def run():
num_classes = 3
image_shape = IMG_SIZE
data_dir = TRAINING_DIR
runs_dir = './runs'
epochs = 1
batch_size = 1
learning_rate=1e-5
net_input = tf.placeholder(
tf.float32,shape=[None,image_shape[0], image_shape[1],3],
name="net_input")
net_output = tf.placeholder(
tf.float32,shape=[None,image_shape[0], image_shape[1],num_classes],
name="net_output")
network = build_fc_densenet(net_input, preset_model = 'FC-DenseNet56', num_classes=num_classes)
network = tf.reshape(network, (-1, num_classes), name='logits')
loss = custom_loss(network, net_output)
opt = tf.train.AdamOptimizer(1e-4).minimize(loss,
var_list=[var for var in tf.trainable_variables()])
with tf.Session() as sess:
# Create function to get batches
get_batches_fn = helper.gen_batch_function(os.path.join(data_dir), RGB_DIR, SEG_DIR, image_shape)
init_op = tf.global_variables_initializer()
saver = tf.train.Saver()
# Runs training
sess.run(init_op)
train_nn(sess, epochs, batch_size, get_batches_fn, opt, loss, net_input,
net_output, learning_rate)
# Save the trained model
today = datetime.datetime.now().strftime("%Y-%m-%d-%H%M")
save_dir = os.path.join(SAVE_MODEL_DIR, today)
helper.save_model(sess, net_input, network, save_dir)
print("SavedModel saved at {}".format(save_dir))
test_dir = TEST_DIR
helper.save_inference_samples(runs_dir, test_dir, sess, image_shape,
network, net_input)
def inference (self, net_input, num_classes, is_training):
if FLAGS.patch_slim:
fuck_slim.patch(is_training)
network = None
init_fn = None
if FLAGS.net == "FC-DenseNet56" or FLAGS.net == "FC-DenseNet67" or FLAGS.net == "FC-DenseNet103":
with slim.arg_scope(aardvark.default_argscope(is_training)):
network = build_fc_densenet(net_input, preset_model = FLAGS.net, num_classes=num_classes)
elif FLAGS.net == "RefineNet-Res50" or FLAGS.net == "RefineNet-Res101" or FLAGS.net == "RefineNet-Res152":
with slim.arg_scope(aardvark.default_argscope(is_training)):
# RefineNet requires pre-trained ResNet weights
network, init_fn = build_refinenet(net_input, preset_model = FLAGS.net, num_classes=num_classes, is_training=is_training)
elif FLAGS.net == "FRRN-A" or FLAGS.net == "FRRN-B":
with slim.arg_scope(aardvark.default_argscope(is_training)):
network = build_frrn(net_input, preset_model = FLAGS.net, num_classes=num_classes)
elif FLAGS.net == "Encoder-Decoder" or FLAGS.net == "Encoder-Decoder-Skip":
with slim.arg_scope(aardvark.default_argscope(is_training)):
network = build_encoder_decoder(net_input, preset_model = FLAGS.net, num_classes=num_classes)
elif FLAGS.net == "MobileUNet" or FLAGS.net == "MobileUNet-Skip":
with slim.arg_scope(aardvark.default_argscope(is_training)):
network = build_mobile_unet(net_input, preset_model = FLAGS.net, num_classes=num_classes)
elif FLAGS.net == "PSPNet-Res50" or FLAGS.net == "PSPNet-Res101" or FLAGS.net == "PSPNet-Res152":
with slim.arg_scope(aardvark.default_argscope(is_training)):
# Image size is required for PSPNet
# PSPNet requires pre-trained ResNet weights
network, init_fn = build_pspnet(net_input, label_size=[args.crop_height, args.crop_width], preset_model = FLAGS.net, num_classes=num_classes, is_training=is_training)
elif FLAGS.net == "GCN-Res50" or FLAGS.net == "GCN-Res101" or FLAGS.net == "GCN-Res152":
with slim.arg_scope(aardvark.default_argscope(is_training)):
# GCN requires pre-trained ResNet weights
network, init_fn = build_gcn(net_input, preset_model = FLAGS.net, num_classes=num_classes, is_training=is_training)
elif FLAGS.net == "DeepLabV3-Res50" or FLAGS.net == "DeepLabV3-Res101" or FLAGS.net == "DeepLabV3-Res152":
with slim.arg_scope(aardvark.default_argscope(is_training)):
# DeepLabV requires pre-trained ResNet weights
network, init_fn = build_deeplabv3(net_input, preset_model = FLAGS.net, num_classes=num_classes, is_training=is_training)
elif FLAGS.net == "DeepLabV3_plus-Res50" or FLAGS.net == "DeepLabV3_plus-Res101" or FLAGS.net == "DeepLabV3_plus-Res152":
# DeepLabV3+ requires pre-trained ResNet weights
with slim.arg_scope(aardvark.default_argscope(is_training)):
network, init_fn = build_deeplabv3_plus(net_input, preset_model = FLAGS.net, num_classes=num_classes, is_training=is_training)
elif FLAGS.net == "AdapNet":
with slim.arg_scope(aardvark.default_argscope(is_training)):
network = build_adaptnet(net_input, num_classes=num_classes)
else:
raise ValueError("Error: the model %d is not available. Try checking which models are available using the command python main.py --help")
self.init_fn = init_fn
return network
download_checkpoints("Res50")
if "Res101" in args.model and not os.path.isfile("models/resnet_v2_101.ckpt"):
download_checkpoints("Res101")
if "Res152" in args.model and not os.path.isfile("models/resnet_v2_152.ckpt"):
download_checkpoints("Res152")
# Compute your softmax cross entropy loss
print("Preparing the model ...")
