with sess.as_default():
# load the saved meta graph and restore variables
saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
saver.restore(sess, checkpoint_file)
# Get the placeholders from the graph by name
X = graph.get_operation_by_name("X").outputs[0]
dropout_keep_prob = graph.get_operation_by_name(
"dropout_keep_prob").outputs[0]
# Tensors we want to evaluate
predictions = graph.get_operation_by_name(
"output/predictions").outputs[0]
#Generate batches for one epoch
batches = gb.batch_generator(list(x_test),
FLAGS.batch_size,
1,
shuffle=False)
# Collect the predictions her
all_predictions = []
counter = 0
for x_test_batch in batches:
print('batch_number: ', counter, end='\r', flush=True)
batch_predictions = sess.run(predictions, {
X: x_test_batch,
dropout_keep_prob: 1.0
})
all_predictions = np.concatenate(
[all_predictions, batch_predictions])
counter += 1
mlp.dropout_keep_prob: 1.0,
}
step, summaries, loss, accuracy = sess.run(
[global_step, dev_summary_op, mlp.loss, mlp.accuracy],
feed_dict)
time_str = datetime.datetime.now().isoformat()
print("Evaluation: {}: step {}, loss{:g}, acc {:g}".format(
time_str, step, loss, accuracy),
end='\r',
flush=True)
if writer:
writer.add_summary(summaries, step)
# Generate batches
batches = gb.batch_generator(list(zip(x_train, y_train)),
FLAGS.train_batch_size,
FLAGS.num_epochs)
dev_batches = gb.batch_generator(list(zip(x_dev, y_dev)),
FLAGS.train_batch_size,
FLAGS.num_epochs * 10)
# Training loop. For each batch..
for batch in batches:
if len(batch) != FLAGS.train_batch_size:
continue
x_batch, y_batch = zip(*batch)
train_step(x_batch, y_batch)
current_step = tf.train.global_step(sess, global_step) - 1
if current_step % FLAGS.evaluate_every == 0:
x_dev_batch, y_dev_batch = zip(*dev_batches.__next__())
dev_step(x_dev_batch,