def check_res50_features(model_name, GPU=0):
os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
os.environ['CUDA_VISIBLE_DEVICES'] = '{}'.format(GPU)
import keras
input_size_fit = (224, 224)
blCol = uab_collectionFunctions.uabCollection('inria')
opDetObj = bPreproc.uabOperTileDivide(255)
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif',
'Map GT to (0, 1)', [3],
opDetObj)
rescObj.run(blCol)
img_mean = blCol.getChannelMeans([0, 1, 2])
if model_name == 'deeplab':
input_size = (321, 321)
overlap = 0
else:
input_size = (572, 572)
overlap = 184
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 4],
cSize=input_size,
numPixOverlap=overlap,
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=overlap // 2)
patchDir = extrObj.run(blCol)
file_name = os.path.join(patchDir, 'fileList.txt')
with open(file_name, 'r') as f:
files = f.readlines()
res50 = keras.applications.resnet50.ResNet50(include_top=True,
weights='imagenet')
pred_list = np.zeros(len(files))
for file_cnt, file_line in enumerate(tqdm(files)):
img = np.zeros((input_size[0], input_size[1], 3), dtype=np.uint8)
for cnt, file in enumerate(file_line.strip().split(' ')[:3]):
img[:, :, cnt] = imageio.imread(os.path.join(patchDir,
file)) - img_mean[cnt]
img = np.expand_dims(crop_center(img, input_size_fit[0],
input_size_fit[1]),
axis=0)
fc1000 = res50.predict(img).reshape((-1, )).tolist()
pred_list[file_cnt] = np.argmax(fc1000)
return pred_list
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_UGAN.UGAN({
'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)
model.create_graph('X', class_num=flags.num_classes)
# 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 = 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)
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=5, # 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))
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')
y = tf.placeholder(
tf.int32,
shape=[None, flags.input_size[0], flags.input_size[1], 1],
name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_ASSN.SSAN_UNet({
'X': X,
'Y': y
},
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,
lada=flags.lada,
slow_iter=flags.slow_iter)
model.create_graph(['X', 'Y'], class_num=flags.num_classes)
# create collection
# the original file is in /ei-edl01/data/uab_datasets/inria
blCol = uab_collectionFunctions.uabCollection('inria')
opDetObj = bPreproc.uabOperTileDivide(255)
# [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 = blCol.getChannelMeans([0, 1, 2])
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 4],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=model.get_overlap() // 2)
patchDir = extrObj.run(blCol)
# make data reader
# use uabCrossValMaker to get fileLists for training and validation
idx_city, file_list = uabCrossValMaker.uabUtilGetFolds(
patchDir, 'fileList.txt', 'city')
idx_tile, _ = uabCrossValMaker.uabUtilGetFolds(patchDir, 'fileList.txt',
'force_tile')
idx = [j * 10 + i for i, j in zip(idx_city, idx_tile)]
# use first city for validation
filter_train = []
filter_train_target = []
filter_valid = []
for i in range(5):
for j in range(1, 37):
if i != flags.finetune_city and j > 5:
filter_train.append(j * 10 + i)
elif i == flags.finetune_city and j > 5:
filter_train_target.append(j * 10 + i)
elif i == flags.finetune_city and j <= 5:
filter_valid.append(j * 10 + i)
# use first city for validation
file_list_train = uabCrossValMaker.make_file_list_by_key(
idx, file_list, filter_train)
filter_list_train_valid = uabCrossValMaker.make_file_list_by_key(
idx, file_list, filter_train_target)
file_list_valid = uabCrossValMaker.make_file_list_by_key(
idx, file_list, filter_valid)
dataReader_train = uabDataReader.ImageLabelReader([3], [0, 1, 2],
patchDir,
file_list_train,
flags.input_size,
flags.batch_size,
dataAug='flip,rotate',
block_mean=np.append(
[0], img_mean),
batch_code=0)
dataReader_train_target = uabDataReader.ImageLabelReader(
[3], [0, 1, 2],
patchDir,
filter_list_train_valid,
flags.input_size,
flags.batch_size,