net_input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
net_output = tf.placeholder(tf.float32, shape=[None, None, None, num_classes])
network = None
init_fn = None
if args.model == "FC-DenseNet56" or args.model == "FC-DenseNet67" or args.model == "FC-DenseNet103":
network = build_fc_densenet(net_input,
preset_model=args.model,
num_classes=num_classes)
elif args.model == "RefineNet-Res50" or args.model == "RefineNet-Res101" or args.model == "RefineNet-Res152":
# RefineNet requires pre-trained ResNet weights
network, init_fn = build_refinenet(net_input,
preset_model=args.model,
num_classes=num_classes)
elif args.model == "FRRN-A" or args.model == "FRRN-B":
network = build_frrn(net_input,
preset_model=args.model,
num_classes=num_classes)
elif args.model == "Encoder-Decoder" or args.model == "Encoder-Decoder-Skip":
network = build_encoder_decoder(net_input,
preset_model=args.model,
num_classes=num_classes)
elif args.model == "MobileUNet" or args.model == "MobileUNet-Skip":
if args.balanced_weight:
b_weight = utils.median_frequency_balancing(
args.dataset + "/train_labels/", num_classes)
print("Preparing the model ...")
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32, shape=[None, None, None, num_classes])
with tf.device('/gpu:' + str(args.gpu)):
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32, shape=[None, None, None, num_classes])
if args.model == "FC-DenseNet56" or args.model == "FC-DenseNet67" or args.model == "FC-DenseNet103" or args.model == "FC-DenseNet158" or args.model == "FC-DenseNet232":
network = build_fc_densenet(input,
preset_model=args.model,
num_classes=num_classes,
dropout_p=0.5)
elif args.model == "RefineNet-Res101" or args.model == "RefineNet-Res152":
network = build_refinenet(input,
preset_model=args.model,
num_classes=num_classes)
elif args.model == "Encoder-Decoder":
network = build_encoder_decoder(input, num_classes)
elif args.model == "Encoder-Decoder-Skip":
network = build_encoder_decoder_skip(input, num_classes)
elif args.model == "HF-FCN":
network = build_hf_fcn(input,
preset_model='FC-DenseNet103',
num_classes=num_classes)
elif args.model == "custom":
network = build_custom(input, num_classes)
for file in os.listdir(dataset_dir + "/test_labels"):
cwd = os.getcwd()
test_output_names.append(cwd + "/" + dataset_dir + "/test_labels/" +
file)
return train_input_names, train_output_names, val_input_names, val_output_names, test_input_names, test_output_names
# Load the data
print("Loading the data ...")
train_input_names, train_output_names, val_input_names, val_output_names, test_input_names, test_output_names = prepare_data(
)
print("Setting up training procedure ...")
