def generate_anchors(self, image_shape):
anchor_params = None
if self.config and 'anchor_parameters' in self.config:
anchor_params = parse_anchor_parameters(self.config)
return anchors_for_shape(image_shape,
anchor_params=anchor_params,
shapes_callback=self.compute_shapes)
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# Set modified tf session to avoid using the GPUs
keras.backend.tensorflow_backend.set_session(get_session())
# optionally load config parameters
anchor_parameters = None
if args.config:
args.config = read_config_file(args.config)
if 'anchor_parameters' in args.config:
anchor_parameters = parse_anchor_parameters(args.config)
# load the model
model = models.load_model(args.model_in, backbone_name=args.backbone)
# check if this is indeed a training model
models.check_training_model(model)
# convert the model
model = models.convert_model(
model,
nms=args.nms,
class_specific_filter=args.class_specific_filter,
anchor_params=anchor_parameters)
# save model
model.save(args.model_out)
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# optionally load config parameters
if args.config:
args.config = read_config_file(args, 'debug')
# make sure keras is the minimum required version
check_keras_version()
# create the generator
generator = create_generator(args)
# optionally load anchor parameters
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
# create the display window
#cv2.namedWindow('Image', cv2.WINDOW_NORMAL)
if args.loop:
while run(generator, args, anchor_params=anchor_params):
pass
else:
run(generator, args, anchor_params=anchor_params)
def create_models(backbone_retinanet, num_classes, weights, num_gpus=0, freeze_backbone=False, lr=1e-5, config=None):
"""
Creates three models (model, training_model, prediction_model).
Args
backbone_retinanet : A function to call to create a retinanet model with a given backbone.
num_classes : The number of classes to train.
weights : The weights to load into the model.
num_gpus : The number of GPUs to use for training.
freeze_backbone : If True, disables learning for the backbone.
config : Config parameters, None indicates the default configuration.
Returns
model : The base model. This is also the model that is saved in snapshots.
training_model : The training model. If num_gpus=0, this is identical to model.
prediction_model : The model wrapped with utility functions to perform object detection (applies regression values and performs NMS).
"""
modifier = freeze_model if freeze_backbone else None
# load anchor parameters, or pass None (so that defaults will be used)
anchor_params = None
num_anchors = None
if config and 'anchor_parameters' in config:
anchor_params = parse_anchor_parameters(config)
num_anchors = anchor_params.num_anchors()
# Keras recommends initialising a multi-gpu model on the CPU to ease weight sharing, and to prevent OOM errors.
# optionally wrap in a parallel model
if num_gpus > 1:
from keras.utils import multi_gpu_model
with tf.device('/cpu:0'):
model = model_with_weights(backbone_retinanet(num_classes,
# num_anchors=num_anchors,
modifier=modifier),
weights=weights, skip_mismatch=True)
training_model = multi_gpu_model(model, gpus=num_gpus)
else:
model = model_with_weights(backbone_retinanet(num_classes,
# num_anchors=num_anchors,
modifier=modifier),
weights=weights, skip_mismatch=True)
training_model = model
# make prediction model
# prediction_model = None
prediction_model = fsaf_bbox(model=model)
# compile model
training_model.compile(
loss={
'cls_loss': lambda y_true, y_pred: y_pred,
'regr_loss': lambda y_true, y_pred: y_pred,
},
# optimizer=keras.optimizers.adam(lr=lr, clipnorm=0.001)
optimizer=keras.optimizers.adam(lr=1e-4)
)
return model, training_model, prediction_model
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# optionally load config parameters
if args.config:
args.config = read_config_file(args, 'evaluation')
#print("----------------------------------")
#print("ARGUMENTS IN CONFIG FILE:")
#for sec in args.config.sections():
#print(sec, "=", dict(args.config.items(sec)))
#print("----------------------------------")
# for arg in vars(args):
# print(arg, "=", getattr(args, arg))
# exit()
# make sure keras is the minimum required version
check_keras_version()
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# make save path if it doesn't exist
if args.save_path is not None and not os.path.exists(args.save_path):
os.makedirs(args.save_path)
# create the generator
generator = create_generator(args)
# optionally load anchor parameters
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
# load the model
print('Loading model, this may take a second...')
