def main(_):
tf.set_random_seed(1234)
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = './'
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
# Second step: with hyperparameters determined in the first run, re-train
# your model on the original train set.
model.train(x_train, y_train, 50)
# Third step: after re-training, test your model on the test set.
# Report testing accuracy in your hard-copy report.
model.test_or_validate(x_test, y_test, [30, 35, 40, 45, 50])
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
#data_dir = "/content/drive/My Drive/Colab Notebooks/code/HW3/data/"
data_dir = "/content/drive/My Drive/data"
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
#model.train(x_train_new, y_train_new, 200)
#model.test_or_validate(x_valid, y_valid, [10,20,30,40,50,100,150,200])
# Second step: with hyperparameters determined in the first run, re-train
# your model on the original train set.
# model.train(x_train, y_train, 200)
# Third step: after re-training, test your model on the test set.
# Report testing accuracy in your hard-copy report.
model.test_or_validate(
x_test, y_test,
[100, 110, 120, 130, 140, 150, 160, 170, 180, 190, 200])
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = "data/"
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
#
#model.train(x_train_new, y_train_new, 200)
#model.train(x_train_new, y_train_new, 3)
#model.test_or_validate(x_valid, y_valid, [160, 170, 180, 190, 200])
#model.test_or_validate(x_valid, y_valid, [10])
# Second step: with hyperparameters determined in the first run, re-train
# your model on the original train set.
model.train(x_train, y_train, 150)
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = '../cifar-10-batches-py/'
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
# model.train(x_train_new, y_train_new, 200)
# model.train(x_train_new, y_train_new, 10)
# model.test_or_validate(x_valid, y_valid, [160, 170, 180, 190, 200])
# model.test_or_validate(x_valid, y_valid, list(range(80, 201, 10)))
# model.test_or_validate(x_valid, y_valid, [150])
# Second step: with hyperparameters determined in the first run, re-train
# your model on the original train set.
model.train(x_train, y_train, 140)
# Third step: after re-training, test your model on the test set.
# Report testing accuracy in your hard-copy report.
model.test_or_validate(x_test, y_test, [140])
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = "cifar-10-batches-py"
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train, 8000)
parse_record(x_train[0], True)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
def del_all_flags(FLAGS):
flags_dict = FLAGS._flags()
keys_list = [keys for keys in flags_dict]
for keys in keys_list:
FLAGS.__delattr__(keys)
# model.train(x_train_new, y_train_new, 3)
sess_test = tf.Session()
del_all_flags(tf.flags.FLAGS)
model_test = Cifar(sess_test, configure())
model_test.test_or_validate(x_valid, y_valid, [1, 2, 3])
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = "/Users/tiandi03/Desktop/dataset/cifar-10-batches-py"
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
model.train(x_train_new, y_train_new, 200)
model.test_or_validate(x_valid, y_valid, [160, 170, 180, 190, 200])
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = os.path.join(os.path.abspath(os.getcwd()),"ResNet/data")
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# First step: use the train_new set and the valid set to choose hyperparameters.
model.train(x_train_new, y_train_new, 200)
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
# Download cifar-10 dataset from https://www.cs.toronto.edu/~kriz/cifar.html
data_dir = "cifar-10-batches-py"
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
model.train(x_train, y_train, 40)
model.test_or_validate(x_test, y_test, [5, 10, 15, 20, 25, 30, 35, 40])
def main(_):
sess = tf.Session()
print('---Prepare data...')
