def main(_):
dataset = cfg.dataset
input_shape, num_classes, use_test_queue = get_dataset_values(
dataset, cfg.test_batch_size, is_training=False)
tf.logging.info("Initializing CNN for {}...".format(dataset))
model = CNN(input_shape,
num_classes,
is_training=False,
use_test_queue=use_test_queue)
tf.logging.info("Finished initialization.")
if not os.path.exists(cfg.logdir):
os.mkdir(cfg.logdir)
logdir = os.path.join(cfg.logdir, model.name)
if not os.path.exists(logdir):
os.mkdir(logdir)
logdir = os.path.join(logdir, dataset)
if not os.path.exists(logdir):
os.mkdir(logdir)
sv = tf.train.Supervisor(graph=model.graph,
logdir=logdir,
save_model_secs=0)
tf.logging.info("Initialize evaluation...")
evaluate(model, sv, dataset)
tf.logging.info("Finished evaluation.")
def run():
args = get_args()
train_set = read_data(data_folder / args.train)
test_set = read_data(data_folder / args.test,
col_names=("tweet_id", "text", "q1_label"))
regular_solution = Naive_Bayes(train_set, test_set, ['yes', 'no'], False)
filtered_solution = Naive_Bayes(train_set, test_set, ['yes', 'no'], True)
output_trace(output_folder / "trace_NB-BOW-OV.txt", regular_solution)
output_trace(output_folder / "trace_NB-BOW-FV.txt", filtered_solution)
evaluate(output_folder / "eval_NB-BOW-OV.txt", regular_solution, "yes",
"no")
evaluate(output_folder / "eval_NB-BOW-FV.txt", filtered_solution, "yes",
"no")
#using sanitized input
train_set_sanitized = sanitize(train_set)
test_set_sanitized = sanitize(test_set)
sanitized_solution = Naive_Bayes(train_set_sanitized, test_set_sanitized,
['yes', 'no'], False)
output_trace(output_folder / "trace_NB-BOW-OV_sanitized.txt",
sanitized_solution)
evaluate(output_folder / "eval_NB-BOW-OV_sanitized.txt",
sanitized_solution, "yes", "no")
def train():
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels.
images, labels = convnet.inputs(eval_data=False)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = convnet.inference(images)
# Calculate loss.
loss = convnet.loss(logits, labels)
# Calculate accuracy
top_k_op = tf.nn.in_top_k(logits, labels, 1)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = convnet.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
sess.run(init)
# Load previously stored model from checkpoint
ckpt = tf.train.get_checkpoint_state(FLAGS.train_dir)
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
# Assuming model_checkpoint_path looks something like:
# /my-favorite-path/cifar10_train/model.ckpt-0,
# extract global_step from it.
global_step = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
print("Loading from checkpoint.Global step %s" % global_step)
else:
print("No checkpoint file found...Creating a new model...")
stepfile = "/home/soms/EmotionMusic/MediaEval_Classification/stepfile.txt"
if not os.path.exists(stepfile):
print("No step file found.")
step = 0
else:
f = open(stepfile, "r")
step = int(f.readlines()[0])
print("Step file step %d" % step)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
while step < FLAGS.max_steps:
#print(images.eval(session = sess).shape)
start_time = time.time()
_, loss_value, predictions = sess.run([train_op, loss, top_k_op])
duration = time.time() - start_time
def signal_handler(signal, frame):
f = open(stepfile, 'w')
f.write(str(step))
print("Step file written to.")
sys.exit(0)
signal.signal(signal.SIGINT, signal_handler)
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
num_examples_per_step = 25
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
accuracy = float(np.sum(predictions)) / num_examples_per_step
format_str = (
'%s: step %d, loss = %.2f accuracy@1 = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), step, loss_value, accuracy,
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 500 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
model_eval.evaluate(mode=1)
step += 1