def my_training_task4(X_train,
y_train,
X_val,
y_val,
conv_featmap=[6],
fc_units=[84],
conv_kernel_size=[5],
pooling_size=[2],
l2_norm=0.01,
seed=235,
learning_rate=1e-3,
epoch=20,
batch_size=245,
verbose=False,
pre_trained_model=None):
print("Building my LeNet. Parameters: ")
print("conv_featmap={}".format(conv_featmap))
print("fc_units={}".format(fc_units))
print("conv_kernel_size={}".format(conv_kernel_size))
print("pooling_size={}".format(pooling_size))
print("l2_norm={}".format(l2_norm))
print("seed={}".format(seed))
print("learning_rate={}".format(learning_rate))
Train_aug = ImageGenerator(x=X_train, y=y_train)
Train_aug_f = Train_aug.flip(mode='hv')
Train_aug_r = Train_aug.rotate(angle=90)
X_train_aug = np.vstack((X_train, Train_aug_f[0]))
y_train_aug = np.hstack((y_train, Train_aug_f[1]))
X_train_aug = np.vstack((X_train_aug, Train_aug_r[0]))
y_train_aug = np.hstack((y_train_aug, Train_aug_r[1]))
X_train = X_train_aug
y_train = y_train_aug
# define the variables and parameter needed during training
with tf.name_scope('inputs'):
xs = tf.placeholder(shape=[None, 32, 32, 3], dtype=tf.float32)
ys = tf.placeholder(shape=[
None,
], dtype=tf.int64)
is_training = tf.placeholder(tf.bool, name='is_training')
output, loss = my_LeNet(xs,
ys,
is_training,
img_len=32,
channel_num=3,
output_size=10,
conv_featmap=conv_featmap,
fc_units=fc_units,
conv_kernel_size=conv_kernel_size,
pooling_size=pooling_size,
l2_norm=l2_norm,
keep_prob=0.7,
seed=seed)
iters = int(X_train.shape[0] / batch_size)
print('number of batches for training: {}'.format(iters))
step = train_step(loss)
eve = evaluate(output, ys)
iter_total = 0
best_acc = 0
cur_model_name = 'lenet_{}'.format(int(time.time()))
with tf.Session() as sess:
merge = tf.summary.merge_all()
writer = tf.summary.FileWriter("log/{}".format(cur_model_name),
sess.graph)
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
# try to restore the pre_trained
if pre_trained_model is not None:
try:
print("Load the model from: {}".format(pre_trained_model))
saver.restore(sess, 'model/{}'.format(pre_trained_model))
except Exception:
raise ValueError("Load model Failed!")
for epc in range(epoch):
print("epoch {} ".format(epc + 1))
for itr in range(iters):
iter_total += 1
training_batch_x = X_train[itr * batch_size:(1 + itr) *
batch_size]
training_batch_y = y_train[itr * batch_size:(1 + itr) *
batch_size]
_, cur_loss = sess.run([step, loss],
feed_dict={
xs: training_batch_x,
ys: training_batch_y,
is_training: True
})
if iter_total % 100 == 0:
# do validation
valid_eve, merge_result = sess.run([eve, merge],
feed_dict={
xs: X_val,
ys: y_val,
is_training: False
})
valid_acc = 100 - valid_eve * 100 / y_val.shape[0]
if verbose:
print(
'{}/{} loss: {} validation accuracy : {}%'.format(
batch_size * (itr + 1), X_train.shape[0],
cur_loss, valid_acc))
# save the merge result summary
writer.add_summary(merge_result, iter_total)
# when achieve the best validation accuracy, we store the model paramters
if valid_acc > best_acc:
print(
'Best validation accuracy! iteration:{} accuracy: {}%'
.format(iter_total, valid_acc))
best_acc = valid_acc
saver.save(sess, 'model/{}'.format(cur_model_name))
print(
"Traning ends. The best valid accuracy is {}. Model named {}.".format(
best_acc, cur_model_name))
def my_training_task4(X_train,
y_train,
X_val,
y_val,
conv_featmap=[6],
fc_units=[84],
conv_kernel_size=[5],
dropout_rate=[0.1],
pooling_size=[2],
l2_norm=0.01,
seed=235,
learning_rate=1e-2,
epoch=20,
batch_size=245,
verbose=False,
pre_trained_model=None):