### YOUR CODE HERE
data_dir = '../cifar-10-batches-py'
### END CODE HERE
x_train, y_train, x_test, y_test = load_data(data_dir)
x_train_new, y_train_new, x_valid, y_valid = train_valid_split(
x_train, y_train)
model = Cifar(sess, configure())
### YOUR CODE HERE
# from Network import ResNet
# network = ResNet(1, 3, 10, 16)
# ips = tf.placeholder(tf.float32, shape=(100, 32, 32, 3))
# sess.run(tf.global_variables_initializer())
# sess.run(tf.local_variables_initializer())
# net = network(ips,training=True)
# from tensorflow.keras import Model
# model = Model(inputs=ips, outputs=net)
# print(model.summary)
# # print(sess.run(network(ips,training=True)))
# writer = tf.summary.FileWriter('output', sess.graph)
# writer.close()
# First step: use the train_new set and the valid set to choose hyperparameters.
# model.train(x_train_new, y_train_new, 200)
# while True:
# model.train(x_train_new, y_train_new, 600)
# model.test_or_validate(x_valid,y_valid,[i*10 for i in range(1,11)])
# model.test_or_validate(x_valid,y_valid,[20])
# model.test_or_validate(x_valid, y_valid, [160, 170, 180, 190, 200])
# model.test_or_validate(x_valid,y_valid,[10])
# Second step: with hyperparameters determined in the first run, re-train
# your model on the original train set.
# model.train(x_train, y_train, 200)
# Third step: after re-training, test your model on the test set.
# Report testing accuracy in your hard-copy report.
model.test_or_validate(x_test, y_test, [170])
def main(_):
os.environ["CUDA_VISIBLE_DEVICES"] = '3'
sess = tf.Session()
print('---Prepare data...')
x_train, y_train, x_test, y_test = load_data()
x_train_new, y_train_new, x_valid, y_valid \
= train_valid_split(x_train, y_train)
model = MNIST(sess, configure())
### YOUR CODE HERE
# First run: use the train_new set and the valid set to choose
# hyperparameters, like num_hid_layers, num_hid_units, stopping epoch, etc.
# Report chosen hyperparameters in your hard-copy report.
num_hidden_layers = [1, 2, 3]
num_hidden_units = [256, 512, 1024]
batch_sizes = [32, 64, 128]
num_epochs = [1, 5, 10]
for model.conf.num_hid_layers in num_hidden_layers:
for model.conf.num_hid_units in num_hidden_units:
for model.conf.batch_size in batch_sizes:
for epochs in num_epochs:
print("Hidden layers: {}, Hidden units: {}, Batch size: {}, Max epochs: {}".format(model.conf.num_hid_layers, \
model.conf.num_hid_units, model.conf.batch_size, epochs))
model.train(x_train_new,
y_train_new,
x_valid,
y_valid,
epochs,
validation=True)
# Second run: with hyperparameters determined in the first run, re-train
# your model on the original train set.
model.train(x_train, y_train, None, None, 10, validation=False)
# Third run: after re-training, test your model on the test set.
# Report testing accuracy in your hard-copy report.
model.test(x_test, y_test, 10)
def main(_):
os.environ["CUDA_VISIBLE_DEVICES"] = '3'
sess = tf.Session()
print('---Prepare data...')
x_train, y_train, x_test, y_test = load_data()
x_train_new, y_train_new, x_valid, y_valid \
= train_valid_split(x_train, y_train)
model = MNIST(sess, configure())
### YOUR CODE HERE
# First run: use the train_new set and the valid set to choose
# hyperparameters, like num_hid_layers, num_hid_units, stopping epoch, etc.
# Report chosen hyperparameters in your hard-copy report.
model.train(x_train_new,
y_train_new,
x_valid,
y_valid,
max_epoch=1,
validation=True)
def main(_):
os.environ["CUDA_VISIBLE_DEVICES"] = '3'
#sess = tf.Session()
print('---Prepare data...')
