parser = argparse.ArgumentParser(description="predicter")
parser.add_argument("--img_path",
default="./images/1.jpg",
help="target img path")
parser.add_argument("--architecture",
default="PSPNet",
choices=["PSPNet", "SegUNet"],
help="architecture type")
parser.add_argument("--weight",
default="./pretrained/LIP_PSPNet50_05.hdf5",
help="pretrained weight path")
parser.add_argument("--output_path",
default="./response.json",
help="output path")
args = parser.parse_args()
# load model
model = PSPNet50()
model.load_weights(args.weight)
# inference
inputs = cv2.imread(args.img_path)
outputs = inference(model, inputs)
# create response
response = createResponse(outputs, inputs)
# save response
with open(args.output_path, "w") as f:
json.dump(response, f, indent=2)
def main(args):
# set the necessary list
train_list = pd.read_csv(args.train_list, header=None)
val_list = pd.read_csv(args.val_list, header=None)
# set the necessary directories
trainimg_dir = args.trainimg_dir
trainmsk_dir = args.trainmsk_dir
valimg_dir = args.valimg_dir
valmsk_dir = args.valmsk_dir
# get old session old_session = KTF.get_session()
with tf.Graph().as_default():
session = tf.Session('')
KTF.set_session(session)
KTF.set_learning_phase(1)
# class weights
classes = ['background', 'hat', 'hair', 'glove', 'sunglasses', 'upperclothes',
'dress', 'coat', 'socks', 'pants', 'jumpsuits', 'scarf', 'skirt',
'face', 'leftArm', 'rightArm', 'leftLeg', 'rightLeg', 'leftShoe','rightShoe']
if args.class_weights:
"""
class_weights = {0:1, 1:40, 2:1, 3:114, 4:151, 5:3, 6:53, 7:7, 8:165, 9:7, 10:106,
11:249, 12:150, 13:1, 14:1, 15:1, 16:1, 17:1, 18:114, 19:118}
"""
class_weights = [1, 40, 1, 114, 151, 3, 53, 7, 165, 7, 106, 249, 150, 1, 1, 1, 1, 1, 114, 118]
# set callbacks
fpath = "./pretrained_class_weights/LIP_PSPNet50_class_weights{epoch:02d}.hdf5"
cp_cb = ModelCheckpoint(filepath = fpath, monitor='val_loss', verbose=1, save_best_only=True, mode='auto', period=2)
es_cb = EarlyStopping(monitor='val_loss', patience=2, verbose=1, mode='auto')
tb_cb = TensorBoard(log_dir="./pretrained_class_weights", write_images=True)
# set generater
train_gen = data_gen_small(
trainimg_dir,
trainmsk_dir,
train_list,
args.batch_size,
[args.input_shape[0], args.input_shape[1]],
args.n_labels)
val_gen = data_gen_small(
valimg_dir,
valmsk_dir,
val_list,
args.batch_size,
[args.input_shape[0], args.input_shape[1]],
args.n_labels)
# set model
pspnet = PSPNet50(
input_shape=args.input_shape,
n_labels=args.n_labels,
output_mode=args.output_mode,
upsample_type=args.upsample_type)
print(pspnet.summary())
# compile model
pspnet.compile(
loss=args.loss,
optimizer=args.optimizer,
metrics=["accuracy"])
# fit with genarater
pspnet.fit_generator(
generator=train_gen,
steps_per_epoch=args.epoch_steps,
epochs=args.n_epochs,
validation_data=val_gen,
validation_steps=args.val_steps,
class_weight=class_weights,
callbacks=[cp_cb, es_cb, tb_cb])
# save model
with open("./pretrained_class_weights/LIP_PSPNet50.json", "w") as json_file:
json_file.write(json.dumps(json.loads(pspnet.to_json()), indent=2))
print("save json model done...")
