def runing(config, budget):
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
tf.reset_default_graph()
network = config["network"]
print("sid {sid}, network: {network}".format(sid=sid, network=network))
# hyperparameters
learning_rate = config["lr"]
batch_size = 256
n_training_epochs = int(budget)
# load data
mnist = input_data.read_data_sets('data/mnist', one_hot=True)
# Input (X) and Target (Y) placeholders, they will be fed with a batch of
# input and target values respectively, from the training and test sets
X = qfns.input_placeholder()
Y = qfns.target_placeholder()
# Create the tensorflow computational graph for our model
if network == "onelayer":
w, b, logits_op, preds_op, xentropy_op, loss_op = qfns.onelayer(X, Y)
# [variable_summaries(v, name) for (v, name) in zip((w, b), ("w", "b"))]
# tf.summary.histogram('pre_activations', logits_op)
elif network == "twolayers":
w1, b1, w2, b2, logits_op, preds_op, xentropy_op, loss_op = \
qfns.twolayer(X, Y, hiddensize=30, outputsize=10)
# [variable_summaries(v, name) for (v, name) in
# zip((w1, b1, w2, b2), ("w1", "b1", "w2", "b2"))]
# tf.summary.histogram('pre_activations', logits_op)
elif network == "conv":
# standard conv layers
conv1out, conv2out, w, b, logits_op, preds_op, xentropy_op, loss_op = \
qfns.convnet(tf.reshape(X, [-1, 28, 28, 1]), Y, convlayer_sizes=[10, 10],
filter_shape=[3, 3], outputsize=10, padding="same")
# [variable_summaries(v, name) for (v, name) in ((w, "w"), (b, "b"))]
# tf.summary.histogram('pre_activations', logits_op)
else:
raise ValueError("Incorrect network string in line 7")
# The training op performs a step of stochastic gradient descent on a minibatch
optimizer = tf.train.AdamOptimizer # ADAM - widely used optimiser (ref: http://arxiv.org/abs/1412.6980)
train_op = optimizer(learning_rate).minimize(loss_op)
# Prediction and accuracy ops
accuracy_op = get_accuracy_op(preds_op, Y)
# TensorBoard for visualisation
# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
summaries_op = tf.summary.merge_all()
# Separate accuracy summary so we can use train and test sets
accuracy_placeholder = tf.placeholder(shape=[], dtype=tf.float32)
# accuracy_summary_op = tf.summary.scalar("accuracy", accuracy_placeholder)
# When run, the init_op initialises any TensorFlow variables
# hint: weights and biases in our case
init_op = tf.global_variables_initializer()
# Get started
with tf.Session() as sess:
sess.run(init_op)
# Initialise TensorBoard Summary writers
# dtstr = "{:%b_%d_%H-%M-%S}".format(datetime.now())
# train_writer = tf.summary.FileWriter('./summaries/' + dtstr + '/train', sess.graph)
# test_writer = tf.summary.FileWriter('./summaries/' + dtstr + '/test')
# Train
print('Starting Training...')
train_accuracy, test_accuracy = train(sess, mnist, n_training_epochs,
batch_size, X, Y, train_op,
loss_op, accuracy_op,
accuracy_placeholder)
print('Training Complete\n')
print(
"train_accuracy: {train_accuracy}, test_accuracy: {test_accuracy}".
format(**locals()))
with open("results.csv", "a") as f:
f.write("{0},{1},{2},{3}\n".format(sid, network, train_accuracy,
train_accuracy))
return train_accuracy, test_accuracy
# hyperparameters
learning_rate = 0.001
batch_size = 128
n_training_epochs = 20
# load data
mnist = input_data.read_data_sets('data/mnist', one_hot=True)
# Input (X) and Target (Y) placeholders, they will be fed with a batch of
# input and target values resepectively, from the training and test sets
X = qfns.input_placeholder()
Y = qfns.target_placeholder()
# Create the tensorflow computational graph for our model
if network == "onelayer":
w, b, logits_op, preds_op, xentropy_op, loss_op = qfns.onelayer(X, Y)
[variable_summaries(v, name) for (v, name) in zip((w, b), ("w", "b"))]
tf.summary.histogram('pre_activations', logits_op)
elif network == "twolayer":
w1, b1, w2, b2, logits_op, preds_op, xentropy_op, loss_op = \
qfns.twolayer(X, Y)
[
variable_summaries(v, name)
for (v, name) in zip((w1, b1, w2, b2), ("w1", "b1", "w2", "b2"))
]
tf.summary.histogram('pre_activations', logits_op)
elif network == "conv":
# standard conv layers
conv1out, conv2out, w, b, logits_op, preds_op, xentropy_op, loss_op = \
qfns.convnet(tf.reshape(X, [-1, 28, 28, 1]), Y)
[variable_summaries(v, name) for (v, name) in ((w, "w"), (b, "b"))]
# hyperparameters
learning_rate = 0.001
batch_size = 128
n_training_epochs = 20
# load data
mnist = input_data.read_data_sets('data/mnist', one_hot=True)
# Input (X) and Target (Y) placeholders, they will be fed with a batch of
# input and target values resepectively, from the training and test sets
X = qfns.input_placeholder()
Y = qfns.target_placeholder()
# Create the tensorflow computational graph for our model
if network == "onelayer":
w, b, logits_op, preds_op, xentropy_op, loss_op = qfns.onelayer(X, Y)
[variable_summaries(v, name) for (v, name) in zip((w, b), ("w", "b"))]
tf.summary.histogram('pre_activations', logits_op)
elif network == "twolayer":
w1, b1, w2, b2, logits_op, preds_op, xentropy_op, loss_op = \
qfns.twolayer(X, Y)
[variable_summaries(v, name) for (v, name) in
zip((w1, b1, w2, b2), ("w1", "b1", "w2", "b2"))]
tf.summary.histogram('pre_activations', logits_op)
elif network == "conv":
# standard conv layers
conv1out, conv2out, w, b, logits_op, preds_op, xentropy_op, loss_op = \
qfns.convnet(tf.reshape(X, [-1, 28, 28, 1]), Y)
[variable_summaries(v, name) for (v, name) in ((w,"w"), (b,"b"))]
tf.summary.histogram('pre_activations', logits_op)
#elif network == "rollyourown":