def get_pretrained_weights(flags):
save_name = os.path.join(flags.weight_dir, 'weight.pkl')
if not os.path.exists(save_name):
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)
train_vars = [v for v in tf.global_variables() if 'global_step' not in v.name]
weight_dict = dict()
with tf.Session() as sess:
model.load(flags.model_dir, sess, epoch=95)
for v in train_vars:
theta = sess.run(v)
weight_dict[v.name] = theta
ersa_utils.save_file(save_name, weight_dict)
else:
weight_dict = ersa_utils.load_file(save_name)
tf.reset_default_graph()
return weight_dict
def get_pretrained_weights(weight_dir, model_dir):
save_name = os.path.join(weight_dir, 'weight.pkl')
if not os.path.exists(save_name):
X = tf.placeholder(tf.float32, shape=[None, input_size[0], input_size[1], 3], name='X')
y = tf.placeholder(tf.int32, shape=[None, input_size[0], input_size[1], 1], name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({'X': X, 'Y': y},
trainable=mode,
input_size=input_size,
start_filter_num=32)
model.create_graph('X', class_num=2)
train_vars = [v for v in tf.trainable_variables()]
weight_dict = dict()
with tf.Session() as sess:
model.load(model_dir, sess, epoch=95)
for v in train_vars:
theta = sess.run(v)
weight_dict[v.name] = theta
ersa_utils.save_file(save_name, weight_dict)
else:
weight_dict = ersa_utils.load_file(save_name)
tf.reset_default_graph()
return weight_dict
def evaluate_on_a_patch(
chip_size,
X_batch,
pretrained_model_dir=r'/hdd/Models/UnetCrop_inria_aug_grid_PS(572, 572)_BS5_EP100_LR0.0001_DS60_DR0.1_SFN32'
):
# experiment settings
batch_size = 9 # mini-batch size
learn_rate = 1e-4 # learning rate
decay_step = 60 # learn rate dacay after 60 epochs
decay_rate = 0.1 # learn rate decay to 0.1*before
epochs = 100 # total number of epochs to rum
start_filter_num = 32 # the number of filters at the first layer
model_name = 'inria_aug_grid' # a suffix for model name
# make network
# define place holder
tf.reset_default_graph()
X = tf.placeholder(tf.float32,
shape=[None, chip_size[0], chip_size[1], 3],
name='X')
y = tf.placeholder(tf.int32,
shape=[None, chip_size[0], chip_size[1], 1],
name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop(
{
'X': X,
'Y': y
},
trainable=mode,
model_name=model_name,
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)
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
model.load(pretrained_model_dir, sess)
pred = sess.run(model.output,
feed_dict={
model.inputs['X']: X_batch,
model.trainable: False
})
pred = pred[0, :, :, :]
pred = np.argmax(pred, axis=2)
return pred
# 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, input_size[0], input_size[1], 3],
name='Z')
y = tf.placeholder(tf.int32,
shape=[None, input_size[0], input_size[1], 1],
name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({
'X': X,
'Y': y
},
trainable=mode,
input_size=input_size,
batch_size=batch_size)
# create graph
model.create_graph('X', class_num=2)
# evaluate on tiles
model.evaluate(file_list,
file_list_truth,
parent_dir,
parent_dir_truth,
input_size,
None,
batch_size,
img_mean,
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_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, 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', 'Y', flags.n_train, flags.n_valid, flags.input_size, uabRepoPaths.modelPath,
loss_type='xent')
model.run(train_reader=dataReader_train,
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=GPU,
tile_size=flags.tile_size,
patch_size=flags.input_size,
continue_dir=model.ckdir)
duration = time.time() - start_time
print('duration {:.2f} hours'.format(duration/60/60))
# make network
# define place holder
X = tf.placeholder(tf.float32,
shape=[None, chip_size[0], chip_size[1], 3],
name='X')
y = tf.placeholder(tf.int32,
shape=[None, chip_size[0], chip_size[1], 1],
name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({
'X': X,
'Y': y
},
trainable=mode,
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
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))
orig_img_name = os.path.join(orig_img_dir, task_id, '{}.tif'.format(img_id))
orig_img = imageio.imread(orig_img_name)
orig_img = scipy.misc.imresize(orig_img, [2541, 2541])
orig_img = cv2.LUT(orig_img, table)
imageio.imsave(os.path.join(adjust_save_dir, '{}.tif'.format(img_id)), orig_img)
