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 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,
pyramid_levels=self.fpn_layers,
anchor_params=anchor_params,
shapes_callback=self.compute_shapes)
def create_models(backbone_retinanet,
num_classes,
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
model = backbone_retinanet(num_classes,
num_anchors=num_anchors,
modifier=modifier)
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))
return model, training_model, prediction_model
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)
# 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)
print('Done')
# optionally convert the model
if args.convert_model:
model = models.convert_model(model, anchor_params=anchor_params)
# start evaluation
if args.dataset_type == 'coco':
from retinanet.utils.coco_eval import evaluate_coco
evaluate_coco(generator, model, args.score_threshold)
elif args.dataset_type == 'ead':
false_positives, true_positives, iou, average_precisions, image_names, detection_list, scores_list, \
labels_list, FP_list = evaluate(
generator,
model,
iou_threshold=args.iou_threshold,
score_threshold=args.score_threshold,
max_detections=args.max_detections,
save_path=args.save_path,
im_threshold=args.im_threshold)
# calculate number of FP and TP:
FP_sum = 0
TP_sum = 0
GT_sum = 0
for i in range(len(false_positives)):
FP_sum += int(false_positives[i][0])
TP_sum += int(true_positives[i][0])
GT_sum += int(true_positives[i][1])
precision_self = TP_sum / GT_sum
recall_self = TP_sum / (FP_sum + TP_sum)
print("AP's: ", average_precisions)
print("FP: ", false_positives)
print("Total False Positives: ", FP_sum)
print("TP: ", true_positives)
print("Total True Positives: ", TP_sum)
print("Overall precision: {:.2f}".format(precision_self))
print("Overall recall: {:.2f}".format(recall_self))
# 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
mIoU = np.mean(iou)
print("len(iou): ", len(iou))
print_mAP = sum(precisions) / sum(x > 0 for x in total_instances)
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(print_mAP))
print('mIoU: {:.4f}'.format(mIoU))
print('EAD Score (old): {:.4f}'.format(0.8 * print_mAP + 0.2 * mIoU))
print('EAD Score (new): {:.4f}'.format(0.6 * print_mAP + 0.4 * mIoU))
return precisions, total_instances, iou, image_names, detection_list, scores_list, labels_list, FP_list
elif args.dataset_type == 'polyp' and args.mode == 'scoring':
TP, FP, TN, FN, p_count = evaluate_polyp(
generator,
model,
args.data_dir,
args.val_dir,
args.val_annotations,
args.mode,
args.classes,
iou_threshold=args.iou_threshold,
score_threshold=args.score_threshold,
max_detections=args.max_detections,
save_path=args.save_path,
im_threshold=args.im_threshold)
prec = precision(TP, FP)
rec = recall(TP, FN)
f1_val = f1(prec, rec)
f2_val = f2(prec, rec)
print("\nTP: %d\nFP: %d\nFN: %d\nNumber of Polyps: %d\n" %
(TP, FP, FN, p_count))
print('precision: {:.4f}'.format(prec))
print('recall: {:.4f}'.format(rec))
print('f1: {:.4f}'.format(f1_val))
print('f2: {:.4f}'.format(f2_val))
return TP, FP, TN, FN, p_count
elif args.dataset_type == 'polyp' and args.mode == 'detection':
detections_df = evaluate_polyp(generator,
model,
args.data_dir,
args.val_dir,
args.val_annotations,
args.mode,
args.classes,
iou_threshold=args.iou_threshold,
score_threshold=args.score_threshold,
max_detections=args.max_detections,
save_path=args.save_path,
im_threshold=args.im_threshold,
save_individual=False)
return detections_df
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 retinanet.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