x_train, y_train, x_test, y_test = load_data()
x_train_new, y_train_new, x_valid, y_valid \
= train_valid_split(x_train, y_train)
# model = MNIST(sess, conf())
### YOUR CODE HERE
conf = configure()
# First run: use the train_new set and the valid set to choose
# hyperparameters, like num_hid_layers, num_hid_units, stopping epoch, etc.
# Report chosen hyperparameters in your hard-copy report.
params = {
'num_hid_layers': [0, 1, 2, 3, 4, 5],
'num_hid_units': [64, 128, 256, 512],
'max_epoch': [50, 100, 125, 150, 175, 200],
'batch_size': [128, 256, 512, 1024, 2048]
}
#lowest supported by python
best_accuracy = -sys.maxsize -1
best_params = None
for batch_size in params['batch_size']:
conf.batch_size = batch_size
for num_hid_units in params['num_hid_units']:
conf.num_hid_units = num_hid_units
for num_hid_layers in params['num_hid_layers']:
conf.num_hid_layers = num_hid_layers
max_epoch = max(params['max_epoch'])
sess = tf.Session(graph=tf.get_default_graph())
model = MNIST(sess, conf)
model.train(x_train_new, y_train_new, x_valid, y_valid, max_epoch, validation=False)
for epoch in params['max_epoch']:
accuracy = model.test(x_valid, y_valid, epoch)
print ("Accuracy with", num_hid_units, "hidden Units,", batch_size, "batch_size,",
num_hid_layers, "hidden Layers and", epoch, "epoch:", accuracy)
if accuracy > best_accuracy:
best_params = (batch_size, num_hid_units, num_hid_layers, epoch)
best_accuracy = accuracy
sess.close()
tf.reset_default_graph()
print ("Best Accuracy with", best_params[1], "hidden Units,", best_params[0], "batch_size,",
best_params[2], "hidden Layers and", best_params[3], "epoch:", best_accuracy)
# Second run: with hyperparameters determined in the first run, re-train
# your model on the original train set.
sess = tf.Session(graph=tf.get_default_graph())
conf.batch_size, conf.num_hid_units, conf.num_hid_layers, max_epoch = best_params
model = MNIST(sess, conf)
model.train(x_train, x_train, x_valid, y_valid, max_epoch, validation=False)
# Third run: after re-training, test your model on the test set.
# Report testing accuracy in your hard-copy report.
accuracy = model.test(x_test, y_test, max_epoch)
sess.close()
def main():
properties = None
if (len(sys.argv) > 1):
properties = Properties(sys.argv[1])
else:
properties = Properties("Local")
x_train, y_train, x_test, y_test = load_data(properties.data_dir,
properties.test_dir)
model = UNetClassifier(num_layers=3, num_filters=64,
num_classes=400).build_model()
def huber_loss(y_true, y_pred, clip_delta=1.0):
error = y_true - y_pred
cond = tf.keras.backend.abs(error) < clip_delta
squared_loss = 0.5 * tf.keras.backend.square(error)
linear_loss = clip_delta * (tf.keras.backend.abs(error) -
0.5 * clip_delta)
return tf.where(cond, squared_loss, linear_loss)
def crossentropy_loss(y_true, y_pred):
return K.categorical_crossentropy(y_true, y_pred)
y_train_new = formbins(y_train)
unique, counts = np.unique(y_train_new, return_counts=True)
weights = []
weights = 1 - counts / np.sum(counts)
weights /= np.sum(weights)
dictionary = dict(zip(unique, weights))
for i in range(10):