model = models.load_model(args.model, backbone_name=args.backbone)
# optionally convert the model
if args.convert_model:
model = models.convert_model(model, anchor_params=anchor_params)
# print model summary
# print(model.summary())
# layer_outputs = []
# layer_names = ['res2c_relu', # C2
# 'res3b3_relu', # C3
# 'res4b22_relu', # C4
# 'P2', # P2
# 'P3', # P3
# 'P4', # P4
# # 'regression_submodel', # Subreg
# # 'classification_submodel', # SubClas
# 'regression', # Regression
# 'classification'] # Classification
#
# for layer in model.layers:
# if layer.name in layer_names:
# print('------------------------------------------------------------------------------------------------------------------')
# print('Layer found: ', layer.name)
# print('\tOutput:', layer.output)
# print('------------------------------------------------------------------------------------------------------------------')
# layer_outputs.append(layer.output)
#
# image = preprocess_image(generator.load_image(0))
# image, scale = resize_image(image, args.image_min_side, args.image_max_side)
#
# activation_model = keras.Model(inputs=model.input, outputs=layer_outputs)
# activations = activation_model.predict(np.expand_dims(image, axis=0))
#
# def display_activation(activations, col_size, row_size, act_index):
# activation = activations[act_index]
# activation_index=0
# fig, ax = plt.subplots(row_size, col_size, figsize=(row_size*2.5,col_size*1.5))
# for row in range(0,row_size):
# for col in range(0,col_size):
# ax[row][col].imshow(activation[0, :, :, activation_index], cmap='gray')
# activation_index += 1
# plt.savefig('layer_{}.png'.format(layer_names[act_index]))
#
# display_activation(activations, 8, 8, 0)
# display_activation(activations, 8, 8, 1)
# display_activation(activations, 8, 8, 2)
# display_activation(activations, 8, 8, 3)
# display_activation(activations, 8, 8, 4)
# display_activation(activations, 8, 8, 5)
#
# exit()
# start evaluation
if args.dataset_type == 'coco':
from ..utils.coco_eval import evaluate_coco
evaluate_coco(generator, model, args.score_threshold)
else:
average_precisions = evaluate(generator,
model,
iou_threshold=args.iou_threshold,
score_threshold=args.score_threshold,
max_detections=args.max_detections,
save_path=args.save_path,
mask_base_path=args.mask_folder)
# print evaluation
total_instances = []
precisions = []
F1s = []
for label, (recall, precision, F1, average_precision,
num_annotations) in average_precisions.items():
print('{:.0f} instances of class'.format(num_annotations),
generator.label_to_name(label),
'with average precision: {:.4f}'.format(average_precision),
'precision: {:.4f}'.format(precision),
'recall: {:.4f}'.format(recall),
'and F1-score: {:.4f}'.format(F1))
total_instances.append(num_annotations)
precisions.append(average_precision)
F1s.append(F1)
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)))
print('mAP: {:.4f}'.format(
sum(precisions) / sum(x > 0 for x in total_instances)))
print('mF1: {:.4f}'.format(
sum(F1s) / sum(x > 0 for x in total_instances)))
def main(args=None):
# create object that stores backbone information
backbone = models.backbone(args.backbone)
# create the generators
train_generator, validation_generator = create_generators(
args, backbone.preprocess_image)
# create the model
if args.snapshot is not None:
print('Loading model, this may take a second...')
model = models.load_model(args.snapshot, backbone_name=args.backbone)
training_model = model
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
prediction_model = retinanet_bbox(model=model,
anchor_params=anchor_params)
# compile model
training_model.compile(
loss={
'regression': losses.iou_loss(args.loss, args.loss_weight),
'classification': losses.focal(),
'centerness': losses.bce(),
},
optimizer=keras.optimizers.Adam(lr=1e-5)
# optimizer=keras.optimizers.sgd(lr=1e-5, momentum=0.9, decay=1e-5, nesterov=True)
)
else:
weights = args.weights
# default to imagenet if nothing else is specified
if weights is None and args.imagenet_weights:
weights = backbone.download_imagenet()
print('Creating model, this may take a second...')
