def train_sub(model,
model_name,
train,
val,
epochs=100,
batch_size=8,
verbose=2):
tf.compat.v1.reset_default_graph()
tf.random.set_seed(42424242)
tf.compat.v1.set_random_seed(42424242)
print('\n\n\nMODEL:' + model_name)
earlystopper = EarlyStopping(patience=20, verbose=2)
os.makedirs("checkpoints", exist_ok=True)
model_path_name = 'checkpoints/ckp_{}.h5'.format(model_name)
checkpointer = ModelCheckpoint(model_path_name,
verbose=1,
save_best_only=True)
os.makedirs("tf_logs", exist_ok=True)
log_dir = "tf_logs/" + model_name + "_" + datetime.datetime.now().strftime(
"%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,
histogram_freq=1)
history = model.fit(
train,
validation_data=val,
epochs=epochs,
callbacks=[earlystopper, checkpointer, tensorboard_callback],
verbose=verbose)
model.load_weights(model_path_name)
submission.create(model, model_name)
def main():
x1, y1 = data.get_training_data()
x2, y2 = data.get_training_data2()
x = np.concatenate((x1, x2), axis=0)
y = np.concatenate((y1, y2), axis=0)
from models.sdf_model import get_CNN_SDFt, get_flat_tanh_CNN_SDFt
# # sdf flat tanh
# train, val = data_g.get_train_val_iterators(aug=None)
# model = get_flat_tanh_CNN_SDFt()
# model_name = 'SDF_cnn_scaled_tanh_EXTDATA_noaug'
# train_sub(model, model_name, x, y, epochs=100)
# submission.create(model, model_name)
# sdf normal tanh
model = get_CNN_SDFt()
model_name = 'SDF_cnn_tanh_EXTDATA_noaug'
train_sub(model, model_name, x, y, epochs=100)
submission.create(model, model_name)
def main():
# no augmentation
train, val = data_g.get_train_val_iterators(aug=None)
model = unet.get_model(None, None, 3, do_compile=False)
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy', f1, tf.keras.metrics.MeanIoU(num_classes=2)])
model_name = 'unet2_crossentropy_augmentation_none'
train_sub(model, model_name, train, val, epochs=100, verbose=1)
submission.create(model, model_name)
# small augmentation
train, val = data_g.get_train_val_iterators(aug='small')
model = unet.get_model(None, None, 3, do_compile=False)
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy', f1, tf.keras.metrics.MeanIoU(num_classes=2)])
model_name = 'unet2_crossentropy_augmentation_small'
train_sub(model, model_name, train, val, epochs=100, verbose=1)
submission.create(model, model_name)
# medium augmentation
train, val = data_g.get_train_val_iterators(aug='medium')
model = unet.get_model(None, None, 3, do_compile=False)
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy', f1, tf.keras.metrics.MeanIoU(num_classes=2)])
model_name = 'unet2_crossentropy_augmentation_medium'
train_sub(model, model_name, train, val, epochs=100, verbose=1)
submission.create(model, model_name)
# large augmentation
train, val = data_g.get_train_val_iterators(aug='large')
model = unet.get_model(None, None, 3, do_compile=False)
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy', f1, tf.keras.metrics.MeanIoU(num_classes=2)])
model_name = 'unet2_crossentropy_augmentation_large'
train_sub(model, model_name, train, val, epochs=100, verbose=1)
submission.create(model, model_name)
def cross_val(model, model_name, load_training_data=True, x=None, y=None, augment_data_func=None, use_class_weight=False, epochs=100, batch_size=4, verbose=2):
print('\n\n\n' '5-Cross-Validation: ' + model_name)
if load_training_data:
x, y = data.get_training_data()
kf = KFold(n_splits=5, shuffle=True, random_state=42424242)
reset_weights = model.get_weights() # for reseting the model weights
histories = []
index = 0
best_losses = []
for train_index, test_index in kf.split(x):
print('\nSplit k=' + str(index))
x_train, x_test = x[train_index], x[test_index]
y_train, y_test = y[train_index], y[test_index]
if augment_data_func != None:
x_train, y_train = augment_data_func(x_train, y_train)
name = model_name + '_crossval-k' + str(index)
crt_history = fit(model, x_train, y_train, epochs=epochs, validation_data=(x_test, y_test), checkpoint_suffix=name, batch_size=batch_size, verbose=verbose,
use_class_weight=use_class_weight)
histories.append(crt_history)
best_epoch = get_min_index(crt_history.history['loss'])
best_loss = crt_history.history['loss'][best_epoch]
best_losses.append(best_loss)
index += 1
model.set_weights(reset_weights) # reset the model weights
# EVALUATION
print("\nCROSS-VALIDATION-RESULTS")
print("model_name: " + model_name)
#print("optimizer: " + str(model.optimizer))
#print("loss: " + str(model.loss))
print("epochs: 100, early_stopping_patience = " + str(PATIENCE))
print('\nMETRICS')
# get used metrics
keys = histories[0].history.keys()
# average of metrics over all data splits
average_metrics = {}
index = 0
for h in histories:
best_index = get_min_index(h.history['loss'])
current_metrics = {}
for k in keys:
if k not in average_metrics:
average_metrics[k] = h.history[k][best_index]
else:
average_metrics[k] += h.history[k][best_index]
current_metrics[k] = h.history[k][best_index]
print('k='+str(index), current_metrics)
index += 1
for k in average_metrics:
average_metrics[k] /= len(histories)
print("\nAVERAGE-METRICS")
print(average_metrics)
# reload first split model weights
model.load_weights("checkpoints/ckp_" + model_name + '_crossval-k' + '0' + ".h5")
# create submission
submission.create(model, model_name + '_crossval-k' + '0' + ".h5")
def main():
model = cnn.get_model(None, None, 3, do_compile=False)
model.load_weights('checkpoints/ckp_cnn_dice_SPECIALDATA.h5')
submission.create(model, 'ckp_cnn_dice_SPECIALDATA')