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32, shape=[None, None, None, 12])
network = build_fc_densenet(input, preset_model='FC-DenseNet103')
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=network, labels=output))
opt = tf.train.RMSPropOptimizer(learning_rate=0.001, decay=0.995).minimize(
loss, var_list=[var for var in tf.trainable_variables()])
is_training = True
num_epochs = 250
continue_training = False
class_names_string = "Sky, Building, Pole, Road, Pavement, Tree, SignSymbol, Fence, Car, Pedestrian, Bicyclist, Unlabelled"
class_names_list = [
"Sky", "Building", "Pole", "Road", "Pavement", "Tree", "SignSymbol",
"Fence", "Car", "Pedestrian", "Bicyclist", "Unlabelled"
]
# print(variable_parameters)
total_parameters += variable_parameters
print("This model has %d trainable parameters"% (total_parameters))
if __name__ == '__main__':
img_dir = '../DL_DATA/mass_buildings/test/sat'
channel = 1
device_id = 0
offset = 0
print("Start prediction ...")
with tf.device('/gpu:0'):
input = tf.placeholder(tf.float32,shape=[None,3,None,None])
output = tf.placeholder(tf.float32,shape=[None,2,None,None])
network, prob = build_fc_densenet(input, preset_model = 'FC-DenseNet56', num_classes=2,is_bottneck=False, compression_rate=1, data_format='NCHW')
is_training = False
continue_training = False
class_names_string = "Building, Unlabelled"
class_names_list = ["Building", "Unlabelled"]
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess=tf.Session(config=config)
saver=tf.train.Saver(max_to_keep=1000)
# sess.run(tf.global_variables_initializer())
count_params()
with tf.device('/gpu:%d' % gpu_id):
print('using tower:%d...' % gpu_id)
with tf.name_scope('tower_%d' % gpu_id) as scope:
with tf.variable_scope('gpu_variables', reuse=gpu_id > 0):
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32,
shape=[None, None, None, num_classes])
if args.is_balanced_weight or args.is_edge_weight:
weight = tf.placeholder(tf.float32,
shape=[None, None, None])
if args.model == "FC-DenseNet56" or args.model == "FC-DenseNet67" or args.model == "FC-DenseNet103" or args.model == "FC-DenseNet158" or args.model == "FC-DenseNet232":
if args.is_BC:
network = build_fc_densenet(input,
preset_model=args.model,
num_classes=num_classes,
is_bottneck=1,
compression_rate=0.5)
else:
network = build_fc_densenet(input,
preset_model=args.model,
num_classes=num_classes,
is_bottneck=False,
compression_rate=1)
elif args.model == "RefineNet-Res50" or args.model == "RefineNet-Res101" or args.model == "RefineNet-Res152":
# RefineNet requires pre-trained ResNet weights
network, init_fn = build_refinenet(input,
preset_model=args.model,
num_classes=num_classes)
elif args.model == "FRRN-A" or args.model == "FRRN-B":
network = build_frrn(input,
def buildNetwork(model, net_input, num_class):
# Get the selected model.
# Some of them require pre-trained ResNet
if "Res50" in model and not os.path.isfile("models/resnet_v2_50.ckpt"):
download_checkpoints("ResnetV2", "50")
if "Res101" in model and not os.path.isfile("models/resnet_v2_101.ckpt"):
utils.download_checkpoints("ResnetV2", "101")
if "Res152" in model and not os.path.isfile("models/resnet_v2_152.ckpt"):
utils.download_checkpoints("ResnetV2", "152")
network = None
init_fn = None
if model == "FC-DenseNet56" or model == "FC-DenseNet67" or model == "FC-DenseNet103":
network = build_fc_densenet(net_input,
preset_model=model,
num_classes=num_class)
elif model == "RefineNet-Res50" or model == "RefineNet-Res101" or model == "RefineNet-Res152":
# RefineNet requires pre-trained ResNet weights
network, init_fn = build_refinenet(net_input,
preset_model=model,
num_classes=num_class)
elif model == "FRRN-A" or model == "FRRN-B":
network = build_frrn(net_input,
preset_model=model,
num_classes=num_class)
elif model == "Encoder-Decoder" or model == "Encoder-Decoder-Skip":
network = build_encoder_decoder(net_input,
preset_model=model,
num_classes=num_class)
elif model == "MobileUNet" or model == "MobileUNet-Skip":
network = build_mobile_unet(net_input,
preset_model=model,
num_classes=num_class)
elif model == "PSPNet-Res50" or model == "PSPNet-Res101" or model == "PSPNet-Res152":
# Image size is required for PSPNet
# PSPNet requires pre-trained ResNet weights
network, init_fn = build_pspnet(
net_input,
label_size=[args.crop_height, args.crop_width],
preset_model=model,
num_classes=num_class)
elif model == "GCN-Res50" or model == "GCN-Res101" or model == "GCN-Res152":
# GCN requires pre-trained ResNet weights
network, init_fn = build_gcn(net_input,
preset_model=model,
num_classes=num_class)
elif model == "DeepLabV3-Res50" or model == "DeepLabV3-Res101" or model == "DeepLabV3-Res152":
# DeepLabV requires pre-trained ResNet weights
network, init_fn = build_deeplabv3(net_input,
preset_model=model,
num_classes=num_class)
elif model == "DeepLabV3_plus-Res50" or model == "DeepLabV3_plus-Res101" or model == "DeepLabV3_plus-Res152":
# DeepLabV3+ requires pre-trained ResNet weights
network, init_fn = build_deeplabv3_plus(net_input,
preset_model=model,
num_classes=num_class)
elif model == "AdapNet":
network = build_adaptnet(net_input, num_classes=num_class)
elif model == "custom":
network = build_custom(net_input, num_class)
else:
raise ValueError(
"Error: the model %d is not available. Try checking which models are available using the command python main.py --help"
)
return network, init_fn
# cwd = os.getcwd()
test_output_names.append(dataset_dir + "/labels_test/" + file)
return train_input_names, train_output_names, val_input_names, val_output_names, test_input_names, test_output_names
# Load the data
print("Loading the data ...")
