def create_model(args):
if args.arch == 'wideresnet':
import models.wideresnet as models
model = models.build_wideresnet(depth=args.model_depth,
widen_factor=args.model_width,
dropout=0,
num_classes=args.num_classes)
elif args.arch == 'resnext':
import models.resnext as models
model = models.build_resnext(cardinality=args.model_cardinality,
depth=args.model_depth,
width=args.model_width,
num_classes=args.num_classes)
logger.info("Total params: {:.2f}M".format(sum(p.numel() for p in model.parameters())/1e6))
return model
def create_model(arch):
if arch == 'wideresnet':
import models.wideresnet as models
model = models.build_wideresnet(depth=depth,
widen_factor=widen_factor,
dropout=0,
num_classes=num_classes).to(device)
elif arch == 'resnext':
import models.resnext as models
model = models.build_resnext(cardinality=cardinality,
depth=depth,
width=width,
num_classes=num_classes).to(device)
print('Total params: {:.2f}M'.format(
sum(p.numel() for p in model.parameters()) / 1e6))
return model
def create_model(args):
if args.arch == 'wideresnet':
import models.wideresnet as models
model = models.build_wideresnet(depth=args.model_depth,
widen_factor=args.model_width,
dropout=args.dropout,
num_classes=args.num_classes)
elif args.arch == 'cnn13':
import models.cnn13 as models
model = models.cnn13(num_classes=args.num_classes,
dropout=args.dropout)
elif args.arch == 'shakeshake':
import models.shakeshake as models
model = models.shakeshake_resnet(num_classes=args.num_classes,
dropout=args.dropout)
return model
def make_one_net_model(self, cf, in_shape, loss, metrics, optimizer):
# Create the *Keras* model
if cf.model_name == 'fcn8':
model = build_fcn8(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
#path_weights='weights/pascal-fcn8s-dag.mat')
path_weights=None)
elif cf.model_name == 'unet':
model = build_unet(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
path_weights=None)
elif cf.model_name == 'segnet_basic':
model = build_segnet(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
path_weights=None, basic=True)
elif cf.model_name == 'segnet_vgg':
model = build_segnet(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
path_weights=None, basic=False)
elif cf.model_name == 'resnetFCN':
model = build_resnetFCN(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
path_weights=None)
elif cf.model_name == 'densenetFCN':
model = build_densenetFCN(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
path_weights=None)
elif cf.model_name == 'lenet':
model = build_lenet(in_shape, cf.dataset.n_classes, cf.weight_decay)
elif cf.model_name == 'alexNet':
model = build_alexNet(in_shape, cf.dataset.n_classes, cf.weight_decay)
elif cf.model_name == 'vgg16':
model = build_vgg(in_shape, cf.dataset.n_classes, 16, cf.weight_decay,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from, out_name=cf.dataset_name)
elif cf.model_name == 'vgg19':
model = build_vgg(in_shape, cf.dataset.n_classes, 19, cf.weight_decay,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'resnet50':
model = build_resnet50(in_shape, cf.dataset.n_classes, cf.weight_decay,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'wideresnet':
model = build_wideresnet(in_shape, cf.dataset.n_classes, cf.weight_decay,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'InceptionV3':
model = build_inceptionV3(in_shape, cf.dataset.n_classes,
cf.weight_decay,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'yolo':
model = build_yolo(in_shape, cf.dataset.n_classes,
cf.dataset.n_priors,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from, tiny=False)
elif cf.model_name == 'tiny-yolo':
model = build_yolo(in_shape, cf.dataset.n_classes,
cf.dataset.n_priors,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from, tiny=True)
elif cf.model_name == 'ssd':
model = build_ssd(in_shape, cf.dataset.n_classes+1,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
else:
raise ValueError('Unknown model')
# Load pretrained weights
if cf.load_pretrained:
print(' loading model weights from: ' + cf.pretrained_weights_file + '...')
model.load_weights(cf.pretrained_weights_file, by_name=True)
# Compile model
model.compile(loss=loss, metrics=metrics, optimizer=optimizer)
# Show model structure
if cf.show_model:
model.summary()
plot(model, to_file=os.path.join(cf.savepath, 'model.png'))
# Output the model
print (' Model: ' + cf.model_name)
# model is a keras model, Model is a class wrapper so that we can have
# other models (like GANs) made of a pair of keras models, with their
# own ways to train, test and predict
return One_Net_Model(model, cf, optimizer)
