def main():
#### setup options of three networks
parser = argparse.ArgumentParser()
parser.add_argument('-opt_P', type=str, help='Path to option YMAL file of Predictor.')
parser.add_argument('-opt_C', type=str, help='Path to option YMAL file of Corrector.')
parser.add_argument('-opt_F', type=str, help='Path to option YMAL file of SFTMD_Net.')
parser.add_argument('--launcher', choices=['none', 'pytorch'], default='none',
help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
opt_P = option.parse(args.opt_P, is_train=True)
opt_C = option.parse(args.opt_C, is_train=True)
opt_F = option.parse(args.opt_F, is_train=True)
# convert to NoneDict, which returns None for missing keys
opt_P = option.dict_to_nonedict(opt_P)
opt_C = option.dict_to_nonedict(opt_C)
opt_F = option.dict_to_nonedict(opt_F)
# choose small opt for SFTMD test
opt_F = opt_F['sftmd']
#### random seed
seed = opt_P['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
util.set_random_seed(seed)
# create PCA matrix of enough kernel
batch_ker = util.random_batch_kernel(batch=30000, l=opt_P['kernel_size'], sig_min=0.2, sig_max=4.0, rate_iso=1.0, scaling=3, tensor=False)
print('batch kernel shape: {}'.format(batch_ker.shape))
b = np.size(batch_ker, 0)
batch_ker = batch_ker.reshape((b, -1))
pca_matrix = util.PCA(batch_ker, k=opt_P['code_length']).float()
print('PCA matrix shape: {}'.format(pca_matrix.shape))
#### distributed training settings
if args.launcher == 'none': # disabled distributed training
opt_P['dist'] = False
opt_F['dist'] = False
opt_C['dist'] = False
rank = -1
print('Disabled distributed training.')
else:
opt_P['dist'] = True
opt_F['dist'] = True
opt_C['dist'] = True
init_dist()
world_size = torch.distributed.get_world_size() #Returns the number of processes in the current process group
rank = torch.distributed.get_rank() #Returns the rank of current process group
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
###### SFTMD train ######
SFTMD_train(opt_F, rank, world_size, pca_matrix)
###### Predictor&Corrector train ######
IKC_train(opt_P, opt_C, opt_F, rank, world_size, pca_matrix)
def predictscore(listLRs, listSRs, LRpath_list):
optpath = './options/test/testScorenet_load.json'
opt = option.parse_imagetest(optpath)
opt = option.dict_to_nonedict(opt)
# initial configure
network_opt = opt['networks']
model_name = network_opt['which_model'].upper()
if opt['self_ensemble']: model_name += 'plus'
tmpsolver = create_solver(opt)
#print('===> Start Test')
#print("==================================================")
listscore = []
for i in range(len(listLRs)):
LR = listLRs[i]
SR = listSRs[i]
LR, SR = np2Tensor([LR,SR], opt['rgb_range'])
tmpsolver.feed_imgs(LR,SR)
tmpsolver.test_scorenet()
print(LRpath_list[i])
visuals = tmpsolver.get_current_visual_scorenet(need_HR=None)
score = visuals['predQS']#.to(torch.double)
listscore.append(score)
return listscore
class SISR():
def __init__(): return
parser = argparse.ArgumentParser(description='Test Super Resolution Models')
parser.add_argument('-opt', type=str, required=True, help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt)
opt = option.dict_to_nonedict(opt)
#initial configure
scale = opt['scale']
degrad = opt['degradation']
network_opt = opt['networks']
model_name = network_opt['which_model'].upper()
if opt['self_ensemble']: model_name += 'plus'
for _, dataset_opt in sorted(opt['datasets'].items()):
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
test_loaders.append(test_loader)
print('===> Test Dataset: [%s] Number of images: [%d]' % (test_set.name(), len(test_set)))
bm_names.append(test_set.name())
# create solver (and load model)
solver = create_solver(opt)
# create test dataloader
bm_names =[]
test_loaders = []
print("==================================================")
print("Method: %s || Scale: %d || Degradation: %s"%(model_name, scale, degrad))
def train_harness(opt, rank, main_loop=train_main):
resume_state = get_resume_state(opt)
# mkdir and loggers
logger, tb_logger = setup_logging(opt, resume_state, rank)
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
# random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
if rank <= 0:
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
# loaders
train_loader, val_loader, train_sampler = create_loaders(opt, logger, rank)
# training
main_loop(opt, train_loader, val_loader, train_sampler, logger,
resume_state, tb_logger, rank)
logger.handlers.clear()
def downloadModel():
# json parse
parser = argparse.ArgumentParser(
description='Test Super Resolution Models')
parser.add_argument('-opt',
type=str,
required=True,
help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt)
opt = option.dict_to_nonedict(opt)
# json parse된것 초기화
scale = opt['scale']
degrad = opt['degradation']
network_opt = opt['networks']
model_name = network_opt['which_model'].upper()
if opt['self_ensemble']: model_name += 'plus'
#json파일로 model로드
solver = create_solver(opt)
#testset SR한번 후 본격 SR 진행
shutil.copy('./results/LR/Test/!.png', './results/LR/MyImage/!.png')
shutil.copy('./results/LR/Test/!.png', './results/LR/MyImage/!!.png')
SR(solver, opt, model_name)
os.remove('./results/LR/MyImage/!!.png')
return solver, opt, model_name
def main():
#### options
parser = argparse.ArgumentParser()
parser.add_argument('--opt', type=str, help='Path to option YAML file.')
args = parser.parse_args()
opt = option.parse(args.opt, is_train=True)
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
#### random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
print('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = False
# torch.backends.cudnn.deterministic = True
#### create model
model = create_model(opt)
#### op counting
print('Start counting')
var_L = torch.zeros(1, 3, 320, 180).cuda()
# var_ref=torch.zeros(1280,720).cuda()
# var_H=torch.zeros(1280,720).cuda()
print('netG')
macs, params = profile(model.netG, inputs=(var_L, ))
macs, params = clever_format([macs, params], "%.5f")
print('macs:{},params:{}'.format(macs, params))
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, required=True, help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=False)
#util.mkdirs((path for key, path in opt['path'].items() if not key == 'pretrain_model_G'))
opt = option.dict_to_nonedict(opt)
#util.setup_logger(None, opt['path']['log'], 'test.log', level=logging.INFO, screen=True)
#logger = logging.getLogger('base')
#logger.info(option.dict2str(opt))
# Create test dataset and dataloader
test_loaders = []
for phase, dataset_opt in sorted(opt['datasets'].items()):
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
#logger.info('Number of test images in [{:s}]: {:d}'.format(dataset_opt['name'], len(test_set)))
test_loaders.append(test_loader)
# Create model
model = create_model(opt)
modelKey = 'SR'
if opt['model'] == 'ppon':
modelKey = 'img_p'
print('Model is recognized as PPON model')
for test_loader in test_loaders:
test_set_name = test_loader.dataset.opt['name']
print('\nTesting [{:s}]...'.format(test_set_name))
#logger.info('\nTesting [{:s}]...'.format(test_set_name))
test_start_time = time.time()
#dataset_dir = os.path.join(opt['path']['results_root'], test_set_name)
dataset_dir = test_loader.dataset.opt['dataroot_HR']
#util.mkdir(dataset_dir)
idx = 0
for data in test_loader:
idx += 1
need_HR = False #if test_loader.dataset.opt['dataroot_HR'] is None else True
model.feed_data(data, need_HR=need_HR)
img_path = data['LR_path'][0]
img_name = os.path.splitext(os.path.basename(img_path))[0]
model.test() # test
visuals = model.get_current_visuals(need_HR=need_HR)
if opt['model'] == 'ppon':
sr_img_c = util.tensor2img(visuals['img_c'])
sr_img_s = util.tensor2img(visuals['img_s'])
sr_img = util.tensor2img(visuals[modelKey])
# save images
baseinput = os.path.splitext(os.path.basename(img_path))[0][:-8]
model_path = opt['path']['pretrain_model_G']
modelname = os.path.splitext(os.path.basename(model_path))[0]
save_img_path = os.path.join(dataset_dir, img_name + '.png')
if opt['model'] == 'ppon':
def load_model(conf_path):
opt = option.parse(conf_path, is_train=False)
opt['gpu_ids'] = None
opt = option.dict_to_nonedict(opt)
model = create_model(opt)
model_path = opt_get(opt, ['model_path'], None)
model.load_network(load_path=model_path, network=model.netG)
return model, opt
def load_model(self):
opt_path = './options/test/test_EDVR_M_AI4KHDR.yml'
opt = option.parse(opt_path, is_train=False)
opt['dist'] = False
rank = -1
opt = option.dict_to_nonedict(opt)
torch.backends.cudnn.benchmark = True
#### create model
model = create_model(opt)
return model
def main():
assert torch.cuda.is_available()
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to option JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=True)
opt = option.dict_to_nonedict(
opt) # Convert to NoneDict, which return None for missing key.