next(data_generator(properties.data_dir, 10, dictionary))
weightsVector = []
for i in range(100):
if i in dictionary:
weightsVector.append(dictionary[i])
else:
weightsVector.append(0)
loss = weighted_categorical_crossentropy(weightsVector)
model.compile(optimizer=optimizers.Adam(lr=0.01),
loss="categorical_crossentropy",
metrics=["accuracy"])
log_directory = properties.log_dir + str(time())
tensorboard = TensorBoard(log_dir=log_directory)
filepath = properties.model_dir + "weights-{epoch:02d}-{acc:.2f}.h5"
checkpoint = ModelCheckpoint(filepath,
monitor='acc',
verbose=1,
save_best_only=True,
mode='max')
model.fit_generator(data_generator(properties.data_dir, 2, dictionary),
steps_per_epoch=len(os.listdir(properties.data_dir)) //
2,
epochs=25,
callbacks=[tensorboard, checkpoint],
verbose=1)
bins = [
0, 8, 14, 20, 25, 106, 143, 139, 179, 159, 189, 199, 209, 219, 248,
265, 259, 283, 307, 323, 334, 341, 380, 384, 23
]
for i in range(0, len(x_test)):
y_pred = model.predict(x_test[i].reshape(1, 256, 256, 1))
if (i == 0):
for k in range(5):
for l in range(5):
fileName = properties.results_dir + str(k) + str(
l) + '.csv'
toprint = y_pred[0, k, l, :].reshape(400, )
np.savetxt(fileName, toprint, delimiter=',')
y_pred_bin = y_pred.reshape(256, 256, 400)
y_pred_bin = np.argmax(y_pred_bin, axis=2)
y_pred_alpha = 13 * (y_pred_bin // 20) + 6
y_pred_beta = 13 * (y_pred_bin % 20) + 6
y_pred = np.dstack((x_test[i], y_pred_alpha.reshape(256, 256, 1),
y_pred_beta.reshape(256, 256, 1)))
y_pred = y_pred.astype(np.uint8)
image = cv2.cvtColor(y_pred, cv2.COLOR_LAB2RGB)
outputfileName = properties.results_dir + str(i) + '.jpg'
cv2.imwrite(outputfileName, image)
eval_metric='mae',
nthread=2)
model.fit(X_train, y_train)
pred_val_y = model.predict(X_val)
print(np.mean(np.abs(pred_val_y - y_val)))
del X_train, y_train
gc.collect()
pred_test_y = model.predict(x_test)
del x_test
gc.collect()
print('=' * 60)
return pred_val_y, pred_test_y
if __name__ == '__main__':
train_X, train_y, test_X = load_data()
train_meta = np.zeros(train_y.shape[0])
test_meta = np.zeros(test_X.shape[0])
splits = list(
KFold(n_splits=5, shuffle=True,
random_state=233).split(train_X, train_y))
for idx, (train_idx, valid_idx) in enumerate(splits):
X_train = train_X[train_idx]
y_train = train_y[train_idx]
X_val = train_X[valid_idx]
y_val = train_y[valid_idx]
pred_val_y, pred_test_y = xgboost_train(X_train,
y_train,
X_val,
y_val,
test_X,
"embedding_size":8,
"deep_layers":[32,32],
"dropout_deep":[0.5,0.5,0.5],
"deep_layer_activation":tf.nn.relu,
"batch_norm":1,
"batch_norm_decay":0.995,
"verbose":True,
"random_seed":config.RANDOM_SEED,
"loss_type":"logloss",
"deep_init_size":50,
"use_inner":False
}
train_params = {
"loss_type":"logloss",
"learning_rate":0.01,
"epochs":30,
"optimizer_type":"sgd",
"batch_size":4
}
if __name__ == '__main__':
# load data
dfTrain, X_train, y_train, X_submission = load_data()
# folds
folds = list(StratifiedKFold(n_splits=config.NUM_SPLITS, shuffle=True,
random_state=config.RANDOM_SEED).split(X_train, y_train))
k_fold_cross_valid(dfTrain, X_submission, folds, pnn_params, train_params)
def main():
properties = None
