def main(_):
"""3.print configurations"""
print('tf version:', tf.__version__)
print('tf setup:')
for k, v in FLAGS.flag_values_dict().items():
print(k, v)
FLAGS.TB_dir += '_' + str(FLAGS.c_dim)
"""4.check/create folders"""
print("check dirs...")
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.TB_dir):
os.makedirs(FLAGS.TB_dir)
"""5.begin tf session"""
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
print("building model...")
"""6.init srcnn model"""
srcnn = SRCNN(sess, FLAGS)
"""7.start to train/test"""
if (FLAGS.is_train):
srcnn.train()
elif FLAGS.patch_test:
srcnn.test()
else:
srcnn.test_whole_img()
def main(_):
t0 = time.time()
pp.pprint(FLAGS.build_model)
if not FLAGS.build_model:
FLAGS.test_img = validate(FLAGS.test_img)
print("Image path = ", FLAGS.test_img)
if not os.path.isfile(FLAGS.test_img):
print("File does not exist ", FLAGS.test_img)
sys.exit()
create_required_directories(FLAGS)
with tf.compat.v1.Session() as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
if FLAGS.build_model:
srcnn.train(FLAGS)
else:
srcnn.test(FLAGS)
print("\n\nTime taken %4.2f\n\n" % (time.time() - t0))
def main():
dataloaders = myDataloader()
train_loader = dataloaders.getTrainLoader(batch_size)
model = SRCNN().cuda()
model.train()
optimizer = optim.Adam(model.parameters(), lr=lr)
mse_loss = nn.MSELoss()
for ep in range(epoch):
running_loss = 0.0
for i, (pic, blurPic, _) in enumerate(train_loader):
pic = pic.cuda()
blurPic = blurPic.cuda()
optimizer.zero_grad()
out = model(blurPic)
loss = mse_loss(out, pic)
loss.backward()
optimizer.step()
running_loss += loss
if i % 10 == 9:
print('[%d %d] loss: %.4f' %
(ep + 1, i + 1, running_loss / 20))
running_loss = 0.0
if ep % 10 == 9:
torch.save(model.state_dict(),
f="./result/train/" + str(ep + 1) + "srcnnParms.pth")
print("finish training")
def main(_): #?
with tf.Session() as sess:
srcnn = SRCNN(sess,
image_size = FLAGS.image_size,
label_size = FLAGS.label_size,
c_dim = FLAGS.c_dim)
srcnn.train(FLAGS)
def main(_):
with tf.Session() as sess:
srcnn = SRCNN(sess,
image_dim=FLAGS.image_dim,
label_dim=FLAGS.label_dim,
channel=FLAGS.channel)
srcnn.train(FLAGS)
def main(args):
srcnn = SRCNN(
image_size=args.image_size,
c_dim=args.c_dim,
is_training=True,
learning_rate=args.learning_rate,
batch_size=args.batch_size,
epochs=args.epochs)
X_train, Y_train = load_train(image_size=args.image_size, stride=args.stride, scale=args.scale)
srcnn.train(X_train, Y_train)
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
with tf.Session() as sess:
srcnn = SRCNN(sess, FLAGS)
srcnn.train()
def main(_): #?
with tf.Session() as sess:
#print("Calling init")
srcnn = SRCNN(sess,
image_size = FLAGS.image_size,
label_size = FLAGS.label_size,
c_dim = FLAGS.c_dim)
#print("Calling train")
srcnn.train(FLAGS)
def main(_):
"""3.print configurations"""
print('tf version:',tf.__version__)
print('tf setup:')
#os.makedirs(FLAGS.checkpoint_dir)
"""5.begin tf session"""
with tf.Session() as sess:
"""6.init srcnn model"""
srcnn = SRCNN(sess, FLAGS)
"""7.start to train/test"""
if(FLAGS.is_train):
srcnn.train()
else:
srcnn.test()
def main(_):
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
with tf.Session() as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
srcnn.train(FLAGS)
def main():
if not os.path.exists(Config.checkpoint_dir):
os.makedirs(Config.checkpoint_dir)
with tf.Session() as sess:
trysr = SRCNN(sess,
image_size=Config.image_size,
label_size=Config.label_size,
batch_size=Config.batch_size,
c_dim=Config.c_dim,
checkpoint_dir=Config.checkpoint_dir,
scale=Config.scale)
trysr.train(Config)
def train():
print("process the image to h5file.....")
