def submission():
"""
Generate submission file for the trained models.
"""
print('Loading and compiling models...')
model_systole = get_vgg_model()
model_diastole = get_vgg_model()
print('Loading models weights...')
model_systole.load_weights('weights_systole_best.hdf5')
model_diastole.load_weights('weights_diastole_best.hdf5')
print('Loading validation data...')
X, ids = load_validation_data()
print('Pre-processing images...')
X = preprocess(X)
batch_size = 32
print('Predicting on validation data...')
pred_systole = model_systole.predict(X, batch_size=batch_size, verbose=1)
pred_diastole = model_diastole.predict(X, batch_size=batch_size, verbose=1)
# real predictions to CDF
cdf_pred_systole = pred_systole.cumsum(axis=-1)
cdf_pred_diastole = pred_diastole.cumsum(axis=-1)
print('Accumulating results...')
sub_systole = accumulate_study_results(ids, cdf_pred_systole)
sub_diastole = accumulate_study_results(ids, cdf_pred_diastole)
# write to submission file
print('Writing submission to file...')
fi = csv.reader(open('/data/heart/sample_submission_test.csv'))
f = open('submission.csv', 'w')
fo = csv.writer(f, lineterminator='\n')
fo.writerow(fi.next())
for line in fi:
idx = line[0]
key, target = idx.split('_')
key = int(key)
out = [idx]
if key in sub_systole:
if target == 'Diastole':
out.extend(list(sub_diastole[key][0]))
else:
out.extend(list(sub_systole[key][0]))
else:
print('Miss {0}'.format(idx))
fo.writerow(out)
f.close()
print('Done.')
def submission():
"""
Generate submission file for the trained models.
"""
print('Loading and compiling models...')
model_systole = get_vgg_model()
model_diastole = get_vgg_model()
print('Loading models weights...')
model_systole.load_weights('weights_systole_best.hdf5')
model_diastole.load_weights('weights_diastole_best.hdf5')
print('Loading validation data...')
X, ids = load_validation_data()
print('Pre-processing images...')
X = preprocess(X)
batch_size = 32
print('Predicting on validation data...')
pred_systole = model_systole.predict(X, batch_size=batch_size, verbose=1)
pred_diastole = model_diastole.predict(X, batch_size=batch_size, verbose=1)
# real predictions to CDF
cdf_pred_systole = pred_systole.cumsum(axis=-1)
cdf_pred_diastole = pred_diastole.cumsum(axis=-1)
print('Accumulating results...')
sub_systole = accumulate_study_results(ids, cdf_pred_systole)
sub_diastole = accumulate_study_results(ids, cdf_pred_diastole)
# write to submission file
print('Writing submission to file...')
fi = csv.reader(open('/data/heart/sample_submission_test.csv'))
f = open('submission.csv', 'w')
fo = csv.writer(f, lineterminator='\n')
fo.writerow(fi.next())
for line in fi:
idx = line[0]
key, target = idx.split('_')
key = int(key)
out = [idx]
if key in sub_systole:
if target == 'Diastole':
out.extend(list(sub_diastole[key][0]))
else:
out.extend(list(sub_systole[key][0]))
else:
print('Miss {0}'.format(idx))
fo.writerow(out)
f.close()
print('Done.')
def train(train_prefix_dir="/data/heart"):
"""
Training systole and diastole models.
"""
print('Loading and compiling models...')
model_systole = get_vgg_model()
model_diastole = get_vgg_model()
print('Loading training data...')
X, y = load_train_data(train_prefix_dir)
print('Pre-processing images...')