def main(args):
# set the necessary list
# train_list = pd.read_csv(args.train_list,header=None)
# val_list = pd.read_csv(args.val_list,header=None)
# set the necessary directories
trainimg_dir = args.trainimg_dir
trainmsk_dir = args.trainmsk_dir
valimg_dir = args.valimg_dir
valmsk_dir = args.valmsk_dir
# get old session
# old_session = KTF.get_session()
with tf.Graph().as_default():
session = tf.Session('')
KTF.set_session(session)
KTF.set_learning_phase(1)
# set callbacks
fpath = './pretrained_mask/' + args.name + '{epoch:02d}.hdf5'
cp_cb = ModelCheckpoint(filepath=fpath,
monitor='val_loss',
verbose=1,
mode='auto',
period=1)
tb_cb = TensorBoard(log_dir="./pretrained_mask",
write_graph=True,
write_images=True)
seq = iaa.Sequential(
[
iaa.Crop(
px=(0, 16)
), # crop images from each side by 0 to 16px (randomly chosen)
iaa.Fliplr(0.5), # horizontally flip 50% of the images
sometimes(
iaa.Affine(
scale={
"x": (0.8, 1.2),
"y": (0.8, 1.2)
},
# scale images to 80-120% of their size, individually per axis
translate_percent={
"x": (-0.2, 0.2),
"y": (-0.2, 0.2)
}, # translate by -20 to +20 percent (per axis)
rotate=(-10, 10), # rotate by -45 to +45 degrees
)),
],
random_order=True)
if args.dataset == 'coco':
train_gen = Datahandler_COCO(trainimg_dir,
trainmsk_dir).make_batches(
batchsize=args.batch_size,
inputshape=args.input_shape,
augmentation=seq)
val_gen = Datahandler_COCO(valimg_dir, valmsk_dir).make_batches(
batchsize=args.batch_size,
inputshape=args.input_shape,
augmentation=None)
elif args.dataset == 'pascal_khamba':
train_gen = Pascal_Generator(trainimg_dir,
trainmsk_dir).make_batches(
batchsize=args.batch_size,
inputshape=args.input_shape,
augmentation=seq)
val_gen = Pascal_Generator(valimg_dir, valmsk_dir).make_batches(
batchsize=args.batch_size,
inputshape=args.input_shape,
augmentation=None)
else:
train_gen = Default_Generator(trainimg_dir,
trainmsk_dir).make_batches(
batchsize=args.batch_size,
inputshape=args.input_shape,
augmentation=seq)
val_gen = Default_Generator(valimg_dir, valmsk_dir).make_batches(
batchsize=args.batch_size,
inputshape=args.input_shape,
augmentation=None)
# set model
pspnet = PSPNet50(input_shape=args.input_shape,
n_labels=args.n_labels,
output_mode=args.output_mode,
upsample_type=args.upsample_type)
print(pspnet.summary())
if args.load is not None:
print("loadinf weights")
pspnet.load_weights(args.load)
# compile model
pspnet.compile(loss=args.loss,
optimizer=args.optimizer,
metrics=["accuracy"])
# fit with genarater
pspnet.fit_generator(generator=train_gen,
steps_per_epoch=args.steps,
epochs=args.epochs,
validation_data=val_gen,
validation_steps=args.val_steps,
callbacks=[cp_cb, tb_cb],
verbose=True)
# save model
with open("./pretrained_mask/" + args.name + ".json", "w") as json_file:
json_file.write(json.dumps(json.loads(pspnet.to_json()), indent=2))
print("save json model done...")
def main(args):
# set the necessary list
train_list = pd.read_csv(args.train_list, header=None)
val_list = pd.read_csv(args.val_list, header=None)
# set the necessary directories
trainimg_dir = args.trainimg_dir
trainmsk_dir = args.trainmsk_dir
valimg_dir = args.valimg_dir
valmsk_dir = args.valmsk_dir
# get old session
old_session = KTF.get_session()
with tf.Graph().as_default():
session = tf.Session('')
KTF.set_session(session)
KTF.set_learning_phase(1)
# set callbacks
fpath = './pretrained_mask/LIP_PSPNet50_mask{epoch:02d}.hdf5'
cp_cb = ModelCheckpoint(filepath=fpath,
monitor='val_loss',
verbose=1,
save_best_only=True,
mode='auto',
period=5)
es_cb = EarlyStopping(monitor='val_loss',
patience=2,
verbose=1,
mode='auto')
tb_cb = TensorBoard(log_dir="./pretrained_mask", write_images=True)
# set generater
train_gen = data_gen_small(trainimg_dir, trainmsk_dir, train_list,
args.batch_size,
[args.input_shape[0], args.input_shape[1]],
args.n_labels)
val_gen = data_gen_small(valimg_dir, valmsk_dir, val_list,
args.batch_size,
[args.input_shape[0], args.input_shape[1]],
args.n_labels)
# set model
pspnet = PSPNet50(input_shape=args.input_shape,
n_labels=args.n_labels,
output_mode=args.output_mode,
upsample_type=args.upsample_type)
print(pspnet.summary())
# compile model
pspnet.compile(loss=args.loss,
optimizer=args.optimizer,
metrics=["accuracy"])
# fit with genarater
pspnet.fit_generator(generator=train_gen,
steps_per_epoch=args.epoch_steps,
epochs=args.n_epochs,
validation_data=val_gen,
validation_steps=args.val_steps,
callbacks=[cp_cb, es_cb, tb_cb])
# save model
with open("./pretrained_mask/LIP_SegUNet_mask.json", "w") as json_file:
json_file.write(json.dumps(json.loads(segunet.to_json()), indent=2))
print("save json model done...")
#
if __name__ == '__main__':
trainroot1 = "train"
trainroot2 = "train2"
folder_create(trainroot2)
valroot = "val"
model_file = "model.hdf5"
BATCH_SIZE = 5
NUM_EPOCH = 2
# sizeおよびch
size = [512,512]
input_ch = 3
color_dic = {1:[255,255,255]}
output_ch = len(color_dic) + 1
# データ拡張
# data_augment_copy(trainroot1, trainroot2)
# modelのcompile
input_shape = [size[0], size[1], input_ch]
model = PSPNet50(input_shape = input_shape, n_labels = output_ch)
# model.compile(loss=, optimizer="adadelta", metrics=["accuracy"])
model_compile_unet(model)
# model構築（Trainとvalidationで）
history = train_unet(trainroot2,valroot,model_file,model,size, BATCH_SIZE, NUM_EPOCH, color_dic)
plot_hist_dice(history)
# trainroot2の消去
folder_delete(trainroot2)