dataAug='flip,rotate',
block_mean=np.append([0], img_mean),
batch_code=0)
# no augmentation needed for validation
dataReader_valid = uabDataReader.ImageLabelReader([3], [0, 1, 2],
patchDir,
file_list_valid,
flags.input_size,
flags.batch_size,
dataAug=' ',
block_mean=np.append(
[0], img_mean),
batch_code=0)
# train
start_time = time.time()
model.load_weights(flags.pred_model_dir.format(flags.finetune_city),
layers2load='1,2,3,4,5,6,7,8,9',
load_final_layer=True)
model.train_config('X',
'Y',
flags.n_train,
flags.n_valid,
flags.input_size,
uabRepoPaths.modelPath,
loss_type='xent',
par_dir='Inria_GAN/SSAN')
model.run(
train_reader=dataReader_train,
train_reader_source=dataReader_train,
train_reader_target=dataReader_train_target,
valid_reader=dataReader_valid,
pretrained_model_dir=
None, # train from scratch, no need to load pre-trained model
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=flags.save_epoch, # 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))
input_size=chip_size,
batch_size=batch_size,
learn_rate=learn_rate,
decay_step=decay_step,
decay_rate=decay_rate,
epochs=epochs,
start_filter_num=start_filter_num)
model.create_graph('X', class_num=2)
# If you only want to load a specific number of layers, you have to do load_weight() here
# don't give pretrained_model_dir and layers2keep when calling model.run(), that will cause problem
model.load_weights(pre_trained_model_dir, layers2keep)
# 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 = blCol.getChannelMeans([0, 1, 2]) # get mean of rgb info
print(blCol.readMetadata()
) # now inria collection has 4 channels, the last one is GT with (0, 1)
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 4], # extract all 4 channels
cSize=chip_size, # patch size as 572*572
numPixOverlap=int(model.get_overlap() / 2), # overlap as 92
extSave=['jpg', 'jpg', 'jpg',
def main(flags):
city_list = ['austin', 'chicago', 'kitsap', 'tyrol-w', 'vienna']
flags.llh_file_dir = flags.llh_file_dir.format(flags.finetune_city)
weight = np.load(flags.llh_file_dir)
# make network
# define place holder
X = tf.placeholder(tf.float32, shape=[None, flags.input_size[0], flags.input_size[1], 3], name='X')
y = tf.placeholder(tf.int32, shape=[None, flags.input_size[0], flags.input_size[1], 1], name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({'X': X, 'Y': y},
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)
model.create_graph('X', class_num=flags.num_classes)
# 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 = 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_city, file_list = uabCrossValMaker.uabUtilGetFolds(patchDir, 'fileList.txt', 'city')
idx_tile, _ = uabCrossValMaker.uabUtilGetFolds(patchDir, 'fileList.txt', 'force_tile')
idx = [j * 10 + i for i, j in zip(idx_city, idx_tile)]
# use first city for validation
filter_train = []
filter_valid = []
for i in range(5):
for j in range(1, 37):
if i != flags.finetune_city and j > 5:
filter_train.append(j * 10 + i)
elif i == flags.finetune_city and j <= 5:
filter_valid.append(j * 10 + i)
# use first city for validation
file_list_train = uabCrossValMaker.make_file_list_by_key(idx, file_list, filter_train)
file_list_valid = uabCrossValMaker.make_file_list_by_key(idx, file_list, filter_valid)
dataReader_train = uabDataReader.ImageLabelReaderPatchSampleControl(
[3], [0, 1, 2], patchDir, file_list_train, flags.input_size, flags.batch_size,
weight, 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.batch_size, dataAug=' ',
block_mean=np.append([0], img_mean), batch_code=0)
# train
start_time = time.time()
model.train_config('X', 'Y', flags.n_train, flags.n_valid, flags.input_size, uabRepoPaths.modelPath,
loss_type='xent', par_dir='Inria_Domain_Selection')
model.run(train_reader=dataReader_train,
valid_reader=dataReader_valid,
pretrained_model_dir=flags.pred_model_dir.format(flags.finetune_city),
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=5, # 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))
def main(flags):
