def learn(train_states,
test_states,
model,
learning_rate=.0001,
save_every=10,
batch_size=2048,
hidden_size=2048,
dropout=.5,
epochs=500,
print_every=1,
model_dir='.',
perceptron=False,
mem_ratio=.95):
data = read_data(train_states, test_states)
model_name = (
'''trust_classifier_epochs_{}_batch_{}_learning_rate_{}'''.format(
epochs, batch_size, learning_rate))
if perceptron:
model_name = '{}_perceptron.pb'.format(model_name)
else:
model_name = '{}_dropout_{}_hidden_size_{}.pb'.format(
model_name, dropout, hidden_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=mem_ratio)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
load_graph(model)
transfer_predictor = sess.graph.get_tensor_by_name('output:0')
# Evaluate the model on the training and test data, for training and testing.
data.train._X = np.vstack([
sess.run(transfer_predictor, {'input:0': chunk})
for chunk in chunks(data.train.X, 10)
])
answer = tf.equal(tf.argmax(data.train.X, 1),
tf.argmax(data.train.Y, 1))
data.train._Y = tf.one_hot(tf.to_int32(answer), depth=2).eval()
data.test._X = sess.run(transfer_predictor, {'input:0': data.test.X})
answer = tf.equal(tf.argmax(data.test.X, 1), tf.argmax(data.test.Y, 1))
data.test._Y = tf.one_hot(tf.to_int32(answer), depth=2).eval()
x = tf.placeholder('float',
shape=[None, data.train.X_features],
name='input_b')
y_ = tf.placeholder('float',
shape=[None, data.train.Y_features],
name='target')
if perceptron:
W = weight_variable([data.train.X_features, data.train.Y_features],
name='weights')
b = bias_variable([data.train.Y_features], name='bias')
logits = tf.matmul(x, W) + b
else:
W_in = weight_variable([data.train.X_features, hidden_size],
name='weights_in')
b_in = bias_variable([hidden_size], name='bias_in')
hidden = tf.matmul(x, W_in) + b_in
relu = tf.nn.relu(hidden)
keep_prob = tf.placeholder_with_default([1.], shape=None)
hidden_dropout = tf.nn.dropout(relu, keep_prob)
W_out = weight_variable([hidden_size, data.train.Y_features],
name='weights_out')
b_out = bias_variable([data.train.Y_features], name='bias_out')
logits = tf.matmul(relu, W_out) + b_out
# Loss & train
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, y_)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(
cross_entropy)
# Evaluation
y = tf.nn.softmax(logits, name='output_b')
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
sess.run(tf.initialize_all_variables())
last_epoch = 0
t_epoch = time.time()
while data.train.epoch <= epochs:
epoch = data.train.epoch
batch_x, batch_y = data.train.next_batch(batch_size)
t_start = time.time()
feed_dict = {
x: batch_x,
y_: batch_y
} if perceptron else {
x: batch_x,
y_: batch_y,
keep_prob: dropout
}
train_step.run(feed_dict=feed_dict)
t_end = time.time() - t_start
if epoch > last_epoch:
if epoch % print_every == 0:
train_accuracy_mean = accuracy.eval(feed_dict={
x: batch_x,
y_: batch_y
})
validation_accuracy_mean = accuracy.eval(feed_dict={
x: data.test.X,
y_: data.test.Y
})
print(
'''Epoch {} train accuracy: {}, test accuracy: {}. '''
'''{} states/sec, {} secs/epoch.'''.format(
epoch, train_accuracy_mean,
validation_accuracy_mean, batch_size / t_end,
time.time() - t_epoch))
if epoch % save_every == 0 or epoch == epochs:
output_graph_def = graph_util.convert_variables_to_constants(
sess, sess.graph.as_graph_def(),
['input_b', 'output_b'])
with gfile.FastGFile(os.path.join(model_dir, model_name),
'w') as f:
f.write(output_graph_def.SerializeToString())
t_epoch = time.time()
last_epoch = epoch
print('Trained model saved to {}'.format(
os.path.join(model_dir, model_name)))
def learn(train_states, test_states, learning_rate, save_every, batch_size, hidden_size, dropout, epochs,