img_mean = get_sum_of_channel(orig_img) / (2541 ** 2)
print(img_mean)
tf.reset_default_graph()
# make the model
# define place holder
X = tf.placeholder(tf.float32, shape=[None, input_size[0], input_size[1], 3], name='X')
y = tf.placeholder(tf.int32, shape=[None, input_size[0], input_size[1], 1], name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({'X': X, 'Y': y},
trainable=mode,
input_size=input_size,
batch_size=5, start_filter_num=32)
# create graph
model.create_graph('X', class_num=2)
reader = uabDataReader.ImageLabelReader(gtInds=[0],
dataInds=[0],
nChannels=3,
parentDir=adjust_save_dir,
chipFiles=[['{}.tif'.format(img_id)]],
chip_size=input_size,
tile_size=tile_size,
batchSize=5,
block_mean=img_mean,
overlap=model.get_overlap(),
padding=np.array((model.get_overlap() / 2, model.get_overlap() / 2)),
isTrain=False)
X = tf.placeholder(tf.float32,
shape=[None, chip_size[0], chip_size[1], 3],
name='X')
y = tf.placeholder(tf.int32,
shape=[None, chip_size[0], chip_size[1], 1],
name='y')
mode = tf.placeholder(
tf.bool, name='mode') # This controls if you'll update weights or not
# Set this True when training
model = uabMakeNetwork_UNet.UnetModelCrop(
{
'X': X,
'Y': y
},
trainable=mode, # control if you're training or not
input_size=chip_size, # input size to NN, same as extracted
# patch size
batch_size=batch_size, # mini-batch size
learn_rate=learn_rate, # learning rate
decay_step=decay_step, # learn rate decay after 60 epochs
decay_rate=decay_rate, # learn rate decay to 0.1*before
epochs=epochs, # total number of epochs to run
start_filter_num=start_filter_num) # number of filters at the first layer
model.create_graph('X', class_num=2) # TensorFlow will now draw the graph
# 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',
def main(flags):
np.random.seed(int(flags.run_id))
tf.set_random_seed(int(flags.run_id))
if flags.start_layer >= 10:
pass
else:
flags.model_name += '_up{}'.format(flags.start_layer)
# 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(flags.ds_name)
blCol.readMetadata()
img_mean = blCol.getChannelMeans([1, 2, 3]) # get mean of rgb info
# extract patches
extrObj = uab_DataHandlerFunctions.uabPatchExtr(
[0, 1, 2, 3],
cSize=flags.input_size,
numPixOverlap=int(model.get_overlap()),
extSave=['png', 'jpg', 'jpg', 'jpg'],
isTrain=True,
gtInd=0,
pad=int(model.get_overlap() // 2))
patchDir = extrObj.run(blCol)
# make data reader
# use first 5 tiles for validation
idx, file_list = uabCrossValMaker.uabUtilGetFolds(patchDir, 'fileList.txt',
'tile')
file_list_train = uabCrossValMaker.make_file_list_by_key(
idx, file_list, [0, 1, 2, 3])
file_list_valid = uabCrossValMaker.make_file_list_by_key(
idx, file_list, [4, 5])
with tf.name_scope('image_loader'):
# GT has no mean to subtract, append a 0 for block mean
dataReader_train = uabDataReader.ImageLabelReader(
[0], [1, 2, 3],
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([0], [1, 2, 3],
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()
if flags.start_layer >= 10:
model.train_config('X',
'Y',
flags.n_train,
flags.n_valid,
flags.input_size,
uabRepoPaths.modelPath,
loss_type='xent',
par_dir='aemo/{}'.format(flags.ds_name))
else:
model.train_config('X',
'Y',
flags.n_train,
flags.n_valid,
flags.input_size,
uabRepoPaths.modelPath,
loss_type='xent',
par_dir='aemo/{}'.format(flags.ds_name),
train_var_filter=[
'layerup{}'.format(i)
for i in range(flags.start_layer, 10)
])
model.run(
train_reader=dataReader_train,
valid_reader=dataReader_valid,
pretrained_model_dir=flags.
model_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))
idx_truth,
file_list_truth, [i for i in range(0, 6)],
filter_list=[
'bellingham', 'bloomington', 'sfo', 'tyrol-e', 'innsbruck'
])
img_mean = blCol.getChannelMeans([0, 1, 2])
# make the model
# define place holder
X = tf.placeholder(tf.float32, shape=[None, 1052, 1052, 3], name='X')
y = tf.placeholder(tf.int32, shape=[None, 1052, 1052, 1], name='y')
mode = tf.placeholder(tf.bool, name='mode')
model = uabMakeNetwork_UNet.UnetModelCrop({
'X': X,
'Y': y
},
trainable=mode,
input_size=[1052, 1052],
batch_size=1)
# create graph
model.create_graph('X', class_num=2)
# evaluate on tiles
iou_return = model.evaluate(file_list_valid,
file_list_valid_truth,
parent_dir,
parent_dir_truth, [1052, 1052],
tile_size,
batch_size,
img_mean,
model_dir,