city_dict = {
'austin': 0,
'chicago': 1,
'kitsap': 2,
'tyrol-w': 3,
'vienna': 4
}
city_alpha = [0.2, 0.5, 0.1, 0.1, 0.1]
# make network
# define place holder
X = tf.placeholder(
tf.float32,
shape=[None, flags.input_size[0], flags.input_size[1], 3],
name='X')
y = tf.placeholder(
tf.int32,
shape=[None, flags.input_size[0], flags.input_size[1], 1],
name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({
'X': X,
'Y': y
},
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)
model.create_graph('X', class_num=flags.num_classes)
# 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 = blCol.getChannelMeans([0, 1, 2]) # get mean of rgb info
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 4],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=model.get_overlap() / 2)
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)])
dataReader_train = uabDataReader.ImageLabelReaderCitySampleControl(
[3], [0, 1, 2],
patchDir,
file_list_train,
flags.input_size,
flags.batch_size,
city_dict,
city_alpha,
dataAug='flip,rotate',
block_mean=np.append([0], img_mean))
# no augmentation needed for validation
dataReader_valid = uabDataReader.ImageLabelReaderCitySampleControl(
[3], [0, 1, 2],
patchDir,
file_list_valid,
flags.input_size,
flags.batch_size,
city_dict,
city_alpha,
dataAug=' ',
block_mean=np.append([0], img_mean))
# train
start_time = time.time()
model.train_config('X',
'Y',
flags.n_train,
flags.n_valid,
flags.input_size,
uabRepoPaths.modelPath,
loss_type='xent',
par_dir='Inria_Domain')
model.run(
train_reader=dataReader_train,
valid_reader=dataReader_valid,
pretrained_model_dir=PRED_DIR,
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=5, # 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))
def main(flags):
copyfile(
os.path.join(
flags.pred_file_dir,
'1iter_pred_building_binary_{}.npy'.format(flags.leave_city)),
os.path.join(
flags.pred_file_dir,
'iter_pred_building_binary_{}.npy'.format(flags.leave_city)))
flags.pred_file_dir = os.path.join(
flags.pred_file_dir,
'iter_pred_building_binary_{}.npy'.format(flags.leave_city))
# make network
# define place holder
X = tf.placeholder(
tf.float32,
shape=[None, flags.input_size[0], flags.input_size[1], 3],
name='X')
y = tf.placeholder(
tf.int32,
shape=[None, flags.input_size[0], flags.input_size[1], 1],
name='y')
y2 = tf.placeholder(tf.float32, shape=[None, 1], name='y2')
mode = tf.placeholder(tf.bool, name='mode')
model = UnetModelCrop_Iter({
'X': X,
'Y': y,
'Y2': y2
},
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)
model.create_graph('X', class_num=flags.num_classes)
# 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 = 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',
'city')
# use first city for validation
file_list_train = uabCrossValMaker.make_file_list_by_key(
idx, file_list, [i for i in range(5) if i != flags.leave_city])
file_list_valid = uabCrossValMaker.make_file_list_by_key(
idx, file_list, [flags.leave_city])
dataReader_train = uabDataReader.ImageLabelReader([3], [0, 1, 2],
patchDir,
file_list_train,
flags.input_size,
flags.batch_size,
dataAug='flip,rotate',
block_mean=np.append(
[0], img_mean),
batch_code=0)
dataReader_train_building = uabDataReader.ImageLabelReaderBuildingCustom(
[3], [0, 1, 2],
patchDir,
file_list_valid,
flags.input_size,
flags.batch_size,
dataAug='flip,rotate',
percent_file=flags.pred_file_dir,
block_mean=np.append([0], img_mean),
patch_prob=0.1,
binary=True)
# no augmentation needed for validation
dataReader_valid = uabDataReader.ImageLabelReader([3], [0, 1, 2],
patchDir,
file_list_valid,
flags.input_size,
flags.batch_size,
dataAug=' ',
block_mean=np.append(
[0], img_mean),
batch_code=0)
# train
start_time = time.time()
model.train_config('X',
'Y',
'Y2',
flags.n_train,
flags.n_valid,
flags.input_size,
uabRepoPaths.modelPath,
loss_type='xent',
par_dir='Inria_Domain_LOO')
model.run(
train_reader=dataReader_train,
train_reader_building=dataReader_train_building,
valid_reader=dataReader_valid,
pretrained_model_dir=flags.