def setup(opts):
global opt
model_scale = opts["scale"]
model = model_scale + "/" + "model.pth"
config = model_scale + "/" + "config.json"
opt = option.parse(config)
opt = option.dict_to_nonedict(opt)
solver = create_solver(opt, model)
return solver
def get_options(json_path):
"""options"""
# parser = argparse.ArgumentParser()
# parser.add_argument(
# '-opt', type=str, required=True, help='Path to options JSON file.')
# opt = option.parse(parser.parse_args().opt, is_train=False)
is_train = False
opt = option.parse(json_path, is_train)
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'pretrain_model_G'))
opt = option.dict_to_nonedict(opt)
util.setup_logger(None,
opt['path']['log'],
'test',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
return opt, logger
def run(pretrained_path,
output_path,
model_name='SRFBN',
scale=4,
degrad='BI',
opt='options/test/test_SRFBN_example.json'):
opt = option.parse(opt)
opt = option.dict_to_nonedict(opt)
# model = create_model(opt)
model = define_net({
"scale": scale,
"which_model": "SRFBN",
"num_features": 64,
"in_channels": 3,
"out_channels": 3,
"num_steps": 4,
"num_groups": 6
})
img = common.read_img('./results/LR/MyImage/chip.png', 'img')
np_transpose = np.ascontiguousarray(img.transpose((2, 0, 1)))
tensor = torch.from_numpy(np_transpose).float()
lr_tensor = torch.unsqueeze(tensor, 0)
checkpoint = torch.load(pretrained_path)
if 'state_dict' in checkpoint.keys():
checkpoint = checkpoint['state_dict']
load_func = model.load_state_dict
load_func(checkpoint)
torch.save(model, './model.pt')
with torch.no_grad():
SR = model(lr_tensor)[0]
# visuals = np.transpose(SR.data[0].float().cpu().numpy(), (1, 2, 0)).astype(np.uint8)
visuals = np.transpose(SR.data[0].float().cpu().numpy(),
(1, 2, 0)).astype(np.uint8)
imageio.imwrite(output_path, visuals)
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to options file.')
opt = option.parse(parser.parse_args().opt, is_train=False)
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'pretrain_model_G'))
opt = option.dict_to_nonedict(opt)
util.setup_logger(None,
opt['path']['log'],
'test.log',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
# Create test dataset and dataloader
test_loaders = []
znorm = False
for phase, dataset_opt in sorted(opt['datasets'].items()):
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
logger.info('Number of test images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(test_set)))
test_loaders.append(test_loader)
# Temporary, will turn znorm on for all the datasets. Will need to introduce a variable for each dataset and differentiate each one later in the loop.
if dataset_opt['znorm'] and znorm == False:
znorm = True
# Create model
model = create_model(opt)
for test_loader in test_loaders:
test_set_name = test_loader.dataset.opt['name']
logger.info('\nTesting [{:s}]...'.format(test_set_name))
test_start_time = time.time()
dataset_dir = os.path.join(opt['path']['results_root'], test_set_name)
util.mkdir(dataset_dir)
test_results = OrderedDict()
test_results['psnr'] = []
test_results['ssim'] = []
test_results['psnr_y'] = []
test_results['ssim_y'] = []
for data in test_loader:
need_HR = False if test_loader.dataset.opt[
'dataroot_HR'] is None else True
model.feed_data(data, need_HR=need_HR)
img_path = data['LR_path'][0]
img_name = os.path.splitext(os.path.basename(img_path))[0]
model.test() # test
visuals = model.get_current_visuals(need_HR=need_HR)
if znorm: #opt['datasets']['train']['znorm']: # If the image range is [-1,1] # In testing, each "dataset" can have a different name (not train, val or other)
sr_img = util.tensor2img(visuals['SR'],
min_max=(-1, 1)) # uint8
else: # Default: Image range is [0,1]
sr_img = util.tensor2img(visuals['SR']) # uint8
# save images
suffix = opt['suffix']
if suffix:
save_img_path = os.path.join(dataset_dir,
img_name + suffix + '.png')
else:
save_img_path = os.path.join(dataset_dir, img_name + '.png')
util.save_img(sr_img, save_img_path)
# calculate PSNR and SSIM
if need_HR:
if znorm: #opt['datasets']['train']['znorm']: # If the image range is [-1,1] # In testing, each "dataset" can have a different name (not train, val or other)
gt_img = util.tensor2img(visuals['HR'],
min_max=(-1, 1)) # uint8
else: # Default: Image range is [0,1]
gt_img = util.tensor2img(visuals['HR']) # uint8
gt_img = gt_img / 255.
sr_img = sr_img / 255.
