import sys
import keras.backend as K
import numpy as np
import os
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
rel_filepath = sys.argv[1]
continue_setup = Setup('')
continue_setup.load(rel_filepath=rel_filepath)
change_lr = None
if change_lr is not None:
K.set_value(continue_setup.getModel().optimizer.lr, change_lr)
print('Changing the model optimizer learning rate to = %f' %
K.get_value(continue_setup.getModel().optimizer.lr))
else:
print('Model optimizer learning rate = %f' %
K.get_value(continue_setup.getModel().optimizer.lr))
XTrain_directory, YTrain_directory, XValidation_directory, YValidation_directory, XTest_directory, YTest_directory = continue_setup.getDataDirectory(
)
no_of_classes = 15000
def train_data_generator(XTrain_directory, YTrain_directory):
filenames = [str(i) + '.npy'
for i in range(2000, 1144000 + 1, 2000)] + ['1144636.npy']
from cnn.Setup import Setup
import sys
import keras.backend as K
rel_filepath = sys.argv[1]
continue_setup = Setup('')
continue_setup.load(rel_filepath=rel_filepath)
change_lr = None
if change_lr is not None:
K.set_value(continue_setup.getModel().optimizer.lr, change_lr)
print('Changing the model optimizer learning rate to = %f' % K.get_value(continue_setup.getModel().optimizer.lr))
else:
print('Model optimizer learning rate = %f' % K.get_value(continue_setup.getModel().optimizer.lr))
X_train_cnn, y_train_one_hot, X_val_cnn, y_val_one_hot, X_test_cnn, y_test_one_hot = continue_setup.getData()
for epoch in range(continue_setup.getEpoch() + 1, 10000):
print('Training \'%s\': Epoch %d' % (continue_setup.getName(), epoch))
dropout = continue_setup.getModel().fit(X_train_cnn, y_train_one_hot,
batch_size=64, epochs=1, verbose=1,
validation_data=(X_val_cnn, y_val_one_hot))
continue_setup.updateEpochs(add_epochs=1,
train_acc=dropout.history['acc'],
train_loss=dropout.history['loss'],
val_acc=dropout.history['val_acc'],
val_loss=dropout.history['val_loss'],
test_acc=[0],
import os
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
rel_filepath = sys.argv[1]
XTest_directory = sys.argv[2]
continue_setup = Setup('')
continue_setup.load(rel_filepath=rel_filepath)
no_of_classes = 15000
def test_data_generator(XTest_directory, YTest_directory):
filenames = [str(i) + '.npy'
for i in range(2000, 114000 + 1, 2000)] + ['115424.npy']
while True:
for filename in filenames:
X_test = np.load(os.path.join(XTest_directory, filename))
X_test = X_test.reshape(-1, 2048, 1, 1)
yield (X_test)
y_pred = continue_setup.getModel().predict_generator(test_data_generator(
XTest_directory, None),
steps=(114000 / 2000 + 1))
y_pred = np.argmax(y_pred, axis=1)
np.save('test_result.npy', y_pred)