print_every, model_dir, perceptron, dense, lenet, filter_width, depth, mem_ratio,
q_size, use_dask, in_memory, dask_chunksize):
data = read_data(train_states, test_states, use_dask, in_memory, dask_chunksize)
model_name = ('''transfer_classifier_epochs_{}_batch_{}_learning_rate_{}'''.format(
epochs, batch_size, learning_rate))
if perceptron:
model_name = '{}_perceptron.pb'.format(model_name)
if dense:
model_name = '{}_dense_dropout_{}_hidden_size_{}.pb'.format(model_name, dropout, hidden_size)
if lenet:
model_name = '{}_lenet_dropout_{}_hidden_size_{}.pb'.format(model_name, dropout, hidden_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=mem_ratio)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
q_x_in = tf.placeholder(tf.float32, shape=[batch_size, data.train.X_features])
q_y_in = tf.placeholder(tf.int32, shape=[batch_size])
y_real = tf.placeholder(tf.int32, shape=[None])
keep_prob = tf.placeholder_with_default([1.], shape=None)
q = tf.FIFOQueue(q_size, [tf.float32, tf.int32],
shapes=[ q_x_in.get_shape(), q_y_in.get_shape()])
enqueue_op = q.enqueue([q_x_in, q_y_in])
q_x_out, q_y_out = q.dequeue()
x = tf.placeholder_with_default(q_x_out, shape=[None, data.train.X_features], name='input')
y_ = tf.placeholder_with_default(q_y_out, shape=[None])
if perceptron:
W = weight_variable([data.train.X_features, data.train.Y_features])
b = bias_variable([data.train.Y_features])
logits = tf.matmul(x, W) + b
if dense:
W_in = weight_variable([data.train.X_features, hidden_size])
b_in = bias_variable([hidden_size])
hidden = tf.matmul(x, W_in) + b_in
relu = tf.nn.relu(hidden)
hidden_dropout = tf.nn.dropout(relu, keep_prob)
W_out = weight_variable([hidden_size,data.train.Y_features])
b_out = bias_variable([data.train.Y_features])
logits = tf.matmul(hidden_dropout, W_out) + b_out
if lenet:
w1 = weight_variable([1, filter_width, 1, depth])
b1 = bias_variable([depth])
x_4d = tf.expand_dims(tf.expand_dims(x,1),-1) # Singleton dimension height, out_channel
conv = tf.nn.conv2d(x_4d, w1, strides=[1,1,1,1], padding='SAME')
relu = tf.nn.relu(tf.nn.bias_add(conv, b1))
pool = tf.nn.max_pool(relu, ksize=[1, 1, 2, 1], strides=[1, 1, 2, 1], padding='SAME')
w2 = weight_variable([1, filter_width, depth, depth*2])
b2 = bias_variable([depth*2])
conv = tf.nn.conv2d(pool, w2, strides=[1,1,1,1], padding='SAME')
relu = tf.nn.relu(tf.nn.bias_add(conv, b2))
pool = tf.nn.max_pool(relu, ksize=[1, 1, 2, 1], strides=[1, 1, 2, 1], padding='SAME')
pool_shape = tf.shape(pool)
reshape = tf.reshape(pool,
[pool_shape[0], pool_shape[1] * pool_shape[2] * pool_shape[3] ])
w3 = weight_variable([ (data.train.X_features/4)*2*depth, hidden_size])
b3 = bias_variable([hidden_size])
hidden = tf.matmul(reshape, w3) + b3
relu = tf.nn.relu(hidden)
hidden_dropout = tf.nn.dropout(relu, keep_prob)
w4 = weight_variable([hidden_size, data.train.Y_features])
b4 = bias_variable([data.train.Y_features])
logits = tf.matmul(hidden_dropout, w4) + b4
# Loss & train
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits, y_)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
# Evaluation
y = tf.nn.softmax(logits)
train_correct_prediction = tf.equal(tf.to_int32(tf.argmax(y, 1)), y_,)
train_accuracy = tf.reduce_mean(tf.cast(train_correct_prediction, tf.float32))
# Applying convolutional filter to put subcategories into original categories for testing
stride = [1,1,1,1]
_filter = tf.constant(data.output_filter, dtype=tf.float32, shape=data.output_filter.shape)
conv_in = tf.expand_dims(y, 0)
conv_in = tf.expand_dims(conv_in,-1)
conv_out = tf.nn.conv2d(conv_in, _filter, stride, 'VALID') # We don't want zero padding.