crop_border = test_loader.dataset.opt['scale']
cropped_sr_img = sr_img[crop_border:-crop_border,
crop_border:-crop_border, :]
cropped_gt_img = gt_img[crop_border:-crop_border,
crop_border:-crop_border, :]
psnr = util.calculate_psnr(cropped_sr_img * 255,
cropped_gt_img * 255)
ssim = util.calculate_ssim(cropped_sr_img * 255,
cropped_gt_img * 255)
test_results['psnr'].append(psnr)
test_results['ssim'].append(ssim)
if gt_img.shape[2] == 3: # RGB image
sr_img_y = bgr2ycbcr(sr_img, only_y=True)
gt_img_y = bgr2ycbcr(gt_img, only_y=True)
cropped_sr_img_y = sr_img_y[crop_border:-crop_border,
crop_border:-crop_border]
cropped_gt_img_y = gt_img_y[crop_border:-crop_border,
crop_border:-crop_border]
psnr_y = util.calculate_psnr(cropped_sr_img_y * 255,
cropped_gt_img_y * 255)
ssim_y = util.calculate_ssim(cropped_sr_img_y * 255,
cropped_gt_img_y * 255)
test_results['psnr_y'].append(psnr_y)
test_results['ssim_y'].append(ssim_y)
logger.info('{:20s} - PSNR: {:.6f} dB; SSIM: {:.6f}; PSNR_Y: {:.6f} dB; SSIM_Y: {:.6f}.'\
.format(img_name, psnr, ssim, psnr_y, ssim_y))
else:
logger.info(
'{:20s} - PSNR: {:.6f} dB; SSIM: {:.6f}.'.format(
img_name, psnr, ssim))
else:
logger.info(img_name)
if need_HR: # metrics
# Average PSNR/SSIM results
ave_psnr = sum(test_results['psnr']) / len(test_results['psnr'])
ave_ssim = sum(test_results['ssim']) / len(test_results['ssim'])
logger.info('----Average PSNR/SSIM results for {}----\n\tPSNR: {:.6f} dB; SSIM: {:.6f}\n'\
.format(test_set_name, ave_psnr, ave_ssim))
if test_results['psnr_y'] and test_results['ssim_y']:
ave_psnr_y = sum(test_results['psnr_y']) / len(
test_results['psnr_y'])
ave_ssim_y = sum(test_results['ssim_y']) / len(
test_results['ssim_y'])
logger.info('----Y channel, average PSNR/SSIM----\n\tPSNR_Y: {:.6f} dB; SSIM_Y: {:.6f}\n'\
.format(ave_psnr_y, ave_ssim_y))
def main():
parser = argparse.ArgumentParser(
description='Test Super Resolution Models')
parser.add_argument('-opt',
type=str,
required=True,
help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt)
opt = option.dict_to_nonedict(opt)
# initial configure
scale = opt['scale']
degrad = opt['degradation']
network_opt = opt['networks']
model_name = network_opt['which_model'].upper()
if opt['self_ensemble']: model_name += 'plus'
# create test dataloader
bm_names = []
test_loaders = []
for _, dataset_opt in sorted(opt['datasets'].items()):
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
test_loaders.append(test_loader)
print('===> Test Dataset: [%s] Number of images: [%d]' %
(test_set.name(), len(test_set)))
bm_names.append(test_set.name())
# create solver (and load model)
solver = create_solver(opt)
# Test phase
print('===> Start Test')
print("==================================================")
print("Method: %s || Scale: %d || Degradation: %s" %
(model_name, scale, degrad))
for bm, test_loader in zip(bm_names, test_loaders):
print("Test set : [%s]" % bm)
sr_list = []
path_list = []
total_psnr = []
total_ssim = []
total_time = []
need_HR = False if test_loader.dataset.__class__.__name__.find(
'LRHR') < 0 else True
for iter, batch in enumerate(test_loader):
solver.feed_data(batch, need_HR=need_HR)
# calculate forward time
t0 = time.time()
solver.test()
t1 = time.time()
total_time.append((t1 - t0))
visuals = solver.get_current_visual(need_HR=need_HR)
sr_list.append(visuals['SR'])
# calculate PSNR/SSIM metrics on Python
if need_HR:
psnr, ssim = util.calc_metrics(visuals['SR'],
visuals['HR'],
crop_border=scale)
total_psnr.append(psnr)
total_ssim.append(ssim)
path_list.append(
os.path.basename(batch['HR_path'][0]).replace(
'HR', model_name))
print(
"[%d/%d] %s || PSNR(dB)/SSIM: %.2f/%.4f || Timer: %.4f sec ."
% (iter + 1, len(test_loader),
os.path.basename(batch['LR_path'][0]), psnr, ssim,
(t1 - t0)))
else:
path_list.append(os.path.basename(batch['LR_path'][0]))
print("[%d/%d] %s || Timer: %.4f sec ." %
(iter + 1, len(test_loader),
os.path.basename(batch['LR_path'][0]), (t1 - t0)))
if need_HR:
print("---- Average PSNR(dB) /SSIM /Speed(s) for [%s] ----" % bm)
print("PSNR: %.2f SSIM: %.4f Speed: %.4f" %
(sum(total_psnr) / len(total_psnr), sum(total_ssim) /
len(total_ssim), sum(total_time) / len(total_time)))
else:
print("---- Average Speed(s) for [%s] is %.4f sec ----" %
(bm, sum(total_time) / len(total_time)))
# save SR results for further evaluation on MATLAB
if need_HR:
save_img_path = os.path.join('./results/SR/' + degrad, model_name,
bm, "x%d" % scale)
else:
save_img_path = os.path.join('./results/SR/' + bm, model_name,
"x%d" % scale)
print("===> Saving SR images of [%s]... Save Path: [%s]\n" %
(bm, save_img_path))
if not os.path.exists(save_img_path): os.makedirs(save_img_path)
for img, name in zip(sr_list, path_list):
imageio.imwrite(os.path.join(save_img_path, name), img)
print("==================================================")
print("===> Finished !")
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to option JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=True)
opt = option.dict_to_nonedict(
opt) # Convert to NoneDict, which return None for missing key.
# train from scratch OR resume training
if opt['path']['resume_state']: # resuming training
resume_state = torch.load(opt['path']['resume_state'])
else: # training from scratch
resume_state = None
util.mkdir_and_rename(
opt['path']['experiments_root']) # rename old folder if exists
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger(None,
opt['path']['log'],
'train',
level=logging.INFO,
screen=True)
util.setup_logger('val', opt['path']['log'], 'val', level=logging.INFO)
logger = logging.getLogger('base')
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
option.check_resume(opt) # check resume options
logger.info(option.dict2str(opt))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt['name'])
# random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benckmark = True
# torch.backends.cudnn.deterministic = True
# create train and val dataloader
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
logger.info('Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
train_loader = create_dataloader(train_set, dataset_opt)
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt)
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
# create model
model = create_model(opt)
# resume training
if resume_state:
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
# training
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs):
for _, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
# update learning rate
model.update_learning_rate()
# training
model.feed_data(train_data)
model.optimize_parameters(current_step)
# log
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
epoch, current_step, model.get_current_learning_rate())
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar(k, v, current_step)
logger.info(message)
# validation
if current_step % opt['train']['val_freq'] == 0:
avg_psnr = 0.0
avg_IS = 0.0
idx = 0
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data['LR_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'], img_name)
util.mkdir(img_dir)
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2img(visuals['SR']) # uint8
gt_img = util.tensor2img(visuals['HR']) # uint8
# Save SR images for reference
save_img_path = os.path.join(img_dir, '{:s}_{:d}.png'.format(\
img_name, current_step))
util.save_img(sr_img, save_img_path)
#calculate IS
IS = model.get_IS()
avg_IS += IS
# calculate PSNR
crop_size = opt['scale']
gt_img = gt_img / 255.
sr_img = sr_img / 255.
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size, :]
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size, :]
avg_psnr += util.calculate_psnr(cropped_sr_img * 255,
cropped_gt_img * 255)
avg_psnr = avg_psnr / idx
avg_IS = avg_IS / idx
# log
logger.info('# Validation # PSNR: {:.4e} IS : {:.4e}'.format(
avg_psnr, avg_IS))
logger_val = logging.getLogger('val') # validation logger
logger_val.info(
'<epoch:{:3d}, iter:{:8,d}> psnr: {:.4e} is： {:.4e} '.
format(epoch, current_step, avg_psnr, avg_IS))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr', avg_psnr, current_step)
tb_logger.add_scalar('IS', avg_IS, current_step)
# save models and training states
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
def main():
#### options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, help='Path to option YMAL file.')
parser.add_argument('--launcher',
choices=['none', 'pytorch'],
default='none',
help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
opt = option.parse(args.opt, is_train=True)
#### distributed training settings
if args.launcher == 'none': # disabled distributed training
opt['dist'] = False
rank = -1
print('Disabled distributed training.')