finetune_dir, # train from scratch, no need to load pre-trained model
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=5, # 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))
def main(flags, weight_dict):
path_to_save = os.path.join(flags.weight_dir, 'shift_dict.pkl')
shift_dict = ersa_utils.load_file(path_to_save)
# 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.input_size[0], flags.input_size[1], 3], name='Z')
y = tf.placeholder(tf.int32, shape=[None, flags.input_size[0], flags.input_size[1], 1], name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelDTDA({'X': X, 'Z': Z, 'Y': y},
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)
model.create_graph('X', 'Z', class_num=flags.num_classes)
# 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 = blCol.getChannelMeans([0, 1, 2]) # get mean of rgb info
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr([0, 1, 2, 4],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=model.get_overlap() // 2)
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_source = 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)])
# AIOI dataset
blCol = uab_collectionFunctions.uabCollection(CITY_LIST[flags.leave_city])
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr([0, 1, 2, 3],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=model.get_overlap() // 2)
patchDir_target = extrObj.run(blCol)
idx, file_list = uabCrossValMaker.uabUtilGetFolds(patchDir_target, 'fileList.txt', 'force_tile')
file_list_target = uabCrossValMaker.make_file_list_by_key(idx, file_list, [i for i in range(5)])
with tf.name_scope('image_loader'):
# GT has no mean to subtract, append a 0 for block mean
dataReader_source = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir, file_list_source, 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_target = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir_target, file_list_target, flags.input_size,
flags.tile_size,
flags.batch_size, dataAug='flip,rotate',
block_mean=np.append([0], img_mean))
dataReader_valid = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir, file_list_valid, flags.input_size,
flags.tile_size,
flags.batch_size, dataAug='flip,rotate',
block_mean=np.append([0], img_mean))
# train
start_time = time.time()
model.train_config('X', 'Y', 'Z', flags.n_train, flags.n_valid, flags.input_size, uabRepoPaths.modelPath,
loss_type='xent', par_dir='domain_baseline/contorl_valid', lam=flags.lam)
model.load_source_weights(flags.model_dir, shift_dict, gpu=flags.GPU)
model.run(train_reader_source=dataReader_source,
train_reader_target=dataReader_target,
valid_reader=dataReader_valid,
pretrained_model_dir=None, # train from scratch, no need to load pre-trained model
isTrain=True,
img_mean=img_mean,
verb_step=100, # print a message every 100 step(sample)
save_epoch=5, # save the model every 5 epochs
gpu=flags.GPU,
tile_size=flags.tile_size,
patch_size=flags.input_size)
duration = time.time() - start_time
print('duration {:.2f} hours'.format(duration/60/60))
shape=[None, chip_size[0], chip_size[1], 1],
name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_ResFCN.ResFcnModel({
'X': X,
'Y': y
},
trainable=mode,
input_size=chip_size,
batch_size=5)
model.create_graph('X', class_num=2)
# create collection
# the original file is in /ei-edl01/data/uab_datasets/inria
blCol = uab_collectionFunctions.uabCollection('inria')
opDetObj = bPreproc.uabOperTileDivide(255)
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif',
'Map GT to (0, 1)', [3],
opDetObj)
rescObj.run(blCol)