back = tf.squeeze(conv_out, squeeze_dims=[0,2], name='output')
test_correct_prediction = tf.equal(tf.to_int32(tf.argmax(back, 1)), y_real)
test_accuracy = tf.reduce_mean(tf.cast(test_correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
def load_data():
try:
while True:
next_x, next_y = data.train.next_batch(batch_size)
if next_x.shape[0] == batch_size:
sess.run(enqueue_op, feed_dict={q_x_in: next_x, q_y_in: next_y})
except Exception as error:
print(error)
print('Stopped streaming of data.')
data_thread = threading.Thread(target=load_data)
data_thread.daemon = True
data_thread.start()
last_epoch = 0
epoch = 0
t_epoch = time.time()
t_end = []
i = 0
while epoch <= epochs:
t_start = time.time()
sess.run(train_step, feed_dict={keep_prob: dropout})
t_end.append(time.time() - t_start)
if epoch > last_epoch:
if epoch % print_every == 0:
batch_x, batch_y = data.train.next_batch(batch_size)
train_accuracy_mean = train_accuracy.eval(feed_dict={
x: batch_x,
y_: batch_y })
validation_accuracy_mean = np.mean([ test_accuracy.eval(feed_dict={x: t_x, y_real: t_y })
for t_x, t_y in zip(chunks(data.test.X, batch_size),
chunks(data.test.Y, batch_size)) ])
print('''Epoch {} train accuracy: {}, test accuracy: {}. '''
'''{} states/sec on average, {} secs/epoch.'''.format(epoch, pf(train_accuracy_mean),
pf(validation_accuracy_mean),
pf(batch_size/np.mean(t_end)),
pf(time.time() - t_epoch)))
if epoch % save_every == 0 or epoch == epochs:
output_graph_def = graph_util.convert_variables_to_constants(
sess, sess.graph.as_graph_def(), ['input', 'output'])
with gfile.FastGFile(os.path.join(model_dir, model_name), 'w') as f:
f.write(output_graph_def.SerializeToString())
t_epoch = time.time()
t_end = []
last_epoch = epoch
i += 1
if batch_size*i > data.train.X_len:
epoch += 1
i = 0
q.close(cancel_pending_enqueues=True)
print('Trained model saved to {}'.format(os.path.join(model_dir, model_name)))
'--in_memory',
help='How many vectors to hold in memory when using dask.',
type=int,
default=200000)
parser.add_argument('--gpu_memory_ratio',
help='How much memory to occupy on the GPU card',
type=float,
default=.95)
parser.add_argument('--dask_chunksize',
help='The size of dask chunks on disk.',
type=int,
default=8 * 1024)
args = parser.parse_args()
data = read_data(args.train_states, args.test_states, args.use_dask,
args.in_memory, args.dask_chunksize)
model_name = (
'''transfer_classifier_epochs_{}_batch_{}_learning_rate_{}_'''.format(
args.epochs, args.batch_size, args.learning_rate))
if args.network == 'perceptron':
model_name = '{}_perceptron.pb'.format(model_name)
if args.network == 'dense':
model_name = '{}_dense_dropout_{}_hidden_size_{}.pb'.format(
model_name, args.dropout, args.hidden_size)
if args.network == 'lenet':
model_name = '{}_lenet_dropout_{}_hidden_size_{}.pb'.format(
model_name, args.dropout, args.hidden_size)
learn(data, model_name, args.learning_rate, args.save_every,
def learn(data_folder,
experts,
learning_rate=.001,
train_ratio=.8,
validation_ratio=.1,
test_ratio=.1,
save_every=10,
batch_size=2048,
hidden_size=1024,
dropout=.5,
epochs=500,
print_every=1,
model_dir='.',
perceptron=False,
mem_ratio=.95):
assert train_ratio + validation_ratio + test_ratio == 1, 'Train/validation/test ratios must sum up to 1'
data = read_data(data_folder, train_ratio, validation_ratio, test_ratio)
model_name = (
'''transfer_classifier_moe_epochs_{}_batch_{}_ratios_{}_{}_{}_'''
'''learning_rate_{}'''.format(epochs, batch_size, train_ratio,
validation_ratio, test_ratio,
learning_rate))
if perceptron:
model_name = '{}_perceptron.pb'.format(model_name)
else:
model_name = '{}_dropout_{}_hidden_size_{}.pb'.format(
model_name, dropout, hidden_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=mem_ratio)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
local_experts = {}
for model in os.listdir(experts):
print('Loading {}'.format(model))
load_graph(os.path.join(args.experts, model))
stripped = model[20:]
h5 = stripped[:stripped.find('_')] # MESSY.
