vis = VIS(save_path=opt.checkpoint_path)
# configuration session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
K.set_session(sess)
K.set_learning_phase(1)
# define data loader (with train and test)
train_generator, _, train_samples, _ = dataLoader(opt.data_path,
opt.batch_size, opt.imSizeX,
opt.imSizeY)
# define test loader (optional to replace above test_generator)
test_generator, test_samples = folderLoader(opt.data_path, opt.imSizeX,
opt.imSizeY)
opt.iter_epoch = int(train_samples)
# define input holders
img_shape = (opt.imSizeY, opt.imSizeX, 3)
#img = tf.placeholder(tf.float32, shape=img_shape)
img = tf.placeholder(tf.int32, shape=img_shape)
label = tf.placeholder(tf.int32, shape=(None, opt.imSizeY, opt.imSizeX))
# define model
with tf.name_scope('unet'):
model = UNet().create_model(img_shape=img_shape, num_class=opt.num_class)
img = model.input
pred = model.output
# define loss
# configure args
from opts import *
# assert(opt.load_from_checkpoint != '')
# assert(opt.batch_size == 1)
vis = VIS(save_path=opt.load_from_checkpoint)
# configuration session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
K.set_session(sess)
K.set_learning_phase(0)
# define data loader
test_generator, test_samples = folderLoader(opt.data_path)
# define model, the last dimension is the channel
img_shape = (opt.imSize, opt.imSize, 3)
# img = tf.placeholder(tf.float32, shape=img_shape)
label = tf.placeholder(tf.int32, shape=(None, opt.imSize, opt.imSize))
with tf.name_scope('unet'):
model = UNet().create_model(img_shape=img_shape, num_class=opt.num_class)
img = model.input
pred = model.output
# define loss
with tf.name_scope('cross_entropy'):
cross_entropy_loss = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(labels=label,
logits=pred))
from utils import VIS, mean_IU
# configure args
from opts import *
# assert(opt.load_from_checkpoint != '')
# assert(opt.batch_size == 1)
vis = VIS(save_path=opt.load_from_checkpoint)
# configuration session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# define data loader
img_shape = [opt.imSize, opt.imSize]
test_generator, test_samples = folderLoader(opt.data_path, imSize=img_shape)
# define model, the last dimension is the channel
label = tf.placeholder(tf.int32, shape=[None]+img_shape)
with tf.name_scope('unet'):
model = UNet().create_model(img_shape=img_shape, num_class=opt.num_class)
img = model.input
pred = model.output
# define loss
with tf.name_scope('cross_entropy'):
cross_entropy_loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=label, logits=pred))
saver = tf.train.Saver() # must be added in the end
''' Main '''
init_op = tf.global_variables_initializer()