print(blCol.readMetadata())
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 4], # extract all 4 channels
cSize=chip_size, # patch size as 224*224
numPixOverlap=0, # overlap as 0
extSave=['jpg', 'jpg', 'jpg',
'png'], # save rgb files as jpg and gt as png
isTrain=True,
gtInd=3)
def main(flags):
# ------------------------------------------Network---------------------------------------------#
# make network
# define place holder
X = tf.placeholder(tf.float32, shape=[None, flags.input_size[0], flags.input_size[1], 3], name='X')
y = tf.placeholder(tf.int32, shape=[None, flags.input_size[0], flags.input_size[1], 1], name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UnetMTL.UnetModelMTL({'X':X, 'Y':y},
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,
source_num=flags.s_num,
source_name=flags.s_name,
source_control=flags.s_control)
model.create_graph('X', class_num=flags.num_classes, start_filter_num=flags.sfn)
# ------------------------------------------Dataset Inria---------------------------------------------#
# create collection for inria
blCol_inria = uab_collectionFunctions.uabCollection('inria')
opDetObj_inria = bPreproc.uabOperTileDivide(255)
# [3] is the channel id of GT
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif', 'Map GT to (0, 1)', [3], opDetObj_inria)
rescObj.run(blCol_inria)
img_mean_inria = blCol_inria.getChannelMeans([0, 1, 2])
# extract patches
extrObj_inria = uab_DataHandlerFunctions.uabPatchExtr([0, 1, 2, 4],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=int(model.get_overlap() / 2))
patchDir_inria = extrObj_inria.run(blCol_inria)
# make data reader
# use uabCrossValMaker to get fileLists for training and validation
idx_inria, file_list_inria = uabCrossValMaker.uabUtilGetFolds(patchDir_inria, 'fileList.txt', 'force_tile')
# use first 5 tiles for validation
file_list_train_inria = uabCrossValMaker.make_file_list_by_key(idx_inria, file_list_inria,
[i for i in range(20, 136)])
file_list_valid_inria = uabCrossValMaker.make_file_list_by_key(idx_inria, file_list_inria,
[i for i in range(0, 20)])
with tf.name_scope('image_loader_inria'):
# GT has no mean to subtract, append a 0 for block mean
dataReader_train_inria = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir_inria, file_list_train_inria,
flags.input_size, flags.tile_size, flags.batch_size,
dataAug='flip,rotate',
block_mean=np.append([0], img_mean_inria))
# no augmentation needed for validation
dataReader_valid_inria = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir_inria, file_list_valid_inria,
flags.input_size, flags.tile_size,
flags.batch_size, dataAug=' ',
block_mean=np.append([0], img_mean_inria))
# ------------------------------------------Dataset Road---------------------------------------------#
# create collection for road
blCol_road = uab_collectionFunctions.uabCollection('road_5000')
opDetObj_road = bPreproc.uabOperTileDivide(255)
# [3] is the channel id of GT
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif', 'Map GT to (0, 1)', [3], opDetObj_road)
rescObj.run(blCol_road)
img_mean_road = blCol_road.getChannelMeans([0, 1, 2])
# extract patches
extrObj_road = uab_DataHandlerFunctions.uabPatchExtr([0, 1, 2, 4],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=int(model.get_overlap() / 2))
patchDir_road = extrObj_road.run(blCol_road)
# make data reader
# use uabCrossValMaker to get fileLists for training and validation
idx_road, file_list_road = uabCrossValMaker.uabUtilGetFolds(patchDir_road, 'fileList.txt', 'city')