local_experts[h5] = sess.graph.get_tensor_by_name(
'{}output:0'.format(h5))
data.train._X = np.hstack([
data.train.X,
np.vstack([
flow(sess, local_experts, x)
for x in chunks(data.train.X, batch_size)
])
])
data.validation._X = np.hstack(
[data.validation.X,
flow(sess, local_experts, data.validation.X)])
data.test._X = np.hstack(
[data.test.X, flow(sess, local_experts, data.test.X)])
x = tf.placeholder('float',
shape=[None, data.train.X_features],
name='input')
y_ = tf.placeholder('float',
shape=[None, data.train.Y_features],
name='target')
if perceptron:
W = weight_variable([data.train.X_features, data.train.Y_features],
name='weights')
b = bias_variable([data.train.Y_features], name='bias')
logits = tf.matmul(x, W) + b
else:
W_in = weight_variable([data.train.X_features, hidden_size],
name='weights_in')
b_in = bias_variable([hidden_size], name='bias_in')
hidden = tf.matmul(x, W_in) + b_in
relu = tf.nn.relu(hidden)
keep_prob = tf.placeholder_with_default([1.], shape=None)
hidden_dropout = tf.nn.dropout(relu, keep_prob)
W_out = weight_variable([hidden_size, data.train.Y_features],
name='weights_out')
b_out = bias_variable([data.train.Y_features], name='bias_out')
logits = tf.matmul(relu, W_out) + b_out
y = tf.nn.softmax(logits, name='output')
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, y_)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(
cross_entropy)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
sess.run(tf.initialize_all_variables())
last_epoch = 0
t_epoch = time.time()
while data.train.epoch <= epochs:
epoch = data.train.epoch
batch_x, batch_y = data.train.next_batch(batch_size)
t_start = time.time()
feed_dict = {
x: batch_x,
y_: batch_y
} if perceptron else {
x: batch_x,
y_: batch_y,
keep_prob: dropout
}
train_step.run(feed_dict=feed_dict)
t_end = time.time() - t_start
if epoch > last_epoch:
if epoch % print_every == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch_x,
y_: batch_y
})
validation_accuracy = accuracy.eval(feed_dict={
x: data.validation.X,
y_: data.validation.Y
})
print(
'''Epoch {} train accuracy: {}, validation accuracy: {}. '''
'''{} states/sec, {} secs/epoch.'''.format(
epoch, train_accuracy, validation_accuracy,
batch_size / t_end,
time.time() - t_epoch))
if epoch % save_every == 0 or epoch == epochs:
output_graph_def = graph_util.convert_variables_to_constants(
sess, sess.graph.as_graph_def(), ['input', 'output'])
with gfile.FastGFile(os.path.join(model_dir, model_name),
'w') as f:
f.write(output_graph_def.SerializeToString())
t_epoch = time.time()
last_epoch = epoch
print('Trained model saved to {}'.format(
os.path.join(model_dir, model_name)))
if test_ratio > 0:
test_accuracy = accuracy.eval(feed_dict={
x: data.test.X,
y_: data.test.Y
})
print('Evaluation on testing data: {}'.format(test_accuracy))
def learn(
train_states,
test_states,
model,
learning_rate=0.0001,
save_every=10,
batch_size=2048,
hidden_size=2048,
dropout=0.5,
epochs=500,
print_every=1,
model_dir=".",
perceptron=False,
mem_ratio=0.95,
):
data = read_data(train_states, test_states)
model_name = """trust_classifier_epochs_{}_batch_{}_learning_rate_{}""".format(epochs, batch_size, learning_rate)
if perceptron:
model_name = "{}_perceptron.pb".format(model_name)
else:
model_name = "{}_dropout_{}_hidden_size_{}.pb".format(model_name, dropout, hidden_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=mem_ratio)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
load_graph(model)
transfer_predictor = sess.graph.get_tensor_by_name("output:0")