else:
opt['dist'] = True
init_dist()
world_size = torch.distributed.get_world_size()
rank = torch.distributed.get_rank()
#### loading resume state if exists
if opt['path'].get('resume_state', None):
# distributed resuming: all load into default GPU
device_id = torch.cuda.current_device()
resume_state = torch.load(
opt['path']['resume_state'],
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt, resume_state['iter']) # check resume options
else:
resume_state = None
#### mkdir and loggers
if rank <= 0: # normal training (rank -1) OR distributed training (rank 0)
if resume_state is None:
util.mkdir_and_rename(
opt['path']
['experiments_root']) # rename experiment folder if exists
util.mkdirs(
(path for key, path in opt['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger('base',
opt['path']['log'],
'train_' + opt['name'],
level=logging.INFO,
screen=True,
tofile=True)
util.setup_logger('val',
opt['path']['log'],
'val_' + opt['name'],
level=logging.INFO,
screen=True,
tofile=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
version = float(torch.__version__[0:3])
if version >= 1.1: # PyTorch 1.1
from torch.utils.tensorboard import SummaryWriter
else:
logger.info(
'You are using PyTorch {}. Tensorboard will use [tensorboardX]'
.format(version))
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt['name'])
else:
util.setup_logger('base',
opt['path']['log'],
'train',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
#### random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
if rank <= 0:
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
#### create train and val dataloader
dataset_ratio = 200 # enlarge the size of each epoch
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
if opt['dist']:
train_sampler = DistIterSampler(train_set, world_size, rank,
dataset_ratio)
total_epochs = int(
math.ceil(total_iters / (train_size * dataset_ratio)))
else:
train_sampler = None
train_loader = create_dataloader(train_set, dataset_opt, opt,
train_sampler)
if rank <= 0:
logger.info(
'Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt, opt, None)
if rank <= 0:
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
#### create model
model = create_model(opt)
#### resume training
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
#### training
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs + 1):
if opt['dist']:
train_sampler.set_epoch(epoch)
for _, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
#### update learning rate
model.update_learning_rate(current_step,
warmup_iter=opt['train']['warmup_iter'])
#### training
model.feed_data(train_data)
model.optimize_parameters(current_step)
#### log
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
epoch, current_step, model.get_current_learning_rate())
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
if rank <= 0:
tb_logger.add_scalar(k, v, current_step)
if rank <= 0:
logger.info(message)
# validation
if current_step % opt['train']['val_freq'] == 0 and rank <= 0:
avg_psnr = 0.0
idx = 0
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data['LQ_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'], img_name)
util.mkdir(img_dir)
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2img(visuals['SR']) # uint8
gt_img = util.tensor2img(visuals['GT']) # uint8
# Save SR images for reference
save_img_path = os.path.join(
img_dir,
'{:s}_{:d}.png'.format(img_name, current_step))
util.save_img(sr_img, save_img_path)
# calculate PSNR
crop_size = opt['scale']
gt_img = gt_img / 255.
sr_img = sr_img / 255.
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size, :]
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size, :]
avg_psnr += util.calculate_psnr(cropped_sr_img * 255,
cropped_gt_img * 255)
avg_psnr = avg_psnr / idx
# log
logger.info('# Validation # PSNR: {:.4e}'.format(avg_psnr))
logger_val = logging.getLogger('val') # validation logger
logger_val.info(
'<epoch:{:3d}, iter:{:8,d}> psnr: {:.4e}'.format(
epoch, current_step, avg_psnr))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr', avg_psnr, current_step)
#### save models and training states
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
if rank <= 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
if rank <= 0:
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
def main():
#### setup options of three networks
parser = argparse.ArgumentParser()
parser.add_argument('-opt_P',
type=str,
help='Path to option YMAL file of Predictor.')
parser.add_argument('-opt_C',
type=str,
help='Path to option YMAL file of Corrector.')
parser.add_argument('-opt_F',
type=str,
help='Path to option YMAL file of SFTMD_Net.')
parser.add_argument('--launcher',
choices=['none', 'pytorch'],
default='none',
help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
opt_P = option.parse(args.opt_P, is_train=True)
opt_C = option.parse(args.opt_C, is_train=True)
opt_F = option.parse(args.opt_F, is_train=True)
# convert to NoneDict, which returns None for missing keys
opt_P = option.dict_to_nonedict(opt_P)
opt_C = option.dict_to_nonedict(opt_C)
opt_F = option.dict_to_nonedict(opt_F)
# choose small opt for SFTMD test, fill path of pre-trained model_F
opt_F = opt_F['sftmd']
# create PCA matrix of enough kernel
batch_ker = util.random_batch_kernel(batch=30000,
l=opt_P['kernel_size'],
sig_min=0.2,
sig_max=4.0,
rate_iso=1.0,
scaling=3,
tensor=False)
print('batch kernel shape: {}'.format(batch_ker.shape))
b = np.size(batch_ker, 0)
batch_ker = batch_ker.reshape((b, -1))
pca_matrix = util.PCA(batch_ker, k=opt_P['code_length']).float()
print('PCA matrix shape: {}'.format(pca_matrix.shape))
#### distributed training settings
if args.launcher == 'none': # disabled distributed training
opt_P['dist'] = False
opt_F['dist'] = False
opt_C['dist'] = False
rank = -1
print('Disabled distributed training.')
else:
opt_P['dist'] = True
opt_F['dist'] = True
opt_C['dist'] = True
init_dist()
world_size = torch.distributed.get_world_size(
) #Returns the number of processes in the current process group
rank = torch.distributed.get_rank(
) #Returns the rank of current process group
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
###### Predictor&Corrector train ######
#### loading resume state if exists
if opt_P['path'].get('resume_state', None):
# distributed resuming: all load into default GPU
device_id = torch.cuda.current_device()
resume_state = torch.load(
opt_P['path']['resume_state'],
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt_P,
resume_state['iter']) # check resume options
else:
resume_state = None
#### mkdir and loggers
if rank <= 0: # normal training (rank -1) OR distributed training (rank 0-7)
if resume_state is None:
# Predictor path
util.mkdir_and_rename(
opt_P['path']
['experiments_root']) # rename experiment folder if exists
util.mkdirs(
(path for key, path in opt_P['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# Corrector path
util.mkdir_and_rename(
opt_C['path']
['experiments_root']) # rename experiment folder if exists
util.mkdirs(
(path for key, path in opt_C['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger('base',
opt_P['path']['log'],
'train_' + opt_P['name'],
level=logging.INFO,
screen=True,
tofile=True)
util.setup_logger('val',
opt_P['path']['log'],
'val_' + opt_P['name'],
level=logging.INFO,
screen=True,
tofile=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt_P))
logger.info(option.dict2str(opt_C))
# tensorboard logger
if opt_P['use_tb_logger'] and 'debug' not in opt_P['name']:
version = float(torch.__version__[0:3])
if version >= 1.1: # PyTorch 1.1
from torch.utils.tensorboard import SummaryWriter
else:
logger.info(
'You are using PyTorch {}. Tensorboard will use [tensorboardX]'
.format(version))
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt_P['name'])
else:
util.setup_logger('base',
opt_P['path']['log'],
'train',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
#### random seed
seed = opt_P['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
if rank <= 0:
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
#### create train and val dataloader
dataset_ratio = 200 # enlarge the size of each epoch
for phase, dataset_opt in opt_P['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
total_iters = int(opt_P['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
if opt_P['dist']:
train_sampler = DistIterSampler(train_set, world_size, rank,
dataset_ratio)
total_epochs = int(
math.ceil(total_iters / (train_size * dataset_ratio)))
else:
train_sampler = None
train_loader = create_dataloader(train_set, dataset_opt, opt_P,
train_sampler)
if rank <= 0:
logger.info(
'Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt, opt_P, None)
if rank <= 0:
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
assert val_loader is not None
#### create model
model_F = create_model(opt_F) #load pretrained model of SFTMD
model_P = create_model(opt_P)
model_C = create_model(opt_C)
#### resume training
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model_P.resume_training(
resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
#### training
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs + 1):
if opt_P['dist']:
train_sampler.set_epoch(epoch)
for _, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
#### update learning rate, schedulers
# model.update_learning_rate(current_step, warmup_iter=opt_P['train']['warmup_iter'])
#### preprocessing for LR_img and kernel map
prepro = util.SRMDPreprocessing(opt_P['scale'],
pca_matrix,
para_input=opt_P['code_length'],
kernel=opt_P['kernel_size'],
noise=False,
cuda=True,
sig_min=0.2,
sig_max=4.0,
rate_iso=1.0,
scaling=3,
rate_cln=0.2,
noise_high=0.0)
LR_img, ker_map = prepro(train_data['GT'])
#### training Predictor
model_P.feed_data(LR_img, ker_map)
model_P.optimize_parameters(current_step)
P_visuals = model_P.get_current_visuals()
est_ker_map = P_visuals['Batch_est_ker_map']
#### log of model_P
if current_step % opt_P['logger']['print_freq'] == 0:
logs = model_P.get_current_log()
message = 'Predictor <epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
epoch, current_step, model_P.get_current_learning_rate())
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt_P['use_tb_logger'] and 'debug' not in opt_P['name']:
if rank <= 0:
tb_logger.add_scalar(k, v, current_step)
if rank <= 0:
logger.info(message)
#### training Corrector
for step in range(opt_C['step']):
# test SFTMD for corresponding SR image
model_F.feed_data(train_data, LR_img, est_ker_map)
model_F.test()
F_visuals = model_F.get_current_visuals()
SR_img = F_visuals['Batch_SR']
# Test SFTMD to produce SR images
# train corrector given SR image and estimated kernel map
model_C.feed_data(SR_img, est_ker_map, ker_map)
model_C.optimize_parameters(current_step)
C_visuals = model_C.get_current_visuals()
est_ker_map = C_visuals['Batch_est_ker_map']
#### log of model_C
if current_step % opt_C['logger']['print_freq'] == 0:
logs = model_C.get_current_log()
message = 'Corrector <epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
epoch, current_step,
model_C.get_current_learning_rate())
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt_C['use_tb_logger'] and 'debug' not in opt_C[
'name']:
if rank <= 0:
tb_logger.add_scalar(k, v, current_step)
if rank <= 0:
logger.info(message)
# validation, to produce ker_map_list(fake)
if current_step % opt_P['train']['val_freq'] == 0 and rank <= 0:
avg_psnr = 0.0
idx = 0
for _, val_data in enumerate(val_loader):
prepro = util.SRMDPreprocessing(
opt_P['scale'],
pca_matrix,
para_input=opt_P['code_length'],
kernel=opt_P['kernel_size'],
noise=False,
cuda=True,
sig_min=0.2,
sig_max=4.0,
rate_iso=1.0,
scaling=3,
rate_cln=0.2,
noise_high=0.0)
LR_img, ker_map = prepro(val_data['GT'])
single_img_psnr = 0.0
# valid Predictor
model_P.feed_data(LR_img, ker_map)
model_P.test()
P_visuals = model_P.get_current_visuals()
est_ker_map = P_visuals['Batch_est_ker_map']
for step in range(opt_C['step']):
step += 1
idx += 1
model_F.feed_data(val_data, LR_img, est_ker_map)
model_F.test()
F_visuals = model_F.get_current_visuals()
SR_img = F_visuals['Batch_SR']
# Test SFTMD to produce SR images
model_C.feed_data(SR_img, est_ker_map, ker_map)
model_C.test()
C_visuals = model_C.get_current_visuals()
est_ker_map = C_visuals['Batch_est_ker_map']
sr_img = util.tensor2img(F_visuals['SR']) # uint8
gt_img = util.tensor2img(F_visuals['GT']) # uint8
# Save SR images for reference
img_name = os.path.splitext(
os.path.basename(val_data['LQ_path'][0]))[0]
img_dir = os.path.join(opt_P['path']['val_images'],
img_name)
# img_dir = os.path.join(opt_F['path']['val_images'], str(current_step), '_', str(step))
util.mkdir(img_dir)
save_img_path = os.path.join(
img_dir, '{:s}_{:d}_{:d}.png'.format(
img_name, current_step, step))
util.save_img(sr_img, save_img_path)
# calculate PSNR
crop_size = opt_P['scale']
gt_img = gt_img / 255.
sr_img = sr_img / 255.
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size, :]
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size, :]
step_psnr = util.calculate_psnr(
cropped_sr_img * 255, cropped_gt_img * 255)
logger.info(
'<epoch:{:3d}, iter:{:8,d}, step:{:3d}> img:{:s}, psnr: {:.4f}'
.format(epoch, current_step, step, img_name,
step_psnr))
single_img_psnr += step_psnr
avg_psnr += util.calculate_psnr(
cropped_sr_img * 255, cropped_gt_img * 255)
avg_signle_img_psnr = single_img_psnr / step
logger.info(
'<epoch:{:3d}, iter:{:8,d}, step:{:3d}> img:{:s}, average psnr: {:.4f}'
.format(epoch, current_step, step, img_name,
avg_signle_img_psnr))
avg_psnr = avg_psnr / idx
# log
logger.info('# Validation # PSNR: {:.4f}'.format(avg_psnr))
logger_val = logging.getLogger('val') # validation logger
logger_val.info(
'<epoch:{:3d}, iter:{:8,d}, step:{:3d}> psnr: {:.4f}'.
format(epoch, current_step, step, avg_psnr))
# tensorboard logger
if opt_P['use_tb_logger'] and 'debug' not in opt_P['name']:
tb_logger.add_scalar('psnr', avg_psnr, current_step)
#### save models and training states
if current_step % opt_P['logger']['save_checkpoint_freq'] == 0:
if rank <= 0:
logger.info('Saving models and training states.')
model_P.save(current_step)
model_P.save_training_state(epoch, current_step)
model_C.save(current_step)
model_C.save_training_state(epoch, current_step)
if rank <= 0:
logger.info('Saving the final model.')
model_P.save('latest')
model_C.save('latest')
logger.info('End of Predictor and Corrector training.')
tb_logger.close()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
default='options/train/train_ESRCNN_S2self.json',
help='Path to option JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=True)
opt = option.dict_to_nonedict(opt)
if opt['path']['resume_state']:
resume_state = torch.load(opt['path']['resume_state'])
else:
resume_state = None
util.mkdir_and_rename(opt['path']['experiments_root'])
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
util.setup_logger(None,
opt['path']['log'],
'train',
level=logging.INFO,
screen=True)
util.setup_logger('val', opt['path']['log'], 'val', level=logging.INFO)
logger = logging.getLogger('base')
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
option.check_resume(opt)
logger.info(option.dict2str(opt))
if opt['use_tb_logger'] and 'debug' not in opt['name']:
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir='./tb_logger/' + opt['name'])
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benckmark = True
# Setup TrainDataLoader
trainloader = DataLoader(opt['datasets']['train']['dataroot'],
split='train')
train_size = int(
math.ceil(len(trainloader) / opt['datasets']['train']['batch_size']))
logger.info('Number of train images: {:,d}, iters: {:,d}'.format(
len(trainloader), train_size))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
TrainDataLoader = data.DataLoader(
trainloader,
batch_size=opt['datasets']['train']['batch_size'],
num_workers=12,
shuffle=True)
#Setup for validate
valloader = DataLoader(opt['datasets']['train']['dataroot'], split='val')
VALDataLoader = data.DataLoader(
valloader,
batch_size=opt['datasets']['train']['batch_size'] // 5,
num_workers=1,
shuffle=True)
logger.info('Number of val images:{:d}'.format(len(valloader)))
# Setup Model
model = get_model('esrcnn_s2self', opt)
if resume_state:
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state)
else:
current_step = 0
start_epoch = 0
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs):
for i, train_data in enumerate(TrainDataLoader):
current_step += 1
if current_step > total_iters:
break
model.update_learning_rate()
model.feed_data(train_data)
model.optimize_parameters(current_step)
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}>'.format(
epoch, current_step, model.get_current_learning_rate())
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v[0])
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar(k, v[0], current_step)
logger.info(message)
if current_step % opt['train']['val_freq'] == 0:
avg_psnr = 0.0
idx = 0
for i_val, val_data in enumerate(VALDataLoader):
idx += 1
img_name = val_data[3][0].split('.')[0]
model.feed_data(val_data)
model.val()
visuals = model.get_current_visuals()
pred_img = util.tensor2img(visuals['Pred'])
gt_img = util.tensor2img(visuals['label'])
avg_psnr += util.calculate_psnr(pred_img, gt_img)
avg_psnr = avg_psnr / idx
logger.info('# Validation #PSNR: {:.4e}'.format(avg_psnr))
logger_val = logging.getLogger('val')
logger_val.info(
'<epoch:{:3d}, iter:{:8,d}> psnr:{:.4e}'.format(
epoch, current_step, avg_psnr))
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr', avg_psnr, current_step)
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training')
def main():
parser = argparse.ArgumentParser(description='Test RCGAN model')
parser.add_argument('-opt', type=str, required=True, help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt)
opt = option.dict_to_nonedict(opt)
# create test dataloader
dataset_opt = opt['datasets']['test']
if dataset_opt is None:
raise ValueError("test dataset_opt is None!")