data_dir = flags.data_dir
h5_dir = flags.h5_dir
stride = flags.train_stride
data_helper.gen_input_image(data_dir, h5_dir, stride)
print("reading data......")
h5_path = os.path.join(h5_dir, "data.h5")
data, label = data_helper.load_data(h5_path)
print("initialize the model......")
model = SRCNN(flags)
model.build_graph()
model.train(data, label)
def main(_):
"""3.print configurations"""
print('tf version:', tf.__version__)
print('tf setup:')
for k, v in FLAGS.flag_values_dict().items():
print(k, v)
"""4.check/create folders"""
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
"""5.begin tf session"""
with tf.Session() as sess:
"""6.init srcnn model"""
srcnn = SRCNN(sess, FLAGS)
"""7.start to train/test"""
if (FLAGS.is_train):
srcnn.train()
else:
srcnn.test()
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
with tf.Session() as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
is_grayscale=FLAGS.is_grayscale,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
srcnn.train(FLAGS)
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
with tf.Session() as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
#srcnn.test('Test/Set5/baby_GT.bmp', FLAGS)
srcnn.train(FLAGS)
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
srcnn.train(FLAGS)
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
srcnn = SRCNN(image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir,
FLAGS=FLAGS)
srcnn.call()
if FLAGS.is_train == True:
srcnn.train()
else:
srcnn.inference()
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
config = tf.ConfigProto(allow_soft_placement=True)
with tf.device('/gpu:0'):
with tf.Session(config=config) as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir,
config=FLAGS)
srcnn.train(FLAGS)
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
config = tf.ConfigProto(allow_soft_placement=True)
with tf.device('/device:GPU:0'):
with tf.Session(config=config) as sess:
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
batch_size=FLAGS.batch_size,
ci_dim=FLAGS.ci_dim,
co_dim=FLAGS.co_dim,
scale_factor=FLAGS.scale_factor,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir,
model_carac=FLAGS.model_carac,
train_dir=FLAGS.train_dir,
test_dir=FLAGS.test_dir)
srcnn.train(FLAGS)
train_dataloader = DataLoader(dataset=train_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers,
pin_memory=True,
drop_last=True)
eval_dataset = EvalDataset(args.eval_file)
eval_dataloader = DataLoader(dataset=eval_dataset, batch_size=1)
best_weights = copy.deepcopy(model.state_dict())
best_epoch = 0
best_psnr = 0.0
for epoch in range(args.num_epochs):
model.train()
epoch_losses = AverageMeter()
with tqdm(total=(len(train_dataset) -
len(train_dataset) % args.batch_size)) as t:
t.set_description('epoch:{}/{}'.format(epoch, args.num_epochs - 1))
for data in train_dataloader:
inputs, labels = data
inputs = inputs.to(device)
labels = labels.to(device)
preds = model(inputs)
loss = criterion(preds, labels)
self.learning_rate = 1e-4
self.batch_size = 128
self.result_dir = 'result'
self.test_img = '' # Do not change this.
arg = this_config()
print(
"Hello TA! We are group 7. Thank you for your work for us. Hope you have a happy day!"
)
with tf.Session() as sess:
FLAGS = arg
srcnn = SRCNN(sess,
image_size=FLAGS.image_size,
label_size=FLAGS.label_size,
c_dim=FLAGS.c_dim)
srcnn.train(FLAGS)
# Testing
files = glob.glob(os.path.join(os.getcwd(), 'train_set', 'LR0', '*.jpg'))
test_files = random.sample(files, len(files) // 5)
FLAGS.is_train = False
count = 1
for f in test_files:
FLAGS.test_img = f
print('Saving ', count, '/', len(test_files), ': ', FLAGS.test_img,
'\n')
count += 1
srcnn.test(FLAGS)