# Evaluate the model on the training and test data, for training and testing.
data.train._X = np.vstack(
[sess.run(transfer_predictor, {"input:0": chunk}) for chunk in chunks(data.train.X, 10)]
)
answer = tf.equal(tf.argmax(data.train.X, 1), tf.argmax(data.train.Y, 1))
data.train._Y = tf.one_hot(tf.to_int32(answer), depth=2).eval()
data.test._X = sess.run(transfer_predictor, {"input:0": data.test.X})
answer = tf.equal(tf.argmax(data.test.X, 1), tf.argmax(data.test.Y, 1))
data.test._Y = tf.one_hot(tf.to_int32(answer), depth=2).eval()
x = tf.placeholder("float", shape=[None, data.train.X_features], name="input_b")
y_ = tf.placeholder("float", shape=[None, data.train.Y_features], name="target")
if perceptron:
W = weight_variable([data.train.X_features, data.train.Y_features], name="weights")
b = bias_variable([data.train.Y_features], name="bias")
logits = tf.matmul(x, W) + b
else:
W_in = weight_variable([data.train.X_features, hidden_size], name="weights_in")
b_in = bias_variable([hidden_size], name="bias_in")
hidden = tf.matmul(x, W_in) + b_in
relu = tf.nn.relu(hidden)
keep_prob = tf.placeholder_with_default([1.0], shape=None)
hidden_dropout = tf.nn.dropout(relu, keep_prob)
W_out = weight_variable([hidden_size, data.train.Y_features], name="weights_out")
b_out = bias_variable([data.train.Y_features], name="bias_out")
logits = tf.matmul(relu, W_out) + b_out
# Loss & train
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, y_)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
# Evaluation
y = tf.nn.softmax(logits, name="output_b")
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
last_epoch = 0
t_epoch = time.time()
while data.train.epoch <= epochs:
epoch = data.train.epoch
batch_x, batch_y = data.train.next_batch(batch_size)
t_start = time.time()
feed_dict = {x: batch_x, y_: batch_y} if perceptron else {x: batch_x, y_: batch_y, keep_prob: dropout}
train_step.run(feed_dict=feed_dict)
t_end = time.time() - t_start
if epoch > last_epoch:
if epoch % print_every == 0:
train_accuracy_mean = accuracy.eval(feed_dict={x: batch_x, y_: batch_y})
validation_accuracy_mean = accuracy.eval(feed_dict={x: data.test.X, y_: data.test.Y})
print(
"""Epoch {} train accuracy: {}, test accuracy: {}. """
"""{} states/sec, {} secs/epoch.""".format(
epoch,
train_accuracy_mean,
validation_accuracy_mean,
batch_size / t_end,
time.time() - t_epoch,
)
)
if epoch % save_every == 0 or epoch == epochs:
output_graph_def = graph_util.convert_variables_to_constants(
sess, sess.graph.as_graph_def(), ["input_b", "output_b"]
)
with gfile.FastGFile(os.path.join(model_dir, model_name), "w") as f:
f.write(output_graph_def.SerializeToString())
t_epoch = time.time()
last_epoch = epoch
print("Trained model saved to {}".format(os.path.join(model_dir, model_name)))
def learn(data_folder, experts, learning_rate=.001, train_ratio=.8, validation_ratio=.1, test_ratio=.1, save_every=10, batch_size=2048, hidden_size=1024, dropout=.5, epochs=500, print_every=1, model_dir='.', perceptron=False, mem_ratio=.95):
assert train_ratio + validation_ratio + test_ratio == 1, 'Train/validation/test ratios must sum up to 1'
data = read_data(data_folder, train_ratio, validation_ratio, test_ratio)
model_name = ('''transfer_classifier_moe_epochs_{}_batch_{}_ratios_{}_{}_{}_'''
'''learning_rate_{}'''.format(
epochs, batch_size,
train_ratio, validation_ratio,
test_ratio, learning_rate))
if perceptron:
model_name = '{}_perceptron.pb'.format(model_name)
else:
model_name = '{}_dropout_{}_hidden_size_{}.pb'.format(model_name, dropout, hidden_size)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=mem_ratio)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
local_experts = {}
for model in os.listdir(experts):
print('Loading {}'.format(model))
load_graph(os.path.join(args.experts, model))
stripped = model[20:]
h5 = stripped[:stripped.find('_')]# MESSY.
