train_datagen = DataGenerator(rescale=1. / 255,
random_crop_size=(cst.CROP_HEIGHT,
cst.CROP_WIDTH))
train_generator = train_datagen.flow_from_directory(
directory_small=cst.TRAIN_SMALL_SIZE,
directory_medium=cst.TRAIN_MEDIUM_SIZE,
directory_large=cst.TRAIN_LARGE_SIZE,
batch_size=BATCH_SIZE)
val_datagen = DataGenerator(rescale=1. / 255,
random_crop_size=(cst.CROP_HEIGHT, cst.CROP_WIDTH))
val_generator = val_datagen.flow_from_directory(
directory_small=cst.VALID_SMALL_SIZE,
directory_medium=cst.VALID_MEDIUM_SIZE,
directory_large=cst.VALID_LARGE_SIZE,
batch_size=BATCH_SIZE,
seed=1)
model = PConvUnet(weight_filepath=cst.WEIGHT_PATH)
model.fit(train_generator,
steps_per_epoch=8000 // BATCH_SIZE,
validation_data=val_generator,
validation_steps=8000 // BATCH_SIZE,
epochs=300,
plot_callback=None,
callbacks=[
TensorBoard(log_dir=cst.TFLOG_PATH, write_graph=False),
])
plt.close()
# Instantiate the model
model = PConvUnet()
model = PConvUnet(weight_filepath='data/logs/')
latest_weights = get_latest_weights_file()
print(latest_weights)
model.load(latest_weights)
# Run training for certain amount of epochs
model.fit(train_generator,
steps_per_epoch=100,
validation_data=val_generator,
validation_steps=10,
epochs=50,
plot_callback=plot_callback,
callbacks=[
TensorBoard(log_dir='../data/logs/initial_training',
write_graph=False)
])
# Load weights from previous run
latest_weights = get_latest_weights_file()
model = PConvUnet(weight_filepath='data/logs/')
model.load(latest_weights, train_bn=False, lr=0.00005)
# Run training for certain amount of epochs
model.fit(train_generator,
steps_per_epoch=100,
validation_data=val_generator,
validation_steps=10,
pred_img = model.predict([masked, mask])
# Clear current output and display test images
for i in range(len(ori)):
imsave('result/{}_orginal.png'.format(i), ori[i,:,:,:])
imsave('result/{}_masked.png'.format(i), masked[i,:,:,:])
imsave('result/{}_pred.png'.format(i), pred_img[i,:,:,:])
if not os.path.exists('result/logs'):
os.mkdir('result/logs')
model = PConvUnet(weight_filepath='result/logs/')
model.fit(
generator,
steps_per_epoch=1000,
epochs=1,
plot_callback=plot_callback,
)
# Load image
org = cv2.imread('./data/building.jpg')
org = cv2.cvtColor(org, cv2.COLOR_BGR2RGB)
org = org / 255
shape = org.shape
print(f"Shape of image is: {shape}")
# Load mask
org_mask = random_mask(shape[0], shape[1])
# Image + mask
masked_org = deepcopy(org)
width_shift_range=0.2,
height_shift_range=0.2,
rescale=1. / 255,
horizontal_flip=True
)
train_generator = train_datagen.flow_from_directory(
TRAIN_DIR, target_size=(256, 256), batch_size=BATCH_SIZE
)
# Create validation generator
val_datagen = DataGenerator(rescale=1. / 255)
val_generator = val_datagen.flow_from_directory(
VAL_DIR, target_size=(256, 256), batch_size=BATCH_SIZE, seed=1
)
# Instantiate the model
model = PConvUnet(weight_filepath="{}/PConv-Keras/data/model/".format(path_prefix))
# Run training for certain amount of epochs
model.fit(
train_generator,
steps_per_epoch=10,
validation_data=val_generator,
validation_steps=100,
epochs=5,
plot_callback=None,
callbacks=[
TensorBoard(log_dir="{}/PConv-Keras/data/model/initial_training".format(path_prefix), write_graph=False)
]
)