if (len(sys.argv) > 1):
properties = Properties(sys.argv[1])
else:
properties = Properties("Local")
x_train, y_train, x_test, y_test = load_data(properties.data_dir, properties.test_dir)
model = UNetRegressor(64, 3).build_model()
#def quantile_metric(quantile, y_true, y_pred):
# e = y_true - y_pred
# metric = K.mean(K.maximum(quantile * e, (quantile - 1) * e), axis=-1)
# return metric
#def loss(y_true, y_pred):
# eA = y_true[:, :, :, 0] - y_pred[:, :, :, 0]
# eB = y_true[:, :, :, 1] - y_pred[:, :, :, 1]
# return K.mean(K.square(eA), axis=-1) + K.mean(K.square(eB), axis=-1)
def huber_loss(y_true, y_pred, clip_delta=1.0):
error = y_true - y_pred
cond = tf.keras.backend.abs(error) < clip_delta
squared_loss = 0.5 * tf.keras.backend.square(error)
linear_loss = clip_delta * (tf.keras.backend.abs(error) - 0.5 * clip_delta)
return tf.where(cond, squared_loss, linear_loss)
def crossentropy_loss(y_true, y_pred):
'''
bins = np.linspace(0, 260, 21)
y_true_new = []
for image_ab in y_true:
y_binned = np.digitize(image_ab, bins) - 1
y_binned = y_binned[:, :, 0] * 20 + y_binned[:, :, 1]
wt = np.zeros((256, 256, 2))
for i in range(y_binned.shape[0]):
for j in range(y_binned.shape[1]):
wt[i][j][0] = weights[y_binned[i][j] - 1]
wt[i][j][1] = weights[y_binned[i][j] - 1]
y_binned = (y_binned * wt).astype(int)
y_binned = np.digitize(y_binned, bins) - 1
y_binned = y_binned[:, :, 0] * 20 + y_binned[:, :, 1]
y_true_new.append(y_binned)
'''
cross_ent = K.categorical_crossentropy(y_pred, y_true)
#.switch(K.equal(y_true, -1), K.zeros_like(y_true), K.square(y_true-y_pred))
#K.categorical_crossentropy(y_pred, y_true)
#K.switch(K.equal(y_true, -1), K.zeros_like(y_true), K.square(y_true-y_pred))
#y_pred - y_true
#
#cross_ent = K.mean(cross_ent, axis=-1)
return cross_ent
'''
model.compile(optimizer=optimizers.Adam(lr=0.001),
loss=lambda y, f: huber_loss(y, f, clip_delta=0.5),
metrics=["accuracy"])
'''
model.compile(optimizer=optimizers.Adam(lr=0.001),
loss=lambda y, f: crossentropy_loss(y, f),
metrics=["accuracy"])
log_directory = properties.log_dir+str(time())
tensorboard = TensorBoard(log_dir=log_directory)
filepath = properties.model_dir+ "weights-{epoch:02d}-{acc:.2f}.h5"
checkpoint = ModelCheckpoint(filepath,
monitor='acc',
verbose=1,
mode='max')
#save_best_only=True,
#checkpoint = ModelCheckpoint(filepath,
# monitor='acc',
# verbose=1,
# mode='max')
y_train_new = formbins(y_train)
print(y_train.shape)
print(y_train_new.shape)
unique, counts = np.unique(y_train_new, return_counts=True)
#dictionary = dict(zip(unique, counts))
#print(len(dictionary))
weights = 1 - counts / np.sum(counts)
weights /= np.sum(weights)
dictionary = dict(zip(unique, weights))
print(dictionary)
'''
#print(y_train[:, :, :, 0])
#print(y_train[:, :, :, 0].shape)
weight = np.zeros((1000, 256, 256, 1))
bins = np.linspace(0, 260, 21)
y_train_new = []
for k, image_ab in enumerate(y_train):
#Create bins - each bin size is kept as 13 so there are roughly 20 bins from 0 to 255
#bins = ([ 0., 13., 26., 39., 52., 65., 78., 91., 104., 117., 130.,
#143., 156., 169., 182., 195., 208., 221., 234., 247., 260.])