local_experts[h5] = sess.graph.get_tensor_by_name('{}output:0'.format(h5))
data.train._X = np.hstack([ data.train.X, np.vstack([ flow(sess, local_experts, x) for x in chunks(data.train.X, batch_size) ]) ])
data.validation._X = np.hstack([ data.validation.X, flow(sess, local_experts, data.validation.X) ])
data.test._X = np.hstack([ data.test.X, flow(sess, local_experts, data.test.X) ])
x = tf.placeholder('float', shape=[None, data.train.X_features], name='input')
y_ = tf.placeholder('float', shape=[None, data.train.Y_features], name='target')
if perceptron:
W = weight_variable([data.train.X_features, data.train.Y_features], name='weights')
b = bias_variable([data.train.Y_features], name='bias')
logits = tf.matmul(x,W) + b
else:
W_in = weight_variable([data.train.X_features, hidden_size], name='weights_in')
b_in = bias_variable([hidden_size], name='bias_in')
hidden = tf.matmul(x,W_in) + b_in
relu = tf.nn.relu(hidden)
keep_prob = tf.placeholder_with_default([1.], shape=None)
hidden_dropout = tf.nn.dropout(relu, keep_prob)
W_out = weight_variable([hidden_size,data.train.Y_features], name='weights_out')
b_out = bias_variable([data.train.Y_features], name='bias_out')
logits = tf.matmul(relu,W_out) + b_out
y = tf.nn.softmax(logits, name='output')
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, y_)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
sess.run(tf.initialize_all_variables())
last_epoch = 0
t_epoch = time.time()
while data.train.epoch <= epochs:
epoch = data.train.epoch
batch_x, batch_y = data.train.next_batch(batch_size)
t_start = time.time()
feed_dict = {x: batch_x, y_: batch_y } if perceptron else {x: batch_x, y_: batch_y, keep_prob: dropout}
train_step.run(feed_dict=feed_dict)
t_end = time.time() - t_start
if epoch > last_epoch:
if epoch % print_every == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch_x,
y_: batch_y })
validation_accuracy = accuracy.eval(feed_dict={
x: data.validation.X,
y_: data.validation.Y })
print('''Epoch {} train accuracy: {}, validation accuracy: {}. '''
'''{} states/sec, {} secs/epoch.'''.format(epoch, train_accuracy,
validation_accuracy, batch_size/t_end,
time.time() - t_epoch))
if epoch % save_every == 0 or epoch == epochs:
output_graph_def = graph_util.convert_variables_to_constants(
sess, sess.graph.as_graph_def(), ['input', 'output'])
with gfile.FastGFile(os.path.join(model_dir, model_name), 'w') as f:
f.write(output_graph_def.SerializeToString())
t_epoch = time.time()
last_epoch = epoch
print('Trained model saved to {}'.format(os.path.join(model_dir, model_name)))
if test_ratio > 0:
test_accuracy = accuracy.eval(feed_dict={x: data.test.X, y_: data.test.Y })
print('Evaluation on testing data: {}'.format(test_accuracy))