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
if test_loader is None:
raise ValueError("The test data does not exist")
solver = RCGANModel(opt)
solver.model_pth = opt['model_path']
solver.results_dir = os.path.join(opt['model_path'], 'results')
solver.cmp_dir = os.path.join(opt['model_path'], 'cmp')
# load model
model_pth = os.path.join(solver.model_pth, 'RCGAN_model.pth')
if model_pth is None:
raise ValueError("model_pth' is required.")
print('[Loading model from %s...]' % model_pth)
model_dict = torch.load(model_pth)
solver.model['netG'].load_state_dict(model_dict['state_dict_G'])
print('=> Done.')
print('[Start Testing]')
test_bar = tqdm(test_loader)
fused_list = []
path_list = []
if not os.path.exists(solver.cmp_dir):
os.makedirs(solver.cmp_dir)
for iter, batch in enumerate(test_bar):
solver.feed_data(batch)
solver.test()
visuals_list = solver.get_current_visual_list() # fetch current iteration results as cpu tensor
visuals = solver.get_current_visual() # fetch current iteration results as cpu tensor
images = torch.stack(visuals_list)
saveimg = thutil.make_grid(images, nrow=3, padding=5)
saveimg_nd = saveimg.byte().permute(1, 2, 0).numpy()
img_name = os.path.splitext(os.path.basename(batch['VIS_path'][0]))[0]
imageio.imwrite(os.path.join(solver.cmp_dir, 'comp_%s.bmp' % (img_name)), saveimg_nd)
fused_img = visuals['img_fuse']
fused_img = np.transpose(util.quantize(fused_img).numpy(), (1, 2, 0)).astype(np.uint8).squeeze()
fused_list.append(fused_img)
path_list.append(img_name)
save_img_path = solver.results_dir
if not os.path.exists(save_img_path):
os.makedirs(save_img_path)
for img, img_name in zip(fused_list, path_list):
imageio.imwrite(os.path.join(solver.results_dir, img_name + '.bmp'), img)
test_bar.close()
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to options JSON file.')
args = parser.parse_args()
options_path = args.opt
opt = option.parse(options_path, is_train=True)
util.mkdir_and_rename(
opt['path']['experiments_root']) # rename old experiments if exists
util.mkdirs((path for key, path in opt['path'].items() if not key == 'experiments_root' and \
not key == 'pretrain_model_G' and not key == 'pretrain_model_D'))
option.save(opt) # save option file to the opt['path']['options']
opt = option.dict_to_nonedict(
opt) # Convert to NoneDict, which return None for missing key.
# print to file and std_out simultaneously
class PrintLogger(object):
def __init__(self):
self.terminal = sys.stdout
self.log = open(os.path.join(opt['path']['log'], 'print_log.txt'), "a")
def write(self, message):
self.terminal.write(message)
self.log.write(message)
def flush(self):
pass
def main():
#### options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, help='Path to option YMAL file.')
parser.add_argument('--launcher',
choices=['none', 'pytorch'],
default='none',
help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
opt = option.parse(args.opt, is_train=True)
#### distributed training settings
opt['dist'] = False
rank = -1
print('Disabled distributed training.')
#### loading resume state if exists
if opt['path'].get('resume_state', None):
resume_state_path, _ = get_resume_paths(opt)
print('\n\t************************')
print('resume_state_path: ', resume_state_path)
print('\n\t************************')
# distributed resuming: all load into default GPU
if resume_state_path is None:
resume_state = None
else:
device_id = torch.cuda.current_device()
resume_state = torch.load(
resume_state_path,
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt,
resume_state['iter']) # check resume options
else:
resume_state = None
#### mkdir and loggers
if rank <= 0: # normal training (rank -1) OR distributed training (rank 0)
if resume_state is None:
util.mkdir_and_rename(
opt['path']
['experiments_root']) # rename experiment folder if exists
util.mkdirs(
(path for key, path in opt['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger('base',
opt['path']['log'],
'train_' + opt['name'],
level=logging.INFO,
screen=True,
tofile=True)
util.setup_logger('val',
opt['path']['log'],
'val_' + opt['name'],
level=logging.INFO,
screen=True,
tofile=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
# tensorboard logger
if opt.get('use_tb_logger', False) and 'debug' not in opt['name']:
version = float(torch.__version__[0:3])
if version >= 1.1: # PyTorch 1.1
from torch.utils.tensorboard import SummaryWriter
else:
logger.info(
'You are using PyTorch {}. Tensorboard will use [tensorboardX]'
.format(version))
from tensorboardX import SummaryWriter
conf_name = basename(args.opt).replace(".yml", "")
exp_dir = opt['path']['experiments_root']
log_dir_train = os.path.join(exp_dir, 'tb', conf_name, 'train')
log_dir_valid = os.path.join(exp_dir, 'tb', conf_name, 'valid')
tb_logger_train = SummaryWriter(log_dir=log_dir_train)
tb_logger_valid = SummaryWriter(log_dir=log_dir_valid)
else:
util.setup_logger('base',
opt['path']['log'],
'train',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
#### random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
if rank <= 0:
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
#### create train and val dataloader
dataset_ratio = 200 # enlarge the size of each epoch
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
print('Dataset created')
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
train_sampler = None
train_loader = create_dataloader(train_set, dataset_opt, opt,
train_sampler)
if rank <= 0:
logger.info(
'Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt, opt, None)
if rank <= 0:
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
#### create model
current_step = 0 if resume_state is None else resume_state['iter']
model = create_model(opt, current_step)
#### resume training
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
#### training
timer = Timer()
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
timerData = TickTock()
for epoch in range(start_epoch, total_epochs + 1):
if opt['dist']:
train_sampler.set_epoch(epoch)
timerData.tick()
for _, train_data in enumerate(train_loader):
timerData.tock()
current_step += 1
if current_step > total_iters:
break
#### training
model.feed_data(train_data)
#### update learning rate
model.update_learning_rate(current_step,
warmup_iter=opt['train']['warmup_iter'])
nll = model.optimize_parameters(current_step)
"""
try:
nll = model.optimize_parameters(current_step)
except RuntimeError as e:
nll = None
print("Skipping ERROR caught in nll = model.optimize_parameters(current_step): ")
print(e)
"""
if nll is None:
nll = 0
#### log
def eta(t_iter):
return (t_iter * (opt['train']['niter'] - current_step)) / 3600
if current_step % opt['logger']['print_freq'] == 0 \
or current_step - (resume_state['iter'] if resume_state else 0) < 25:
avg_time = timer.get_average_and_reset()
avg_data_time = timerData.get_average_and_reset()
message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}, t:{:.2e}, td:{:.2e}, eta:{:.2e}, nll:{:.3e}> '.format(
epoch, current_step, model.get_current_learning_rate(),
avg_time, avg_data_time, eta(avg_time), nll)
print(message)
timer.tick()
# Reduce number of logs
if current_step % 5 == 0:
tb_logger_train.add_scalar('loss/nll', nll, current_step)
tb_logger_train.add_scalar('lr/base',
model.get_current_learning_rate(),
current_step)
tb_logger_train.add_scalar('time/iteration',
timer.get_last_iteration(),
current_step)
