def evaluation(model, supervisor, num_label):
teX, teY, num_te_batch = load_data(cfg.dataset,
cfg.batch_size,
is_training=False)
fd_test_acc = save_to()
with supervisor.managed_session(config=tf.ConfigProto(
allow_soft_placement=True)) as sess:
supervisor.saver.restore(sess, tf.train.latest_checkpoint(cfg.logdir))
tf.logging.info('Model restored!')
test_acc = 0
prob = np.zeros((num_te_batch * cfg.batch_size, num_label))
for i in tqdm(range(num_te_batch),
total=num_te_batch,
ncols=70,
leave=False,
unit='b'):
start = i * cfg.batch_size
end = start + cfg.batch_size
acc, prob[start:end, :] = sess.run(
[model.accuracy, model.activation], {
model.X: teX[start:end],
model.labels: teY[start:end]
})
test_acc += acc
test_acc = test_acc / (cfg.batch_size * num_te_batch)
np.savetxt(cfg.results + '/prob_test.txt', prob, fmt='%1.2f')
print(
'Classification probability for each category has been saved to ' +
cfg.results + '/prob_test.txt')
fd_test_acc.write(str(test_acc))
fd_test_acc.close()
print('Test accuracy has been saved to ' + cfg.results +
'/test_accuracy.txt')
def train(model, supervisor):
trX, trY, num_tr_batch, valX, valY, num_val_batch = load_data(cfg.dataset, is_training=True)
Y = valY[:num_val_batch * cfg.batch_size].reshape((-1, 1))
if cfg.dataset == 'mnist' or cfg.dataset == 'fashion-mnist':
num_label = 10
elif cfg.dataset == 'smallNORB':
num_label = 5
fd_train_acc, fd_loss, fd_val_acc = save_to()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with supervisor.managed_session(config=config) as sess:
print("\nNote: all of results will be saved to directory: " + cfg.results)
for epoch in range(cfg.epoch):
print('Training for epoch ' + str(epoch) + '/' + str(cfg.epoch) + ':')
if supervisor.should_stop():
print('supervisor stoped!')
break
for step in tqdm(range(num_tr_batch), total=num_tr_batch, ncols=70, leave=False, unit='b'):
start = step * cfg.batch_size
end = start + cfg.batch_size
global_step = epoch * num_tr_batch + step
if global_step % cfg.train_sum_freq == 0:
_, loss, train_acc, summary_str = sess.run([model.train_op, model.loss, model.accuracy, model.train_summary])
assert not np.isnan(loss), 'Something wrong! loss is nan...'
supervisor.summary_writer.add_summary(summary_str, global_step)
fd_loss.write(str(global_step) + ',' + str(loss) + "\n")
fd_loss.flush()
fd_train_acc.write(str(global_step) + ',' + str(train_acc / cfg.batch_size) + "\n")
fd_train_acc.flush()
else:
sess.run(model.train_op)
if cfg.val_sum_freq != 0 and (global_step) % cfg.val_sum_freq == 0:
val_acc = 0
prob = np.zeros((num_val_batch * cfg.batch_size, num_label))
for i in range(num_val_batch):
start = i * cfg.batch_size
end = start + cfg.batch_size
acc, prob[start:end, :] = sess.run([model.accuracy, model.activation], {model.X: valX[start:end], model.labels: valY[start:end]})
val_acc += acc
val_acc = val_acc / (cfg.batch_size * num_val_batch)
np.savetxt(cfg.results + '/activations_step_' + str(global_step) + '.txt', np.hstack((prob, Y)), fmt='%1.2f')
fd_val_acc.write(str(global_step) + ',' + str(val_acc) + '\n')
fd_val_acc.flush()
if (epoch + 1) % cfg.save_freq == 0:
supervisor.saver.save(sess, cfg.logdir + '/model_epoch_%04d_step_%02d' % (epoch, global_step))
fd_val_acc.close()
fd_train_acc.close()
fd_loss.close()