def train(dataset, model_name, learning_rate, weight_decay,
num_epochs, max_patience, batch_size, optimizer,
savepath, train_path, valid_path, test_path,
crop_size=(224, 224), in_shape=(3, None, None),
n_classes=5, gtSet=None, void_class=[4], w_balance=None,
weights_file=False, show_model=False,
plot_hist=True, train_model=True):
# Remove void classes from number of classes
n_classes = n_classes - len(void_class)
# Mask folder (For different polyp groundtruths)
if gtSet is not None:
mask_floder = 'masks' + str(gtSet)
else:
mask_floder = 'masks'
# TODO: Get the number of images directly from data loader
n_images_train = 30 # 547
n_images_val = 20 # 183
n_images_test = 20 # 182
# Normalization mean and std computed on training set for RGB pixel values
print ('\n > Computing mean and std for normalization...')
if False:
rgb_mean, rgb_std = compute_mean_std(os.path.join(train_path, 'images'),
os.path.join(train_path, mask_floder),
n_classes)
rescale = None
else:
rgb_mean = None
rgb_std = None
rescale = 1/255.
print ('Mean: ' + str(rgb_mean))
print ('Std: ' + str(rgb_std))
# Compute class balance weights
if w_balance is not None:
class_balance_weights = compute_class_balance(masks_path=train_path + mask_floder,
n_classes=n_classes,
method=w_balance,
void_labels=void_class
)
print ('Class balance weights: ' + str(class_balance_weights))
else:
class_balance_weights = None
# Build model
print ('\n > Building model (' + model_name + ')...')
if model_name == 'fcn8':
model = build_fcn8(in_shape, l2_reg=weight_decay, nclasses=n_classes,
weights_file=weights_file, deconv='deconv')
model.output
else:
raise ValueError('Unknown model')
# Create the optimizer
print ('\n > Creating optimizer ({}) with lr ({})...'.format(optimizer,
learning_rate))
if optimizer == 'rmsprop':
opt = RMSprop(lr=learning_rate, rho=0.9, epsilon=1e-8, clipnorm=10)
else:
raise ValueError('Unknown optimizer')
# Compile model
print ('\n > Compiling model...')
model.compile(loss=cce_flatt(void_class, class_balance_weights),
optimizer=opt)
# Show model structure
if show_model:
model.summary()
plot(model, to_file=savepath+'model.png')
# Create the data generators
print ('\n > Reading training set...')
dg_tr = ImageDataGenerator(crop_size=crop_size, # Crop the image to a fixed size
featurewise_center=False, # Substract mean - dataset
samplewise_center=False, # Substract mean - sample
featurewise_std_normalization=False, # Divide std - dataset
samplewise_std_normalization=False, # Divide std - sample
rgb_mean=rgb_mean,
rgb_std=rgb_std,
gcn=False, # Global contrast normalization
zca_whitening=False, # Apply ZCA whitening
rotation_range=180, # Rnd rotation degrees 0-180
width_shift_range=0.0, # Rnd horizontal shift
height_shift_range=0.0, # Rnd vertical shift
shear_range=0.5, # 0.5, # Shear in radians
zoom_range=0.1, # Zoom
channel_shift_range=0., # Channel shifts
fill_mode='constant', # Fill mode
cval=0., # Void image value
void_label=void_class[0], # Void class value
horizontal_flip=True, # Rnd horizontal flip
vertical_flip=True, # Rnd vertical flip
rescale=rescale, # Rescaling factor
spline_warp=False, # Enable elastic deformation
warp_sigma=10, # Elastic deformation sigma
warp_grid_size=3 # Elastic deformation gridSize
)
train_gen = dg_tr.flow_from_directory(train_path + 'images',
batch_size=batch_size,
gt_directory=train_path + mask_floder,
target_size=crop_size,
class_mode='seg_map',
classes=n_classes,
# save_to_dir=savepath, # Save DA
save_prefix='data_augmentation',
save_format='png')
print ('\n > Reading validation set...')
dg_va = ImageDataGenerator(rgb_mean=rgb_mean, rgb_std=rgb_std, rescale=rescale)
valid_gen = dg_va.flow_from_directory(valid_path + 'images',
batch_size=1,
gt_directory=valid_path + mask_floder,
target_size=None,
class_mode='seg_map',
classes=n_classes)
print ('\n > Reading testing set...')