model, training_model, prediction_model = create_models(
backbone_retinanet=backbone.retinanet,
num_classes=train_generator.num_classes(),
weights=weights,
num_gpus=args.num_gpus,
freeze_backbone=args.freeze_backbone,
lr=args.lr,
config=args.config,
args=args)
parallel_model = multi_gpu_model(training_model, gpus=2)
parallel_model.compile(loss={
'regression':
losses.iou_loss(args.loss, args.loss_weight),
'classification':
losses.focal(),
'centerness':
losses.bce(),
},
optimizer=keras.optimizers.Adam(lr=1e-4))
# print model summary
# print(model.summary())
# this lets the generator compute backbone layer shapes using the actual backbone model
if 'vgg' in args.backbone or 'densenet' in args.backbone:
train_generator.compute_shapes = make_shapes_callback(model)
if validation_generator:
validation_generator.compute_shapes = train_generator.compute_shapes
# create the callbacks
callbacks = create_callbacks(
model,
training_model,
prediction_model,
validation_generator,
args,
)
if not args.compute_val_loss:
validation_generator = None
# start training
parallel_model.fit_generator(generator=train_generator,
steps_per_epoch=len(train_generator),
epochs=args.epochs,
verbose=1,
callbacks=callbacks,
validation_data=validation_generator)
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# make sure keras is the minimum required version
check_keras_version()
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# make save path if it doesn't exist
if args.save_path is not None and not os.path.exists(args.save_path):
os.makedirs(args.save_path)
# optionally load config parameters
if args.config:
args.config = read_config_file(args.config)
# create the generator
generator = create_generator(args)
# optionally load anchor parameters
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
# load the model
print('Loading model, this may take a second...')
model = models.load_model(args.model, backbone_name=args.backbone)
# optionally convert the model
if args.convert_model:
model = models.convert_model(model, anchor_params=anchor_params)
# print model summary
# print(model.summary())
# start evaluation
if args.dataset_type == 'coco':
from ..utils.coco_eval import evaluate_coco
evaluate_coco(generator, model, args.score_threshold)
else:
average_precisions = evaluate(generator,
model,
iou_threshold=args.iou_threshold,
score_threshold=args.score_threshold,
max_detections=args.max_detections,
save_path=args.save_path)
# print evaluation
total_instances = []
precisions = []
for label, (average_precision,
num_annotations) in average_precisions.items():
print('{:.0f} instances of class'.format(num_annotations),
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)))
print('mAP: {:.4f}'.format(
sum(precisions) / sum(x > 0 for x in total_instances)))
return precisions, total_instances
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# create object that stores backbone information
backbone = models.backbone(args.backbone)
# make sure keras is the minimum required version
check_keras_version()
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# optionally load config parameters
if args.config:
args.config = read_config_file(args.config)
# create the generators
train_generator, validation_generator = create_generators(
args, backbone.preprocess_image)
# create the model
if args.snapshot is not None:
print('Loading model, this may take a second...')
model = models.load_model(args.snapshot, backbone_name=args.backbone)
training_model = model
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
prediction_model = retinanet_bbox(model=model,
anchor_params=anchor_params)
# compile model
training_model.compile(
loss={
'regression': losses.iou(),
'classification': losses.focal(),
'centerness': losses.bce(),
},
optimizer=keras.optimizers.adam(lr=1e-5)
# optimizer=keras.optimizers.sgd(lr=1e-5, momentum=0.9, decay=1e-5, nesterov=True)
)
else:
weights = args.weights
# default to imagenet if nothing else is specified
if weights is None and args.imagenet_weights:
weights = backbone.download_imagenet()
print('Creating model, this may take a second...')
