def val():
num_test = 10000
data_dir = '/home/rong/something_for_deep/cifar-10-batches-bin'
train_log_dir = './logs/train'
image_batch, label_batch = input_data.read_cifar10(data_dir,
is_train=False,
batch_size=BATCH_SIZE,
shuffle=False)
vgg16 = model.VGG16()
logits = vgg16.build(image_batch, NUM_CLASSES, False)
saver = tf.train.Saver()
correct_per_batch = tools.num_correct_prediction(logits, label_batch)
with tf.Session() as sess:
print('Reading checkpoints')
ckpt = tf.train.get_checkpoint_state(train_log_dir)
if ckpt and ckpt.model_checkpoint_path:
global_step = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
saver.restore(sess, ckpt.model_checkpoint_path)
print('Loading success, global_step is %s' % global_step)
else:
print('No checkpoint file found')
return
saver.restore(sess, './logs/train/model.ckpt-8000')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
print('\nEvaluating......')
num_step = int(math.floor(num_test / BATCH_SIZE))
num_sample = num_step * BATCH_SIZE
step = 0
total_correct = 0
while step < num_step and not coord.should_stop():
batch_correct = sess.run(correct_per_batch)
total_correct += np.sum(batch_correct)
step += 1
if step % 10 == 0:
print('Testing samples: %d' % (step * BATCH_SIZE))
print('Correct predictions: %d' % total_correct)
print('Average accuracy: %.2f%%' % (total_correct /
(step * BATCH_SIZE)))
print('Total testing samples: %d' % num_sample)
print('Total correct predictions: %d' % total_correct)
print('Average accuracy: %.2f%%' %
(100 * total_correct / num_sample))
except Exception as e:
coord.request_stop(e)
finally:
coord.request_stop()
coord.join(threads)
def main(args, model_name, trainloader, testloader):
n_classes = args["dataset"]["n_classes"]
net = model.VGG16(n_classes, True)
optimizer = torch.optim.SGD(params=net.parameters(),
lr=lr,
momentum=momentum,
weight_decay=weight_decay)
criterion = nn.CrossEntropyLoss(reduction="none").cuda()
net = torch.nn.DataParallel(net).to(device)
train_dp(model_name, model_path, mode, net, criterion, optimizer,
trainloader, testloader, n_epochs, noise)