dg_ts = ImageDataGenerator(rgb_mean=rgb_mean, rgb_std=rgb_std, rescale=rescale)
test_gen = dg_ts.flow_from_directory(test_path + 'images',
batch_size=1,
gt_directory=test_path + mask_floder,
target_size=None,
class_mode='seg_map',
classes=n_classes,
shuffle=False)
# Define the jaccard validation callback
eval_model = Evaluate_model(n_classes=n_classes,
void_label=void_class[0],
save_path=savepath,
valid_gen=valid_gen,
valid_epoch_length=n_images_val,
valid_metrics=['val_loss',
'val_jaccard',
'val_acc',
'val_jaccard_perclass'])
# Define early stopping callbacks
early_stop_jac = EarlyStopping(monitor='val_jaccard', mode='max',
patience=max_patience, verbose=0)
early_stop_jac_class = []
for i in range(n_classes):
early_stop_jac_class += [EarlyStopping(monitor=str(i)+'_val_jacc_percl',
mode='max', patience=max_patience,
verbose=0)]
# Define model saving callbacks
checkp_jac = ModelCheckpoint(filepath=savepath+"weights.hdf5",
verbose=0, monitor='val_jaccard',
mode='max', save_best_only=True,
save_weights_only=True)
checkp_jac_class = []
for i in range(n_classes):
checkp_jac_class += [ModelCheckpoint(filepath=savepath+"weights"+str(i)+".hdf5",
verbose=0,
monitor=str(i)+'_val_jacc_percl',
mode='max', save_best_only=True,
save_weights_only=True)]
# Train the model
if (train_model):
print('\n > Training the model...')
cb = [eval_model, early_stop_jac, checkp_jac] + checkp_jac_class
hist = model.fit_generator(train_gen, samples_per_epoch=n_images_train,
nb_epoch=num_epochs,
callbacks=cb)
# Compute test metrics
print('\n > Testing the model...')
model.load_weights(savepath + "weights.hdf5")
color_map = [
(255/255., 0, 0), # Background
(192/255., 192/255., 128/255.), # Polyp
(128/255., 64/255., 128/255.), # Lumen
(0, 0, 255/255.), # Specularity
(0, 255/255., 0), #
(192/255., 128/255., 128/255.), #
(64/255., 64/255., 128/255.), #
]
test_metrics = compute_metrics(model, test_gen, n_images_test, n_classes,
metrics=['test_loss',
'test_jaccard',
'test_acc',
'test_jaccard_perclass'],
color_map=color_map, tag="test",
void_label=void_class[0],
out_images_folder=savepath,
epoch=0,
save_all_images=True,
useCRF=False)
for k in sorted(test_metrics.keys()):
print('{}: {}'.format(k, test_metrics[k]))
if (train_model):
# Save the results
print ("\n > Saving history...")
with open(savepath + "history.pickle", 'w') as f:
pickle.dump([hist.history, test_metrics], f)
# Load the results
print ("\n > Loading history...")
with open(savepath + "history.pickle") as f:
history, test_metrics = pickle.load(f)
# print (str(test_metrics))
# Show the trained model history
if plot_hist:
print('\n > Show the trained model history...')
plot_history(history, savepath, n_classes)
# plot data
if(not args.nodisplay):
for idx in range(25):
plt.subplot(5,10,2*idx+1)
plt.imshow(x_train[idx,:,:,0])
plt.subplot(5,10,2*idx+2)
plt.imshow(y_train[idx,:,:,0])
plt.show()
if(not args.nomodel):
loss = cce_flatt(void_class, None)
metrics = [IoU(n_classes, void_class)]
#opt = RMSprop(lr=0.001, clipnorm=10)
opt = Nadam(lr=0.002)
model = build_fcn8(in_shape, n_classes, 0.)
model.compile(loss=loss, metrics=metrics, optimizer=opt)
cb = [EarlyStopping(monitor='val_loss', min_delta = 0.0001, patience=2)]
model.fit(x_train, y_train, epochs=1000, batch_size=16, callbacks=cb, validation_data=(x_valid,y_valid))
score = model.evaluate(x_test, y_test) #, batch_size=128)
y_pred = model.predict(x_test)
print(score)
for sample in range(y_test.shape[0]):
print('sample: ' + str(sample))
print('actual:')
print(y_test[sample,:,:,0])
print('predicted:')
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=cf.load_imageNet)
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=cf.load_imageNet)
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)
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 == '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)
else:
raise ValueError('Unknown model')
# Load pretrained weights
if cf.load_pretrained:
print(' loading model weights from: ' + cf.weights_file + '...')