model, training_model, prediction_model = create_models(
backbone_retinanet=backbone.retinanet,
num_classes=train_generator.num_classes(),
weights=weights,
num_gpus=args.num_gpus,
freeze_backbone=args.freeze_backbone,
lr=args.lr,
config=args.config)
# print model summary
# print(model.summary())
# this lets the generator compute backbone layer shapes using the actual backbone model
if 'vgg' in args.backbone or 'densenet' in args.backbone:
train_generator.compute_shapes = make_shapes_callback(model)
if validation_generator:
validation_generator.compute_shapes = train_generator.compute_shapes
# create the callbacks
callbacks = create_callbacks(
model,
training_model,
prediction_model,
validation_generator,
args,
)
if not args.compute_val_loss:
validation_generator = None
# start training
return training_model.fit_generator(
generator=train_generator,
initial_epoch=0,
steps_per_epoch=args.steps,
epochs=args.epochs,
verbose=1,
callbacks=callbacks,
workers=args.workers,
use_multiprocessing=args.multiprocessing,
max_queue_size=args.max_queue_size,
validation_data=validation_generator)
def create_models(fl_gamma,
fl_alpha,
r_weight,
c_weight,
p_weight,
train_type,
sample_t,
backbone_retinanet,
num_classes,
weights,
class_weights,
loss_weights,
multi_gpu=0,
freeze_backbone=False,
lr=1e-5,
config=None):
""" Creates three models (model, training_model, prediction_model).
Args
backbone_retinanet : A function to call to create a retinanet model with a given backbone.
num_classes : The number of classes to train.
weights : The weights to load into the model.
multi_gpu : The number of GPUs to use for training.
freeze_backbone : If True, disables learning for the backbone.
config : Config parameters, None indicates the default configuration.
Returns
model : The base model. This is also the model that is saved in snapshots.
training_model : The training model. If multi_gpu=0, this is identical to model.
prediction_model : The model wrapped with utility functions to perform object detection (applies regression values and performs NMS).
"""
modifier = freeze_model if freeze_backbone else None
# load anchor parameters, or pass None (so that defaults will be used)
anchor_params = None
num_anchors = None
if config and 'anchor_parameters' in config:
anchor_params = parse_anchor_parameters(config)
num_anchors = anchor_params.num_anchors()
# Keras recommends initialising a multi-gpu model on the CPU to ease weight sharing, and to prevent OOM errors.
# optionally wrap in a parallel model
if multi_gpu > 1:
from keras.utils import multi_gpu_model
with tf.device('/cpu:0'):
model = model_with_weights(backbone_retinanet(
num_classes, num_anchors=num_anchors, modifier=modifier),
weights=weights,
skip_mismatch=True)
training_model = multi_gpu_model(model, gpus=multi_gpu)
else:
model = model_with_weights(backbone_retinanet(num_classes,
train_type,
num_anchors=num_anchors,
modifier=modifier),
weights=weights,
skip_mismatch=True)
training_model = model
# make prediction model
prediction_model = retinanet_bbox(model=model, anchor_params=anchor_params)
if train_type == "single":
# compile model
training_model.compile(
loss={
'regression':
losses.smooth_l1(r_weight),
## HERE THE INPUT ARGUMENTS CAN BE GIVEN: default focal(alpha=0.25, gamma=2.0)
## gamma: the actual "focusing parameter"
'classification':
losses.focal(c_weight, fl_alpha, fl_gamma, class_weights)
},
optimizer=keras.optimizers.adam(lr=lr, clipnorm=0.001),
#sample_weight_mode="temporal",
#sample_weights=sample_t
)
elif train_type == "multi":
training_model.compile(
loss={
'regression':
losses.smooth_l1(r_weight),
## HERE THE INPUT ARGUMENTS CAN BE GIVEN: default focal(alpha=0.25, gamma=2.0)
## gamma: the actual "focusing parameter"
'classification_artefact':
losses.focal(c_weight, fl_alpha, fl_gamma),
'classification_polyp':
losses.focal2(p_weight, fl_alpha, fl_gamma)
},
optimizer=keras.optimizers.adam(lr=lr, clipnorm=0.001)
#loss_weights=loss_weights
)
return model, training_model, prediction_model
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# create object that stores backbone information
#backbone = models.backbone(args.backbone)
backbone = models.backbone(args.backbone)
# make sure keras is the minimum required version
check_keras_version()
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# optionally load config parameters
if args.config:
args.config = read_config_file(args.config)
# create the generators
#print(args)
train_generator, validation_generator = create_generators(
args, backbone.preprocess_image)
# Log configs
#run.log('batch-size', args.batch_size)
