def run_training():
"""Train for a number of steps."""
data_sets = overexpress_data.read_data_sets(
seq_file=FLAGS.seq_file,
expr_file=FLAGS.expr_file,
reg_names_file=FLAGS.reg_names_file,
fold_change=FLAGS.fold_change)
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
# Generate placeholders for the images and labels.
seq_placeholder, reg_expr_placeholder, labels_placeholder, keep_prob_placeholder, meta_placeholder = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
y = regression_model.inference(seq_placeholder, reg_expr_placeholder,
keep_prob_placeholder, FLAGS.batch_size)
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# And then after everything is built:
# Run the Op to initialize the variables.
sess.run(init)
saver = tf.train.import_meta_graph(FLAGS.graph)
saver.restore(sess, tf.train.latest_checkpoint(FLAGS.log_dir))
# Make confusion matrix:
# print(data_sets.overexpress_data.next_batch())
pred = prediction(sess, y, seq_placeholder, reg_expr_placeholder,
labels_placeholder, keep_prob_placeholder,
meta_placeholder, data_sets.overexpress_data)
np.savetxt(FLAGS.out,
pred,
fmt=['%.3f', '%.3f', '%s', '%s', '%s'],
delimiter='\t')
def run_training():
"""Train for a number of steps."""
data_sets = input_data.read_data_sets(seq_file=FLAGS.seq_file,
expr_file=FLAGS.expr_file,
reg_names_file=FLAGS.reg_names_file)
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
# Generate placeholders for the images and labels.
seq_placeholder, reg_expr_placeholder, labels_placeholder, keep_prob_pl = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
y = regression_model.inference(seq_placeholder, reg_expr_placeholder,
keep_prob_pl, FLAGS.batch_size)
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# And then after everything is built:
# Run the Op to initialize the variables.
sess.run(init)
# saver = tf.train.import_meta_graph('../../../processed_data/dropout/model.ckpt-381999.meta')
saver = tf.train.import_meta_graph(FLAGS.graph)
saver.restore(sess, tf.train.latest_checkpoint(FLAGS.log_dir))
# Make confusion matrix:
pred = prediction(sess, y, seq_placeholder, reg_expr_placeholder,
labels_placeholder, keep_prob_pl, data_sets.test)
np.savetxt("%s/prediction.txt" % (FLAGS.log_dir), pred)
def run_training():
"""Train for a number of steps."""
data_sets = input_data.read_data_sets(seq_file=FLAGS.seq_file,
expr_file=FLAGS.expr_file,
reg_names_file=FLAGS.reg_names_file)
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
# Generate placeholders for the images and labels.
seq_placeholder, reg_expr_placeholder, labels_placeholder, keep_prob_pl = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
y = regression_model.inference(seq_placeholder, reg_expr_placeholder,
keep_prob_pl, FLAGS.batch_size)
# Add to the Graph the Ops for loss calculation.
loss = regression_model.loss(y, labels_placeholder)
# Add to the Graph the Ops that calculate and apply gradients.
train_op = regression_model.training(loss, FLAGS.learning_rate)
# Add the Op to compare the logits to the labels during evaluation.
eval_sse = regression_model.evaluation(y, labels_placeholder)
# Add summaries:
tf.summary.scalar('loss', loss)
# Build the summary Tensor based on the TF collection of Summaries.
summary = tf.summary.merge_all()
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session(config=tf.ConfigProto(
intra_op_parallelism_threads=FLAGS.threads))
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)
# And then after everything is built:
# Open files to write:
train_log = open(FLAGS.log_dir + '/train_mse.log', 'w')
val_log = open(FLAGS.log_dir + '/val_mse.log', 'w')
test_log = open(FLAGS.log_dir + '/test_mse.log', 'w')
# Run the Op to initialize the variables.
sess.run(init)
# Start the training loop.
for step in xrange(FLAGS.max_steps):
start_time = time.time()
# Fill a feed dictionary with the actual set of images and labels
# for this particular training step.
feed_dict = fill_feed_dict(data_sets.train,
seq_placeholder,
reg_expr_placeholder,
labels_placeholder,
keep_prob_pl,
keep_prob=0.5,
batch_size=FLAGS.batch_size)
# Run one step of the model. The return values are the activations
# from the `train_op` (which is discarded) and the `loss` Op.
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
duration = time.time() - start_time
# Write the summaries and print an overview fairly often.
if step % 100 == 0:
# Print status to stdout.
print('Step %d: loss = %.2f (%.3f sec)' %
(step, loss_value, duration))
# Update the events file.
summary_str = sess.run(summary, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# Save a checkpoint and evaluate the model periodically.
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.log_dir, 'model.ckpt')
saver.save(sess, checkpoint_file, global_step=step)
# Evaluate against the training set.
print('Training Data Eval:')
do_eval(sess, eval_sse, seq_placeholder, reg_expr_placeholder,
labels_placeholder, keep_prob_pl, data_sets.train,
step, train_log)
# Evaluate against the validation set.
print('Validation Data Eval:')
do_eval(sess, eval_sse, seq_placeholder, reg_expr_placeholder,
labels_placeholder, keep_prob_pl, data_sets.validation,
step, val_log)
# Evaluate against the test set.
print('Test Data Eval:')
do_eval(sess, eval_sse, seq_placeholder, reg_expr_placeholder,
labels_placeholder, keep_prob_pl, data_sets.test, step,
test_log)
# Close files and session:
train_log.close()
val_log.close()
test_log.close()
sess.close()