model.load_weights(cf.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)
def make_one_net_model(self, cf, in_shape, loss, metrics, optimizer):
# Assertions
if 'tiramisu' in cf.model_name:
input_rows, input_cols = cf.target_size_train[0], cf.target_size_train[1]
multiple = 2 ** 5 # 5 transition blocks
if input_rows is not None:
if input_rows % multiple != 0:
raise ValueError('The number of rows of the input data must be a multiple of {}'.format(multiple))
if input_cols is not None:
if input_cols % multiple != 0:
raise ValueError(
'The number of columns of the input data must be a multiple of {}'.format(multiple))
# 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 == 'dilation':
model = build_dilation(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 == '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 == 'densenetFCN':
model = build_densenetFCN(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from)
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)
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 == '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 == 'ssd300':
model = build_ssd300(in_shape, cf.dataset.n_classes + 1, cf.weight_decay,
load_pretrained=cf.load_imageNet, freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'deeplabV2':
model = build_deeplabv2(in_shape, nclasses=cf.dataset.n_classes, load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from, weight_decay=cf.weight_decay)
elif cf.model_name == 'ssd300':
model = build_ssd300(in_shape, cf.dataset.n_classes + 1, cf.weight_decay,
load_pretrained=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'tiramisu_fc56':
model = build_tiramisu_fc56(in_shape, cf.dataset.n_classes, cf.weight_decay,
compression=0, dropout=0.2, nb_filter=48,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'tiramisu_fc67':
model = build_tiramisu_fc67(in_shape, cf.dataset.n_classes, cf.weight_decay,
compression=0, dropout=0.2, nb_filter=48,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'tiramisu_fc103':
model = build_tiramisu_fc103(in_shape, cf.dataset.n_classes, cf.weight_decay,
compression=0, dropout=0.2, nb_filter=48,
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.weights_file + '...')
model.load_weights(cf.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)
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=cf.load_imageNet)
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,
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,
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 == 'inceptionFCN':
model = build_inceptionFCN(in_shape, cf.dataset.n_classes, cf.weight_decay,
freeze_layers_from=cf.freeze_layers_from,
path_weights=None)
elif cf.model_name == 'densenet':
model = build_densenet(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_imageNet=cf.load_imageNet,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'vgg19':
model = build_vgg(in_shape, cf.dataset.n_classes, 19, cf.weight_decay,
load_imageNet=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_imageNet=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_imageNet=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_imageNet=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_imageNet=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,
cf.dataset.n_priors,
freeze_layers_from=cf.freeze_layers_from)
elif cf.model_name == 'densenet_segmentation':
model = build_densenet_segmentation(in_shape, cf.dataset.n_classes, weight_decay = cf.weight_decay,
freeze_layers_from = cf.freeze_layers_from, path_weights = cf.load_imageNet)
else:
raise ValueError('Unknown model')
# Load pretrained weights
if cf.load_pretrained:
print(' loading model weights from: ' + cf.weights_file + '...')
