def main(flags):
# make network
# define place holder
X = tf.placeholder(
tf.float32,
shape=[None, flags.input_size[0], flags.input_size[1], 3],
name='X')
z = tf.placeholder(tf.float32, shape=[None, flags.z_dim], name='z')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_BiGAN.BiGAN({
'X': X,
'Z': z
},
trainable=mode,
model_name=flags.model_name,
input_size=flags.input_size,
batch_size=flags.batch_size,
learn_rate=flags.learning_rate,
decay_step=flags.decay_step,
decay_rate=flags.decay_rate,
epochs=flags.epochs,
start_filter_num=flags.sfn,
z_dim=flags.z_dim,
lr_mult=flags.lr_mult,
depth=4)
model.create_graph('X', class_num=flags.num_classes, reduce_dim=False)
# prepare data
dataReader_train = ImageLabelReader_celeb(
flags.data_dir, flags.batch_size,
(flags.input_size[0], flags.input_size[1]), True)
dataReader_valid = ImageLabelReader_celeb(
flags.data_dir, flags.batch_size,
(flags.input_size[0], flags.input_size[1]), False)
img_mean = np.zeros(3)
# train
start_time = time.time()
model.train_config('X',
'Z',
flags.n_train,
flags.n_valid,
flags.input_size,
uabRepoPaths.modelPath,
par_dir='BiGAN_CELEB')
model.run(
train_reader=dataReader_train,
valid_reader=dataReader_valid,
pretrained_model_dir=None,
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=50, # save the model every 5 epochs
gpu=GPU,
tile_size=flags.tile_size,
patch_size=flags.input_size)
duration = time.time() - start_time
print('duration {:.2f} hours'.format(duration / 60 / 60))
img_dir, task_dir = sis_utils.get_task_img_folder()
os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu)
# make the model
# define place holder
X = tf.placeholder(tf.float32,
shape=[None, input_size[0], input_size[1], 3],
name='X')
z = tf.placeholder(tf.float32, shape=[None, latent_num], name='z')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_BiGAN.BiGAN({
'X': X,
'Z': z
},
trainable=mode,
input_size=input_size,
batch_size=1,
start_filter_num=64,
z_dim=latent_num,
depth=4)
# create graph
model.create_graph('X', class_num=3)
model_dir = r'/hdd6/Models/BiGAN_INRIA_RESIZE/BiGAN_inria_z100_lrm1_resize_PS(128, 128)_BS64_EP50_LR0.0001_DS25_DR0.1_SFN64'
blCol = uab_collectionFunctions.uabCollection('inria')
opDetObj = bPreproc.uabOperTileDivide(
255) # inria GT has value 0 and 255, we map it back to 0 and 1
# [3] is the channel id of GT
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif',
'Map GT to (0, 1)', [3],
opDetObj)
def main(flags):
# make network
# define place holder
X = tf.placeholder(tf.float32, shape=[None, flags.input_size[0], flags.input_size[1], 3], name='X')
z = tf.placeholder(tf.float32, shape=[None, flags.z_dim], name='z')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_BiGAN.BiGAN({'X': X, 'Z': z},
trainable=mode,
model_name=flags.model_name,
input_size=flags.input_size,
batch_size=flags.batch_size,
learn_rate=flags.learning_rate,
decay_step=flags.decay_step,
decay_rate=flags.decay_rate,
epochs=flags.epochs,
start_filter_num=flags.sfn,
z_dim=flags.z_dim,
lr_mult=flags.lr_mult)
model.create_graph('X', class_num=flags.num_classes, reduce_dim=False)
# create collection
# the original file is in /ei-edl01/data/uab_datasets/inria
blCol = uab_collectionFunctions.uabCollection('inria')
opDetObj = bPreproc.uabOperTileDivide(255) # inria GT has value 0 and 255, we map it back to 0 and 1
# [3] is the channel id of GT
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif', 'Map GT to (0, 1)', [3], opDetObj)
rescObj.run(blCol)
img_mean = np.zeros(3) #blCol.getChannelMeans([0, 1, 2]) # get mean of rgb info
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr([0, 1, 2, 4], # extract all 4 channels
cSize=flags.input_size, # patch size as 572*572
numPixOverlap=int(model.get_overlap()/2), # overlap as 92
extSave=['jpg', 'jpg', 'jpg', 'png'], # save rgb files as jpg and gt as png
isTrain=True,
gtInd=3,
pad=model.get_overlap()) # pad around the tiles
patchDir = extrObj.run(blCol)
# make data reader
# use uabCrossValMaker to get fileLists for training and validation
idx, file_list = uabCrossValMaker.uabUtilGetFolds(patchDir, 'fileList.txt', 'force_tile')
# use first 5 tiles for validation
file_list_train = uabCrossValMaker.make_file_list_by_key(idx, file_list, [i for i in range(6, 37)])
file_list_valid = uabCrossValMaker.make_file_list_by_key(idx, file_list, [i for i in range(0, 6)])
with tf.name_scope('image_loader'):
# GT has no mean to subtract, append a 0 for block mean
dataReader_train = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir, file_list_train, flags.input_size,
flags.tile_size,
flags.batch_size, dataAug='flip,rotate',
block_mean=np.append([0], img_mean))
# no augmentation needed for validation
dataReader_valid = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir, file_list_valid, flags.input_size,
flags.tile_size,
flags.batch_size, dataAug=' ', block_mean=np.append([0], img_mean))
# train
start_time = time.time()
model.train_config('X', 'Z', flags.n_train, flags.n_valid, flags.input_size, uabRepoPaths.modelPath,
par_dir='BiGAN_128')
model.run(train_reader=dataReader_train,
valid_reader=dataReader_valid,
pretrained_model_dir=None,
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=20, # save the model every 5 epochs
gpu=GPU,
tile_size=flags.tile_size,
patch_size=flags.input_size)
duration = time.time() - start_time
print('duration {:.2f} hours'.format(duration/60/60))