#run.log('gamma', args.fl_gamma)
#run.log('alpha', args.fl_alpha)
#run.log('lr', args.lr)
#run.log('neg-overlap', args.neg_overlap)
#run.log('pos-overlap', args.pos_overlap)
#run.log('fpn-layers', args.fpn_layers)
if args.class_weights is not None:
if args.class_weights == "cw1":
polyp_weight = 0.25
#class_weights = {'classification': {0:a_w, 1:a_w, 2:a_w, 3:a_w, 4:a_w, 5:a_w, 6:a_w, 7:polyp_weight}, 'regression': {0:0.25, 1:0.25, 2:0.25, 3:0.25}}
#class_weights = {'classification': [polyp_weight, a_w, a_w, a_w, a_w, a_w, a_w, a_w]}
elif args.class_weights == "cw2":
polyp_weight = 0.5
elif args.class_weights == "cw3":
polyp_weight = 0.75
a_w = (1 - polyp_weight) / 7
#class_weights = {'classification': [polyp_weight, a_w, a_w, a_w, a_w, a_w, a_w, a_w]}
class_weights = [polyp_weight, a_w, a_w, a_w, a_w, a_w, a_w, a_w]
else:
class_weights = None
if args.loss_weights is None:
loss_weights = [1, 1]
elif args.loss_weights == "lw0":
loss_weights = [1, 1, 1]
elif args.loss_weights == "lw1":
loss_weights = [1, 1, 3]
elif args.loss_weights == "lw2":
loss_weights = [1, 1, 10]
elif args.loss_weights == "lw3":
loss_weights = [1, 1, 20]
# create the model
if args.snapshot is not None:
print('Loading model, this may take a second...')
model = models.load_model(os.path.join(args.data_dir, args.snapshot),
backbone_name=args.backbone)
training_model = model
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
prediction_model = retinanet_bbox(model=model,
anchor_params=anchor_params)
else:
if args.weights is None and args.imagenet_weights:
weights = backbone.download_imagenet()
else:
weights = args.weights
# default to imagenet if nothing else is specified
## SO the file that is downloaded is actually only the weights
## this means that I should be able to use --weights to give it my own model
sample_test = np.array([[0.25, 0.25, 0.25, 0.25, 0, 0, 0, 0],
[10, 10, 10, 10, 10, 10, 10, 10]])
print('Creating model, this may take a second...')
model, training_model, prediction_model = create_models(
backbone_retinanet=backbone.retinanet,
num_classes=train_generator.num_classes(),
weights=weights,
class_weights=class_weights,
loss_weights=loss_weights,
multi_gpu=args.multi_gpu,
freeze_backbone=args.freeze_backbone,
lr=args.lr,
config=args.config,
fl_gamma=args.fl_gamma,
fl_alpha=args.fl_alpha,
c_weight=args.c_weight,
r_weight=args.r_weight,
p_weight=args.p_weight,
train_type=args.train_type,
sample_t=sample_test)
# print model summary
#print(model.summary())
# this lets the generator compute backbone layer shapes using the actual backbone model
if 'vgg' in args.backbone or 'densenet' in args.backbone:
train_generator.compute_shapes = make_shapes_callback(model)
if validation_generator:
validation_generator.compute_shapes = train_generator.compute_shapes
# create the callbacks
callbacks = create_callbacks(
model,
training_model,
prediction_model,
validation_generator,
args,
)
# Use multiprocessing if workers > 0
if args.workers > 0:
use_multiprocessing = True
else:
use_multiprocessing = False
temp_df = pd.read_csv(
os.path.join(args.data_dir, args.annotations),
names=["image_path", "x1", "y1", "x2", "y2", "object_id"])
im_count = len(set(list(temp_df.image_path)))
# start training
training_model.fit_generator(generator=train_generator,
steps_per_epoch=int(im_count /
args.batch_size),
epochs=args.epochs,
verbose=1,
callbacks=callbacks,
workers=args.workers,
use_multiprocessing=use_multiprocessing,
max_queue_size=args.max_queue_size
#class_weight=class_weights
)
def main(args=None):
# parse arguments
if args is None:
args = sys.argv[1:]
args = parse_args(args)
# optionally load config parameters
if args.config:
args.config = read_config_file(args, 'training')
# print("----------------------------------")
# print("ARGUMENTS IN CONFIG FILE:")
# for sec in args.config.sections():
# print(sec, "=", dict(args.config.items(sec)))
# print("----------------------------------")
#
# for arg in vars(args):
# print(arg, "=", getattr(args, arg))
# exit()
# create object that stores backbone information
backbone = models.backbone(args.backbone)
# make sure keras is the minimum required version
check_keras_version()
# optionally choose specific GPU
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
keras.backend.tensorflow_backend.set_session(get_session())
# create the generators
train_generator, validation_generator = create_generators(
args, backbone.preprocess_image)
# # Debuging
# for i in range(1):
# inputs, targets = train_generator.__getitem__(i)
# exit()
# create the model
if args.snapshot is not None:
print('Loading model, this may take a second...')