# If the weights are from different datasets
if cf.different_datasets:
if cf.freeze_layers_from == 'base_model':
raise TypeError('Please, enter the layer id instead of "base_model"'
' for the freeze_layers_from config parameter')
croppedmodel = model_from_json(model.to_json())
# Remove not frozen layers
for i in range(len(model.layers[cf.freeze_layers_from:])):
croppedmodel.layers.pop()
# Load weights only for the frozen layers
croppedmodel.load_weights(cf.weights_file, by_name=True)
model.set_weights(croppedmodel.get_weights())
else:
model.load_weights(cf.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)
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)
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 == 'resnet50Keras':
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 == 'resnet18':
model = ResnetBuilder.build_resnet_18(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet34':
model = ResnetBuilder.build_resnet_34(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet50':
model = ResnetBuilder.build_resnet_50(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet101':
model = ResnetBuilder.build_resnet_101(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet152':
model = ResnetBuilder.build_resnet_152(in_shape,
cf.dataset.n_classes)
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 == 'densenet':
model = build_densenet(in_shape, cf.dataset.n_classes,
cf.weight_decay)
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_SSD300(in_shape, cf.dataset.n_classes)
if cf.load_imageNet:
# Rename last layer to not load pretrained weights
model.layers[-1].name += '_new'
model.load_weights('weights/weights_SSD300.hdf5', by_name=True)
else:
raise ValueError('Unknown model')
# Load pretrained weights
if cf.load_pretrained:
print(' loading model weights from: ' + cf.weights_file)
#old_name=model.layers[-2].name
#model.layers[-2].name=model.layers[-2].name+'_replaced'
model.load_weights(cf.weights_file, by_name=True)
#model.layers[-2].name=old_name
# 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)
def make_one_net_model(self, cf, in_shape, loss, metrics, optimizer):
# Create the *Keras* model
model_name = cf.model_name
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=cf.load_imageNet)
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 == 'densenet_fc':
model = DenseNetFCN((224, 224, 3),
nb_dense_block=5,
growth_rate=16,
nb_layers_per_block=4,
upsampling_type='upsampling',
classes=cf.dataset.n_classes)
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)
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 == 'resnet50Keras':
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 == 'resnet18':
model = ResnetBuilder.build_resnet_18(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet34':
model = ResnetBuilder.build_resnet_34(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet50':
model = ResnetBuilder.build_resnet_50(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet101':
model = ResnetBuilder.build_resnet_101(in_shape,
cf.dataset.n_classes)
elif cf.model_name == 'resnet152':
model = ResnetBuilder.build_resnet_152(in_shape,
cf.dataset.n_classes)
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 == 'densenet':
model = build_densenet(in_shape, cf.dataset.n_classes,
cf.weight_decay)
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,
typeNet='Regular')
elif cf.model_name == 'tiny-yolo':
if hasattr(cf, 'lookTwice'):
yolt = cf.lookTwice
if yolt:
model_name = 'Tiny-YOLT'
else:
yolt = False
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,
typeNet='Tiny',
lookTwice=yolt)
elif cf.model_name == 'yolt':
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,
typeNet='YOLT')
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.weights_file)
model.load_weights(cf.weights_file, by_name=True)
else:
try:
if cf.load_transferlearning:
print(' loading model weights from: ' + cf.weights_file)
old_name = model.layers[-2].name
model.layers[-2].name = model.layers[-2].name + '_replaced'
model.load_weights(cf.weights_file, by_name=True)
model.layers[-2].name = old_name
except:
pass
# 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: ' + 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)
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'
if cf.load_pascalVOC else 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)
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 == '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 == 'densenet':
model = build_densenet(
in_shape,
cf.dataset.n_classes,
layers_in_dense_block=cf.layers_in_dense_block,
initial_filters=cf.initial_filters,
growth_rate=cf.growth_rate,
n_bottleneck=cf.n_bottleneck,
compression=cf.compression,
dropout=cf.dropout,
weight_decay=cf.weight_decay)
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 == 'ssd300':
model = build_ssd300(in_shape, cf.dataset.n_classes + 1)
# TODO: find best parameters
ssd_utils.initialize_module(model,
in_shape,
cf.dataset.n_classes + 1,
overlap_threshold=0.5,
nms_thresh=0.45,
top_k=400)
elif cf.model_name == 'tiramisu':
model = build_tiramisu(
in_shape,
cf.dataset.n_classes,
layers_in_dense_block=cf.layers_in_dense_block,
initial_filters=cf.initial_filters,
growth_rate=cf.growth_rate,
n_bottleneck=cf.n_bottleneck,
compression=cf.compression,
dropout=cf.dropout,
weight_decay=cf.weight_decay)
elif cf.model_name == 'ssd300_pretrained':
model = build_ssd300_pretrained(in_shape, cf.dataset.n_classes + 1)
# TODO: find best parameters
ssd_utils.initialize_module(model,
in_shape,
cf.dataset.n_classes + 1,
overlap_threshold=0.5,
nms_thresh=0.45,
top_k=400)
elif cf.model_name == 'ssd_resnet50':
model = build_ssd_resnet50(in_shape, cf.dataset.n_classes + 1)
# TODO: find best parameters
ssd_utils.initialize_module(model,
in_shape,
cf.dataset.n_classes + 1,
overlap_threshold=0.5,
nms_thresh=0.45,
top_k=400)
else:
raise ValueError('Unknown model')
# Load pretrained weights
if cf.load_pretrained:
print(' loading model weights from: ' + cf.weights_file + '...')
model.load_weights(cf.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)