tb_logger_train.add_scalar('time/data',
timerData.get_last_iteration(),
current_step)
tb_logger_train.add_scalar('time/eta',
eta(timer.get_last_iteration()),
current_step)
for k, v in model.get_current_log().items():
tb_logger_train.add_scalar(k, v, current_step)
# validation
if current_step % opt['train']['val_freq'] == 0 and rank <= 0:
avg_psnr = 0.0
idx = 0
nlls = []
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data['LQ_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'], img_name)
util.mkdir(img_dir)
model.feed_data(val_data)
nll = model.test()
if nll is None:
nll = 0
nlls.append(nll)
visuals = model.get_current_visuals()
sr_img = None
# Save SR images for reference
if hasattr(model, 'heats'):
for heat in model.heats:
for i in range(model.n_sample):
sr_img = util.tensor2img(
visuals['SR', heat, i]) # uint8
save_img_path = os.path.join(
img_dir,
'{:s}_{:09d}_h{:03d}_s{:d}.png'.format(
img_name, current_step,
int(heat * 100), i))
util.save_img(sr_img, save_img_path)
else:
sr_img = util.tensor2img(visuals['SR']) # uint8
save_img_path = os.path.join(
img_dir,
'{:s}_{:d}.png'.format(img_name, current_step))
util.save_img(sr_img, save_img_path)
assert sr_img is not None
# Save LQ images for reference
save_img_path_lq = os.path.join(
img_dir, '{:s}_LQ.png'.format(img_name))
if not os.path.isfile(save_img_path_lq):
lq_img = util.tensor2img(visuals['LQ']) # uint8
util.save_img(
cv2.resize(lq_img,
dsize=None,
fx=opt['scale'],
fy=opt['scale'],
interpolation=cv2.INTER_NEAREST),
save_img_path_lq)
# Save GT images for reference
gt_img = util.tensor2img(visuals['GT']) # uint8
save_img_path_gt = os.path.join(
img_dir, '{:s}_GT.png'.format(img_name))
if not os.path.isfile(save_img_path_gt):
util.save_img(gt_img, save_img_path_gt)
# calculate PSNR
crop_size = opt['scale']
gt_img = gt_img / 255.
sr_img = sr_img / 255.
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size, :]
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size, :]
avg_psnr += util.calculate_psnr(cropped_sr_img * 255,
cropped_gt_img * 255)
avg_psnr = avg_psnr / idx
avg_nll = sum(nlls) / len(nlls)
# log
logger.info('# Validation # PSNR: {:.4e}'.format(avg_psnr))
logger_val = logging.getLogger('val') # validation logger
logger_val.info(
'<epoch:{:3d}, iter:{:8,d}> psnr: {:.4e}'.format(
epoch, current_step, avg_psnr))
# tensorboard logger
tb_logger_valid.add_scalar('loss/psnr', avg_psnr, current_step)
tb_logger_valid.add_scalar('loss/nll', avg_nll, current_step)
tb_logger_train.flush()
tb_logger_valid.flush()
#### save models and training states
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
if rank <= 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
timerData.tick()
with open(os.path.join(opt['path']['root'], "TRAIN_DONE"), 'w') as f:
f.write("TRAIN_DONE")
if rank <= 0:
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to option JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=True)
# Convert to NoneDict, which return None for missing key.
opt = option.dict_to_nonedict(opt)
pytorch_ver = get_pytorch_ver()
# train from scratch OR resume training
if opt['path']['resume_state']:
if os.path.isdir(opt['path']['resume_state']):
import glob
resume_state_path = util.sorted_nicely(
glob.glob(
os.path.normpath(opt['path']['resume_state']) +
'/*.state'))[-1]
else:
resume_state_path = opt['path']['resume_state']
resume_state = torch.load(resume_state_path)
else: # training from scratch
resume_state = None
# rename old folder if exists
util.mkdir_and_rename(opt['path']['experiments_root'])
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger(None,
opt['path']['log'],
'train',
level=logging.INFO,
screen=True)
util.setup_logger('val', opt['path']['log'], 'val', level=logging.INFO)
logger = logging.getLogger('base')
if resume_state:
logger.info('Set [resume_state] to ' + resume_state_path)
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
option.check_resume(opt) # check resume options
logger.info(option.dict2str(opt))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
from tensorboardX import SummaryWriter
try:
# for version tensorboardX >= 1.7
tb_logger = SummaryWriter(logdir='../tb_logger/' + opt['name'])
except:
# for version tensorboardX < 1.6
tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt['name'])
# random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benckmark = True
# torch.backends.cudnn.deterministic = True
# create train and val dataloader
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
logger.info('Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
train_loader = create_dataloader(train_set, dataset_opt)
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt)
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
# create model
model = create_model(opt)
# resume training
if resume_state:
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
# updated schedulers in case JSON configuration has changed
model.update_schedulers(opt['train'])
else:
current_step = 0
start_epoch = 0
# training
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs):
for n, train_data in enumerate(train_loader, start=1):
current_step += 1
if current_step > total_iters:
break
if pytorch_ver == "pre": # Order for PyTorch ver < 1.1.0
# update learning rate
model.update_learning_rate(current_step - 1)
# training
model.feed_data(train_data)
model.optimize_parameters(current_step)
elif pytorch_ver == "post": # Order for PyTorch ver > 1.1.0
# training
model.feed_data(train_data)
model.optimize_parameters(current_step)
# update learning rate
model.update_learning_rate(current_step - 1)
else:
print('Error identifying PyTorch version. ', torch.__version__)
break
# log
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
epoch, current_step, model.get_current_learning_rate())
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar(k, v, current_step)
logger.info(message)
# save models and training states (changed to save models before validation)
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
model.save(current_step)
model.save_training_state(epoch + (n >= len(train_loader)),
current_step)
logger.info('Models and training states saved.')
# validation
if current_step % opt['train']['val_freq'] == 0:
avg_psnr = 0.0
avg_ssim = 0.0
avg_lpips = 0.0
idx = 0
val_sr_imgs_list = []
val_gt_imgs_list = []
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data['LR_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'], img_name)
util.mkdir(img_dir)
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
if opt['datasets']['train'][
'znorm']: # If the image range is [-1,1]
sr_img = util.tensor2img(visuals['SR'],
min_max=(-1, 1)) # uint8
gt_img = util.tensor2img(visuals['HR'],
min_max=(-1, 1)) # uint8
else: # Default: Image range is [0,1]
sr_img = util.tensor2img(visuals['SR']) # uint8
gt_img = util.tensor2img(visuals['HR']) # uint8
# sr_img = util.tensor2img(visuals['SR']) # uint8
# gt_img = util.tensor2img(visuals['HR']) # uint8
# print("Min. SR value:",sr_img.min()) # Debug
# print("Max. SR value:",sr_img.max()) # Debug
# print("Min. GT value:",gt_img.min()) # Debug
# print("Max. GT value:",gt_img.max()) # Debug
# Save SR images for reference
save_img_path = os.path.join(
img_dir,
'{:s}_{:d}.png'.format(img_name, current_step))
util.save_img(sr_img, save_img_path)
# calculate PSNR, SSIM and LPIPS distance
crop_size = opt['scale']
gt_img = gt_img / 255.
sr_img = sr_img / 255.