train_input_names, train_output_names, val_input_names, val_output_names, test_input_names, test_output_names = prepare_data(
'/media/zhoun/Data/lx/caffe/DeepNetsForEO/ISPRS/Vaihingen/vaihingen_128_128_32_fold1'
)
print("Setting up training procedure ...")
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32, shape=[None, None, None, 6])
network = build_fc_densenet(input,
preset_model='FC-DenseNet103',
num_classes=6)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=network, labels=output))
opt = tf.train.RMSPropOptimizer(learning_rate=0.001, decay=0.995).minimize(
loss, var_list=[var for var in tf.trainable_variables()])
is_training = False
num_epochs = 500
continue_training = True
class_names_string = "Impervious surfaces, Buildings, Low vegetation, Tree, Car, Clutter, Unclassified "
class_names_list = [
"Impervious surfaces", "Buildings", "Low vegetation", "Tree", "Car",
"Clutter", "Unclassified"
file)
return train_input_names, train_output_names, val_input_names, val_output_names, test_input_names, test_output_names
# Load the data
print("Loading the data ...")
train_input_names, train_output_names, val_input_names, val_output_names, test_input_names, test_output_names = prepare_data(
'./data/mass_buildings/patches')
print("Setting up training procedure ...")
with tf.device('/gpu:0'):
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32, shape=[None, None, None, 2])
network = build_fc_densenet(input,
preset_model='FC-DenseNet232',
num_classes=2,
dropout_p=0.4)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=network, labels=output))
opt = tf.train.RMSPropOptimizer(learning_rate=0.001, decay=0.995).minimize(
loss, var_list=[var for var in tf.trainable_variables()])
is_training = True
num_epochs = 300
continue_training = False
class_names_string = "Building, Unlabelled"
class_names_list = ["Building", "Unlabelled"]
config = tf.ConfigProto()
network = None
init_fn = None
print("Preparing the model ...")
# with tf.device('/gpu'):
# with tf.name_scope('tower_%d' % args.gpu_ids) as scope:
# z = tf.placeholder(tf.float32,shape=[None,None,None,3],name='input')
# gt = tf.placeholder(tf.float32,shape=[None,None,None,num_classes],name='output')
# if args.is_balanced_weight or args.is_edge_weight:
# weight = tf.placeholder(tf.float32,shape=[None,None,None],name='weight')
if args.model == "FC-DenseNet56" or args.model == "FC-DenseNet67" or args.model == "FC-DenseNet103" or args.model == "FC-DenseNet158" or args.model == "FC-DenseNet232":
if args.is_BC:
G_logist, G, G_var = build_fc_densenet(z,
preset_model=args.model,
num_classes=num_classes,
is_bottneck=True,
compression_rate=0.5)
else:
G_logist, G, G_var = build_fc_densenet(z,
preset_model=args.model,
num_classes=num_classes,
is_bottneck=False,
compression_rate=1)
k_t = tf.Variable(0., trainable=False, name='k_t')
step = tf.Variable(0, name='step', trainable=False)
g_lr = tf.Variable(1e-3, name='g_lr')
d_lr = tf.Variable(8e-5, name='d_lr')
if __name__ == '__main__':
img_dir = './data/mass_buildings/test/sat'
channel = 1
device_id = 0
offset = 0
print("Start prediction ...")