# TODO: Copy my_training function, make modifications so that it uses your
# data generator from task 4 to train.
#raise NotImplementedError
print("Building my LeNet. Parameters: ")
print("conv_featmap={}".format(conv_featmap))
print("fc_units={}".format(fc_units))
print("conv_kernel_size={}".format(conv_kernel_size))
print("pooling_size={}".format(pooling_size))
print("l2_norm={}".format(l2_norm))
print("seed={}".format(seed))
print("learning_rate={}".format(learning_rate))
imageGe = ImageGenerator(X_train, y_train)
# define the variables and parameter needed during training
with tf.name_scope('inputs'):
xs = tf.placeholder(shape=[None, 32, 32, 3], dtype=tf.float32)
ys = tf.placeholder(shape=[
None,
], dtype=tf.int64)
output, loss = my_LeNet(xs,
ys,
img_len=32,
channel_num=3,
output_size=10,
conv_featmap=conv_featmap,
fc_units=fc_units,
conv_kernel_size=conv_kernel_size,
dropout_rate=dropout_rate,
pooling_size=pooling_size,
l2_norm=l2_norm,
seed=seed)
iters = int(X_train.shape[0] / batch_size)
print('number of batches for training: {}'.format(iters))
step = train_step(loss)
eve = evaluate(output, ys)
iter_total = 0
best_acc = 0
cur_model_name = 'lenet_{}'.format(int(time.time()))
with tf.Session() as sess:
merge = tf.summary.merge_all()
writer = tf.summary.FileWriter("log/{}".format(cur_model_name),
sess.graph)
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
# try to restore the pre_trained
if pre_trained_model is not None:
try:
print("Load the model from: {}".format(pre_trained_model))
saver.restore(sess, 'model/{}'.format(pre_trained_model))
except Exception:
print("Load model Failed!")
pass
for epc in range(epoch):
print("epoch {} ".format(epc + 1))
for itr in range(iters):
iter_total += 1
#training_batch_x = X_train[itr * batch_size: (1 + itr) * batch_size]
#training_batch_y = y_train[itr * batch_size: (1 + itr) * batch_size]
training_batch_x, training_batch_y = next(
imageGe.next_batch_gen(batch_size, shuffle=False))
_, cur_loss = sess.run([step, loss],
feed_dict={
xs: training_batch_x,
ys: training_batch_y
})
if iter_total % 100 == 0:
# do validation
valid_eve, merge_result = sess.run([eve, merge],
feed_dict={
xs: X_val,
ys: y_val
})
valid_acc = 100 - valid_eve * 100 / y_val.shape[0]
if verbose:
print(
'{}/{} loss: {} validation accuracy : {}%'.format(
batch_size * (itr + 1), X_train.shape[0],
cur_loss, valid_acc))
# save the merge result summary
writer.add_summary(merge_result, iter_total)
# when achieve the best validation accuracy, we store the model paramters
if valid_acc > best_acc:
print(
'Best validation accuracy! iteration:{} accuracy: {}%'
.format(iter_total, valid_acc))
best_acc = valid_acc
saver.save(sess, 'model/{}'.format(cur_model_name))
if (epc % 4 == 1):
imageGe.translate(4, 4)
elif (epc % 4 == 2):
imageGe.rotate(90)
elif (epc % 4 == 3):
imageGe.flip('hv')
elif (epc % 4 == 0):
imageGe = ImageGenerator(X_train, y_train)
print(
"Traning ends. The best valid accuracy is {}. Model named {}.".format(
best_acc, cur_model_name))