X = preprocess(X)
# split to training and test
X_train, y_train, X_test, y_test = split_data(X, y, split_ratio=0.2)
nb_iter = 200
epochs_per_iter = 1
batch_size = 32
calc_crps = 1 # calculate CRPS every n-th iteration (set to 0 if CRPS estimation is not needed)
# remember min val. losses (best iterations), used as sigmas for submission
min_val_loss_systole = sys.float_info.max
min_val_loss_diastole = sys.float_info.max
print('-'*50)
print('Training...')
print('-'*50)
# Create Image Augmentation
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=15, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=True) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(X_train)
# Create model checkpointers for systole and diastole
systole_checkpointer_best = ModelCheckpoint(filepath="weights_systole_best.hdf5", verbose=1, save_best_only=True)
diastole_checkpointer_best = ModelCheckpoint(filepath="weights_diastole_best.hdf5", verbose=1, save_best_only=True)
systole_checkpointer = ModelCheckpoint(filepath="weights_systole.hdf5", verbose=1, save_best_only=False)
diastole_checkpointer = ModelCheckpoint(filepath="weights_diastole.hdf5", verbose=1, save_best_only=False)
# Create 600-dimentional y cdfs from observations
y_syst_train = np.array([(i < np.arange(600)) for i in y_train[:, 0]], dtype=np.uint8)
y_syst_test = np.array([(i < np.arange(600)) for i in y_test[:, 0]], dtype=np.uint8)
y_diast_train = np.array([(i < np.arange(600)) for i in y_train[:, 1]], dtype=np.uint8)
y_diast_test = np.array([(i < np.arange(600)) for i in y_test[:, 1]], dtype=np.uint8)
print('Fitting Systole Shapes')
hist_systole = model_systole.fit_generator(datagen.flow(X_train, y_syst_train, batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_iter, show_accuracy=False,
validation_data=(X_test, y_syst_test),
callbacks=[systole_checkpointer, systole_checkpointer_best],
nb_worker=1)
print('Fitting Diastole Shapes')
hist_diastole = model_diastole.fit_generator(datagen.flow(X_train, y_diast_train, batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_iter, show_accuracy=False,
validation_data=(X_test, y_diast_test),
callbacks=[diastole_checkpointer, diastole_checkpointer_best],
nb_worker=1)
loss_systole = hist_systole.history['loss'][-1]
loss_diastole = hist_diastole.history['loss'][-1]
val_loss_systole = hist_systole.history['val_loss'][-1]
val_loss_diastole = hist_diastole.history['val_loss'][-1]
if calc_crps > 0:
print('Evaluating CRPS...')
pred_systole = model_systole.predict(X_train, batch_size=batch_size, verbose=1)
pred_diastole = model_diastole.predict(X_train, batch_size=batch_size, verbose=1)
val_pred_systole = model_systole.predict(X_test, batch_size=batch_size, verbose=1)
val_pred_diastole = model_diastole.predict(X_test, batch_size=batch_size, verbose=1)
# CDF for train and test data (actually a step function)
cdf_train = real_to_cdf(np.concatenate((y_train[:, 0], y_train[:, 1])))
cdf_test = real_to_cdf(np.concatenate((y_test[:, 0], y_test[:, 1])))
# CDF for predicted data
cdf_pred_systole = real_to_cdf(pred_systole, loss_systole)
cdf_pred_diastole = real_to_cdf(pred_diastole, loss_diastole)
cdf_val_pred_systole = real_to_cdf(val_pred_systole, val_loss_systole)
cdf_val_pred_diastole = real_to_cdf(val_pred_diastole, val_loss_diastole)
# evaluate CRPS on training data
crps_train = crps(cdf_train, np.concatenate((cdf_pred_systole, cdf_pred_diastole)))
print('CRPS(train) = {0}'.format(crps_train))
# evaluate CRPS on test data
crps_test = crps(cdf_test, np.concatenate((cdf_val_pred_systole, cdf_val_pred_diastole)))
print('CRPS(test) = {0}'.format(crps_test))
# save best (lowest) val losses in file (to be later used for generating submission)
with open('val_loss.txt', mode='w+') as f:
f.write(str(min(hist_systole.history['val_loss'])))
f.write('\n')
f.write(str(min(hist_diastole.history['val_loss'])))
"""