model = models.load_model(args.snapshot, backbone_name=args.backbone)
# When using as a second step for fine-tuning
for layer in model.layers:
layer.trainable = True
training_model = model
anchor_params = None
if args.config and 'anchor_parameters' in args.config:
anchor_params = parse_anchor_parameters(args.config)
prediction_model = retinanet_bbox(model=model,
anchor_params=anchor_params)
###################################################################################### BRUNO
# compile model
training_model.compile(loss={
'regression': losses.smooth_l1(),
'classification': losses.focal()
},
optimizer=keras.optimizers.adam(lr=args.lr,
clipnorm=0.001))
else:
weights = args.weights
# default to imagenet if nothing else is specified
if weights is None and args.imagenet_weights:
weights = backbone.download_imagenet()
print('Creating model, this may take a second...')
model, training_model, prediction_model = create_models(
backbone_retinanet=backbone.retinanet,
num_classes=train_generator.num_classes(),
weights=weights,
multi_gpu=args.multi_gpu,
freeze_backbone=args.freeze_backbone,
lr=args.lr,
config=args.config)
# Print model design
# print(model.summary())
# print(training_model.summary())
# plot_model(model, to_file='model_plot.png', show_shapes=True, show_layer_names=True)
# exit()
# Get the number of samples in the training and validations datasets.
train_size = train_generator.size()
val_size = validation_generator.size()
print('Train on {} samples, val on {} samples, with batch size {}.'.format(
train_size, val_size, args.batch_size))
# this lets the generator compute backbone layer shapes using the actual backbone model
if 'vgg' in args.backbone or 'densenet' in args.backbone:
train_generator.compute_shapes = make_shapes_callback(model)
if validation_generator:
validation_generator.compute_shapes = train_generator.compute_shapes
# create the callbacks
callbacks = create_callbacks(
model,
training_model,
prediction_model,
validation_generator,
train_size,
[1e-6, 1e-4],
args,
)
# Use multiprocessing if workers > 0
if args.workers > 0:
use_multiprocessing = True
else:
use_multiprocessing = False
# check to see if we are attempting to find an optimal learning rate
# before training for the full number of epochs
if args.find_lr:
# initialize the learning rate finder and then train with learning
# rates ranging from 1e-10 to 1e+1
print("[INFO] Finding learning rate...")
lrf = LearningRateFinder(training_model)
lrf.find(train_generator,
1e-10,
1e+1,
stepsPerEpoch=np.ceil((train_size / float(args.batch_size))),
batchSize=args.batch_size)
# plot the loss for the various learning rates and save the
# resulting plot to disk
lrf.plot_loss()
plt.savefig("lrfind_plot.png")
# save values into a csv file
lrf.save_csv("lr_loss.csv")
# gracefully exit the script so we can adjust our learning rates
# in the config and then train the network for our full set of
# epochs
print("[INFO] Learning rate finder complete")
print("[INFO] Examine plot and adjust learning rates before training")
sys.exit(0)
# Number of epochs and steps for training new layers
n_epochs = 350
steps = train_size // args.batch_size
# start training
training_model.fit_generator(generator=train_generator,
validation_data=validation_generator,
steps_per_epoch=steps,
epochs=n_epochs,
verbose=1,
callbacks=callbacks,
workers=args.workers,
use_multiprocessing=use_multiprocessing,
max_queue_size=args.max_queue_size)