with tf.device('/gpu:0'):
input = tf.placeholder(tf.float32, shape=[None, None, None, 3])
output = tf.placeholder(tf.float32, shape=[None, None, None, 2])
network = build_fc_densenet(input,
preset_model='FC-DenseNet158',
num_classes=2,
is_bottneck=True,
compression_rate=0.5)
prob = tf.nn.softmax(network)
is_training = False
continue_training = False
class_names_string = "Building, Unlabelled"
class_names_list = ["Building", "Unlabelled"]
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
saver = tf.train.Saver(max_to_keep=1000)
# sess.run(tf.global_variables_initializer())
def build_model(model_name,
net_input,
num_classes,
frontend="ResNet101",
is_training=True):
# Get the selected model.
# Some of them require pre-trained ResNet
print("Preparing the model ...")
if model_name not in SUPPORTED_MODELS:
raise ValueError(
"The model you selelect is not supported. The following models are currently supported: {0}"
.format(SUPPORTED_MODELS))
if frontend not in SUPPORTED_FRONTENDS:
raise ValueError(
"The frontend you selelect is not supported. The following models are currently supported: {0}"
.format(SUPPORTED_FRONTENDS))
if "ResNet50" == frontend and not os.path.isfile(
"models/resnet_v2_50.ckpt"):
download_checkpoints("ResNet50")
if "ResNet101" == frontend and not os.path.isfile(
"models/resnet_v2_101.ckpt"):
download_checkpoints("ResNet101")
if "ResNet152" == frontend and not os.path.isfile(
"models/resnet_v2_152.ckpt"):
download_checkpoints("ResNet152")
if "MobileNetV2" == frontend and not os.path.isfile(
"models/mobilenet_v2_1.4_224.ckpt.data-00000-of-00001"):
download_checkpoints("MobileNetV2")
if "InceptionV4" == frontend and not os.path.isfile(
"models/inception_v4.ckpt"):
download_checkpoints("InceptionV4")
network = None
init_fn = None
if model_name == "FC-DenseNet56" or model_name == "FC-DenseNet67" or model_name == "FC-DenseNet103":
network = build_fc_densenet(net_input,
preset_model=model_name,
num_classes=num_classes)
elif model_name == "RefineNet":
# RefineNet requires pre-trained ResNet weights
network, init_fn = build_refinenet(net_input,
preset_model=model_name,
frontend=frontend,
num_classes=num_classes,
is_training=is_training)
elif model_name == "FRRN-A" or model_name == "FRRN-B":
network = build_frrn(net_input,
preset_model=model_name,
num_classes=num_classes)
elif model_name == "Encoder-Decoder" or model_name == "Encoder-Decoder-Skip":
network = build_encoder_decoder(net_input,
preset_model=model_name,
num_classes=num_classes)
elif model_name == "MobileUNet" or model_name == "MobileUNet-Skip":
network = build_mobile_unet(net_input,
preset_model=model_name,
num_classes=num_classes)
elif model_name == "PSPNet":
# Image size is required for PSPNet
# PSPNet requires pre-trained ResNet weights
network, init_fn = build_pspnet(
net_input,
label_size=[args.crop_height, args.crop_width],
preset_model=model_name,
frontend=frontend,
num_classes=num_classes,
is_training=is_training)
elif model_name == "GCN":
# GCN requires pre-trained ResNet weights
network, init_fn = build_gcn(net_input,
preset_model=model_name,
frontend=frontend,
num_classes=num_classes,
is_training=is_training)
elif model_name == "DeepLabV3":
# DeepLabV requires pre-trained ResNet weights
network, init_fn = build_deeplabv3(net_input,
preset_model=model_name,
frontend=frontend,
num_classes=num_classes,
is_training=is_training)
elif model_name == "DeepLabV3_plus":
# DeepLabV3+ requires pre-trained ResNet weights
network, init_fn = build_deeplabv3_plus(net_input,
preset_model=model_name,
frontend=frontend,
num_classes=num_classes,
is_training=is_training)
elif model_name == "AdapNet":
network = build_adaptnet(net_input, num_classes=num_classes)
elif model_name == "custom":
network = build_custom(net_input, num_classes)
else:
raise ValueError(
"Error: the model %d is not available. Try checking which models are available using the command python main.py --help"
)
return network, init_fn