y_train_bin = np.digitize(image_ab, bins)-1 #returns a value in 0 to 19
y_train_bin = y_train_bin[:,:,0]*20 + y_train_bin[:,:,1]
#print(image_ab.shape)
#print(y_train_bin.shape)
#exit(0)
for i in range(y_train_bin.shape[0]):
for j in range(y_train_bin.shape[1]):
weight[k][i][j] = dictionary[y_train_bin[i][j]]
#weight = dictionary(y_train_bin)
#print(y_train_bin)
#print(y_train_bin.shape)
#print(weight)
#exit(0)
#print(weight)
'''
#for key in dictionary:
#a = key//20
#b = key%20
#alpha = np.full((256, 256), 13*a + 7)
#beta = np.full((256, 256), 13*b + 7)
#L = np.full((256, 256), 50)
#print(13*a + 7, 13*b + 7)
#image_lab = np.dstack((L, alpha, beta))
#print(image_lab.shape)
#image_lab = image_lab.astype(np.uint8)
#image = cv2.cvtColor(image_lab, cv2.COLOR_Lab2RGB)
#outputfileName = properties.results_dir+str(key)+'.jpg'
#cv2.imwrite(outputfileName, image)
#fit/fit_generator giving OOM when batch_size is high
#model.fit(x_train, y_train,
# epochs=1,
# batch_size=16,
# callbacks=[tensorboard, checkpoint],
# verbose=1)
model.fit_generator(data_generator(properties.data_dir, 4, dictionary),
steps_per_epoch=len(os.listdir(properties.data_dir)) // 4,
epochs=10,
callbacks=[tensorboard, checkpoint],
verbose=1)
#Burn! Burn! Burn! How do I know the corresponding 3rd channel for each prediction?
#y_pred = model.predict_generator(data_generator(test_dir, 10),
# steps=len(os.listdir(test_dir)) // 10,
# verbose=1)
'''for i in range(0, len(x_test)):
y_pred = model.predict(x_test[i].reshape(1, 256, 256, 1))
y_pred = np.dstack((x_test[i], y_pred.reshape(256, 256, 2)))
y_pred = y_pred.astype(np.uint8)
image = cv2.cvtColor(y_pred, cv2.COLOR_LAB2RGB)
outputfileName = properties.results_dir+str(i)+'.jpg'
cv2.imwrite(outputfileName, image)'''
check_output=[]
for i in range(0, len(x_test)):
y_pred = model.predict(x_test[i].reshape(1, 256, 256, 1))
#print("y_pred", y_pred)
y_pred = y_pred.reshape(256,256,100)
check_output=y_pred
#print("y_pred shape", y_pred.shape)
y_pred_bin = np.argmax(y_pred, axis=2)
#print("y_pred bin", y_pred_bin)
y_pred_alpha = 25.6*(y_pred_bin//5)+12.8
#print("y_pred alpha", y_pred_alpha)
y_pred_beta = 25.6*(y_pred_bin % 5)+12.8
#print("y_pred beta", y_pred_beta)
y_pred = np.dstack((x_test[i], y_pred_alpha.reshape(256, 256, 1), y_pred_beta.reshape(256,256,1)))
y_pred = y_pred.astype(np.uint8)
image = cv2.cvtColor(y_pred, cv2.COLOR_LAB2RGB)
outputfileName = properties.results_dir + str(i) + '.jpg'
#trueoutputfileName = properties.trueresults_dir + str(i) + '.jpg'
cv2.imwrite(outputfileName, image)
print("###############printing ypred################")
print(check_output)
np.savetxt('/content/drive/My Drive/UNet-Colorization/data/data/test/ypred0.csv', np.reshape(check_output[0,0,:],100), delimiter=',')
np.savetxt('/content/drive/My Drive/UNet-Colorization/data/data/test/ypred1.csv', np.reshape(check_output[0,1,:],100), delimiter=',')
np.savetxt('/content/drive/My Drive/UNet-Colorization/data/data/test/ypred100.csv', np.reshape(check_output[100,100,:],100), delimiter=',')
np.savetxt('/content/drive/My Drive/UNet-Colorization/data/data/test/ypred255.csv', np.reshape(check_output[255,255,:],100), delimiter=',')