# Unfreeze and continue training, to fine-tune.
# Train longer if the result is not good.
if True:
# for layer in model.layers:
# if layer.name is 'bn_conv1':
# print("Before\t-> Trainable: {}, Freeze: {}".format(layer.trainable, layer.freeze))
for layer in model.layers:
layer.trainable = True
# recompile to apply the change
model.compile(
loss={
'regression': losses.smooth_l1(),
'classification': losses.focal()
},
# Learning rate must be lower for training the entire network
optimizer=keras.optimizers.adam(lr=args.lr * 0.1, clipnorm=0.001),
metrics=['accuracy'])
if args.multi_gpu > 1:
from keras.utils import multi_gpu_model
with tf.device('/gpu:1'):
training_model = multi_gpu_model(model, gpus=args.multi_gpu)
else:
training_model = model
# recompile to apply the change
training_model.compile(
loss={
'regression': losses.smooth_l1(),
'classification': losses.focal()
},
# Learning rate must be lower for training the entire network
optimizer=keras.optimizers.adam(lr=args.lr * 0.1, clipnorm=0.001),
metrics=['accuracy'])
print('Unfreezing all layers.')
# for layer in model.layers:
# if layer.name is 'bn_conv1':
# print("After\t-> Trainable: {}, Freeze: {}".format(layer.trainable, layer.freeze))
# Print training_model design
# print(model.summary())
# print(training_model.summary())
# create the callbacks
callbacks = create_callbacks(
model,
training_model,
prediction_model,
validation_generator,
train_size,
[1e-8, 1e-6],
args,
)
batch_size = 2 # note that more GPU memory is required after unfreezing the body
steps = train_size // batch_size
print('Train on {} samples, val on {} samples, with batch size {}.'.
format(train_size, val_size, batch_size))
training_model.fit_generator(generator=train_generator,
validation_data=validation_generator,
steps_per_epoch=steps,
epochs=args.epochs,
initial_epoch=n_epochs,
verbose=1,
callbacks=callbacks,
workers=args.workers,
use_multiprocessing=use_multiprocessing,
max_queue_size=args.max_queue_size)
def create_models(backbone_retinanet,
num_classes,
weights,
multi_gpu=2,
freeze_backbone=False,
lr=1e-5,
config=None):
"""!@brief
Creates three models (model, training_model, prediction_model).
@param backbone_retinanet : A function to call to create a retinanet model with a given backbone.
@param num_classes : The number of classes to train.
@param weights : The weights to load into the model.
@param multi_gpu : The number of GPUs to use for training.
@param freeze_backbone : If True, disables learning for the backbone.
@param config : Config parameters, None indicates the default configuration.
@returns
model : The base model. This is also the model that is saved in snapshots.
training_model : The training model. If multi_gpu=0, this is identical to model.
prediction_model : The model wrapped with utility functions to perform object detection
(applies regression values and performs NMS).
"""
modifier = freeze_model if freeze_backbone else None
# load anchor parameters, or pass None (so that defaults will be used)
anchor_params = None
num_anchors = None
if config and 'anchor_parameters' in config:
anchor_params = parse_anchor_parameters(config)
num_anchors = anchor_params.num_anchors()
# Keras recommends initialising a multi-gpu model on the CPU to ease weight
# sharing, and to prevent OOM errors.
# Optionally wrap in a parallel model
if multi_gpu > 1:
from keras.utils import multi_gpu_model
with tf.device('/gpu:1'):
model = model_with_weights(backbone_retinanet(
num_classes, num_anchors=num_anchors, modifier=modifier),
weights=weights,
skip_mismatch=True)
training_model = multi_gpu_model(
model,
gpus=multi_gpu) # , cpu_merge=False) # <- recommended for NV-Link
else:
model = model_with_weights(backbone_retinanet(num_classes,
num_anchors=num_anchors,
modifier=modifier),
weights=weights,
skip_mismatch=True)
training_model = model
# make prediction model
prediction_model = retinanet_bbox(model=model, anchor_params=anchor_params)
# compile model
training_model.compile(loss={
'regression': losses.smooth_l1(),
'classification': losses.focal()
},
optimizer=keras.optimizers.adam(lr=lr,
clipnorm=0.001),
metrics=['accuracy'])
return model, training_model, prediction_model