# use first 5 tiles for validation
file_list_train_road = uabCrossValMaker.make_file_list_by_key(idx_road, file_list_road, [1])
file_list_valid_road = uabCrossValMaker.make_file_list_by_key(idx_road, file_list_road, [0, 2])
with tf.name_scope('image_loader_road'):
# GT has no mean to subtract, append a 0 for block mean
dataReader_train_road = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir_road, file_list_train_road,
flags.input_size, flags.tile_size, flags.batch_size,
dataAug='flip,rotate',
block_mean=np.append([0], img_mean_road))
# no augmentation needed for validation
dataReader_valid_road = uabDataReader.ImageLabelReader([3], [0, 1, 2], patchDir_road, file_list_valid_road,
flags.input_size, flags.tile_size,
flags.batch_size, dataAug=' ',
block_mean=np.append([0], img_mean_road))
# ------------------------------------------Train---------------------------------------------#
start_time = time.time()
model.train_config('X', 'Y', flags.n_train, flags.n_valid, flags.input_size, uabRepoPaths.modelPath,
loss_type='xent')
model.run(train_reader=[dataReader_train_inria, dataReader_train_road],
valid_reader=[dataReader_valid_inria, dataReader_valid_road],
pretrained_model_dir=None, # train from scratch, no need to load pre-trained model
isTrain=True,
img_mean=[img_mean_inria, img_mean_road],
verb_step=100, # print a message every 100 step(sample)
save_epoch=5, # 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))
def make_res50_features(model_name, task_dir, GPU=0, force_run=False):
feature_file_name = os.path.join(task_dir,
'res50_inria_{}.csv'.format(model_name))
patch_file_name = os.path.join(task_dir,
'res50_inria_{}.txt'.format(model_name))
if model_name == 'deeplab':
input_size = (321, 321)
overlap = 0
else:
input_size = (572, 572)
overlap = 184
blCol = uab_collectionFunctions.uabCollection('inria')
opDetObj = bPreproc.uabOperTileDivide(255)
rescObj = uabPreprocClasses.uabPreprocMultChanOp([], 'GT_Divide.tif',
'Map GT to (0, 1)', [3],
opDetObj)
rescObj.run(blCol)
img_mean = blCol.getChannelMeans([0, 1, 2])
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 4],
cSize=input_size,
numPixOverlap=overlap,
extSave=['jpg', 'jpg', 'jpg', 'png'],
isTrain=True,
gtInd=3,
pad=overlap // 2)
patchDir = extrObj.run(blCol)
idx, _ = uabCrossValMaker.uabUtilGetFolds(patchDir, 'fileList.txt',
'force_tile')
if not os.path.exists(feature_file_name) or not os.path.exists(
patch_file_name) or force_run:
os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
os.environ['CUDA_VISIBLE_DEVICES'] = '{}'.format(GPU)
import keras
input_size_fit = (224, 224)
file_name = os.path.join(patchDir, 'fileList.txt')
with open(file_name, 'r') as f:
files = f.readlines()
res50 = keras.applications.resnet50.ResNet50(include_top=True,
weights='imagenet')
fc2048 = keras.models.Model(
inputs=res50.input, outputs=res50.get_layer('flatten_1').output)
with open(feature_file_name, 'w+') as f:
with open(patch_file_name, 'w+') as f2:
for file_line in tqdm(files):
patch_name = file_line.split('.')[0][:-5]
img = np.zeros((input_size[0], input_size[1], 3),
dtype=np.uint8)
for cnt, file in enumerate(
file_line.strip().split(' ')[:3]):
img[:, :, cnt] = imageio.imread(
os.path.join(patchDir, file)) - img_mean[cnt]
img = np.expand_dims(crop_center(img, input_size_fit[0],
input_size_fit[1]),
axis=0)
fc1000 = fc2048.predict(img).reshape((-1, )).tolist()
writer = csv.writer(f, lineterminator='\n')
writer.writerow(['{}'.format(x) for x in fc1000])
f2.write('{}\n'.format(patch_name))
return feature_file_name, patch_file_name, input_size[0], patchDir, idx