, 2]:
# Freeze darknet53 body or freeze all but 3 output layers.
num = (185, len(model_body.layers)-3)[freeze_body-1]
for i in range(num): model_body.layers[i].trainable = False
print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))
# get output of second last layers and create bottleneck model of it
out1=model_body.layers[246].output
out2=model_body.layers[247].output
out3=model_body.layers[248].output
bottleneck_model = Model([model_body.input, *y_true], [out1, out2, out3])
# create last layer model of last layers from yolo model
in0 = Input(shape=bottleneck_model.output[0].shape[1:].as_list())
in1 = Input(shape=bottleneck_model.output[1].shape[1:].as_list())
in2 = Input(shape=bottleneck_model.output[2].shape[1:].as_list())
last_out0=model_body.layers[249](in0)
last_out1=model_body.layers[250](in1)
last_out2=model_body.layers[251](in2)
model_last=Model(inputs=[in0, in1, in2], outputs=[last_out0, last_out1, last_out2])
model_loss_last =Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
[*model_last.output, *y_true])
last_layer_model = Model([in0,in1,in2, *y_true], model_loss_last)
model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
[*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model, bottleneck_model, last_layer_model