# For training models with only one channel ndim==2, if RGB ndim==3, etc.
if gt_img.ndim == 2:
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size]
else:
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size, :]
if sr_img.ndim == 2:
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size]
else: # Default: RGB images
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size, :]
# If calculating only once for all images
val_gt_imgs_list.append(cropped_gt_img)
# If calculating only once for all images
val_sr_imgs_list.append(cropped_sr_img)
# LPIPS only works for RGB images
avg_psnr += util.calculate_psnr(cropped_sr_img * 255,
cropped_gt_img * 255)
avg_ssim += util.calculate_ssim(cropped_sr_img * 255,
cropped_gt_img * 255)
# If calculating for each image
# avg_lpips += lpips.calculate_lpips([cropped_sr_img], [cropped_gt_img])
avg_psnr = avg_psnr / idx
avg_ssim = avg_ssim / idx
# avg_lpips=avg_lpips / idx # If calculating for each image
# If calculating only once for all images
avg_lpips = lpips.calculate_lpips(val_sr_imgs_list,
val_gt_imgs_list)
# log
# logger.info('# Validation # PSNR: {:.5g}, SSIM: {:.5g}'.format(avg_psnr, avg_ssim))
logger.info(
'# Validation # PSNR: {:.5g}, SSIM: {:.5g}, LPIPS: {:.5g}'.
format(avg_psnr, avg_ssim, avg_lpips))
logger_val = logging.getLogger('val') # validation logger
# logger_val.info('<epoch:{:3d}, iter:{:8,d}> psnr: {:.5g}, ssim: {:.5g}'.format(
# epoch, current_step, avg_psnr, avg_ssim))
logger_val.info(
'<epoch:{:3d}, iter:{:8,d}> psnr: {:.5g}, ssim: {:.5g}, lpips: {:.5g}'
.format(epoch, current_step, avg_psnr, avg_ssim,
avg_lpips))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr', avg_psnr, current_step)
tb_logger.add_scalar('ssim', avg_ssim, current_step)
tb_logger.add_scalar('lpips', avg_lpips, current_step)
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
def main():
PreUp = False
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, required=True, help='Path to option JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=True)
opt = option.dict_to_nonedict(opt) # Convert to NoneDict, which return None for missing key.
ratio = opt["scale"]
if PreUp == True:
ratio=5
# train from scratch OR resume training
if opt['path']['resume_state']: # resuming training
resume_state = torch.load(opt['path']['resume_state'])
else: # training from scratch
resume_state = None
util.mkdir_and_rename(opt['path']['experiments_root']) # rename old folder if exists
util.mkdirs((path for key, path in opt['path'].items() if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger(None, opt['path']['log'], 'train', level=logging.INFO, screen=True)
util.setup_logger('val', opt['path']['log'], 'val', level=logging.INFO)
logger = logging.getLogger('base')
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
option.check_resume(opt) # check resume options
logger.info(option.dict2str(opt))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
from tensorboardX import SummaryWriter
tb_logger_train = SummaryWriter(log_dir='/mnt/gpid07/users/luis.salgueiro/git/mnt/BasicSR/tb_logger/' + opt['name'] + "/train")
tb_logger_val = SummaryWriter(log_dir='//mnt/gpid07/users/luis.salgueiro/git/mnt/BasicSR/tb_logger/' + opt['name'] + "/val" )
# random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = 100 #random.randint(1, 10000)
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benckmark = True
# torch.backends.cudnn.deterministic = True
# print("OLAAAA_-...", os.environ['CUDA_VISIBLE_DEVICES'])
# #########################################
# ######## DATA LOADER ####################
# #########################################
# create train and val dataloader
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
print("Entro DATASET train......")
train_set = create_dataset(dataset_opt)
print("CREO DATASET train_set ", train_set)
train_size = int(math.ceil(len(train_set) / dataset_opt['batch_size']))
logger.info('Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
train_loader = create_dataloader(train_set, dataset_opt)
print("CREO train loader: ", train_loader)
elif phase == 'val':
print("Entro en phase VAL....")
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt)
logger.info('Number of val images in [{:s}]: {:d}'.format(dataset_opt['name'],
len(val_set)))
# for _,ii in enumerate(val_loader):
# print("VAL LOADER:........", ii)
# print(val_loader[0])
else:
raise NotImplementedError('Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
assert val_loader is not None
# create model
model = create_model(opt)
#print("PASO..... MODEL ")
# resume training
if resume_state:
print("RESUMING state")
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
print("PASO..... INIT ")
# #########################################
# ######### training ################
# #########################################
# ii=0
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(start_epoch, current_step))
for epoch in range(start_epoch, total_epochs):
# print("Entro EPOCH...", ii)
for _, train_data in enumerate(train_loader):
# print("Entro TRAIN_LOADER...")
current_step += 1
if current_step > total_iters:
break
# update learning rate
model.update_learning_rate()
# training
#print("....... TRAIN DATA..........", train_data)
model.feed_data(train_data)
model.optimize_parameters(current_step)
# log train
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
epoch, current_step, model.get_current_learning_rate())
# print(".............MESSAGE: ", message)
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
#print("MSG: ", message)
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
# print("K: ", k)
# print("V: ", v)
if "test" in k:
tb_logger_val.add_scalar(k, v, current_step)
else:
tb_logger_train.add_scalar(k, v, current_step)
logger.info(message)
if current_step % opt['train']['val_freq'] == 0:
avg_psnr_sr = 0.0
avg_psnr_lr = 0.0
avg_psnr_dif = 0.0
avg_ssim_lr, avg_ssim_sr, avg_ssim_dif = 0.0, 0.0, 0.0
avg_ergas_lr, avg_ergas_sr, avg_ergas_dif = 0.0, 0.0, 0.0
idx = 0
# for val_data in val_loader:
for _, val_data in enumerate(val_loader):
idx += 1
img_name = os.path.splitext(os.path.basename(val_data['LR_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'], img_name)
# print("Img nameVaL: ", img_name)
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2imgNorm(visuals['SR'],out_type=np.uint8, min_max=(0, 1), MinVal=val_data["LR_min"], MaxVal=val_data["LR_max"]) # uint16
gt_img = util.tensor2imgNorm(visuals['HR'],out_type=np.uint8, min_max=(0, 1), MinVal=val_data["HR_min"], MaxVal=val_data["HR_max"]) # uint16
lr_img = util.tensor2imgNorm(visuals['LR'], out_type=np.uint8, min_max=(0, 1),
MinVal=val_data["LR_min"], MaxVal=val_data["LR_max"]) # uint16
# Save SR images for reference
if idx < 10:
# print(idx)
util.mkdir(img_dir)
save_img_path = os.path.join(img_dir, '{:s}_{:d}'.format(img_name, current_step))
util.save_imgSR(sr_img, save_img_path)
util.save_imgHR(gt_img, save_img_path)
util.save_imgLR(lr_img, save_img_path)
print("SAVING CROPS")
util.save_imgCROP(lr_img,gt_img,sr_img , save_img_path, ratio, PreUp=PreUp)
if PreUp==False:
dim2 = (gt_img.shape[1], gt_img.shape[1])
print("DIM:", dim2)
print("LR image shape ", lr_img.shape)
print("HR image shape ", gt_img.shape)
lr_img = cv2.resize(np.transpose(lr_img,(1,2,0)), dim2, interpolation=cv2.INTER_NEAREST)
lr_img = np.transpose(lr_img,(2,0,1))
print("LR image 2 shape ", lr_img.shape)
print("LR image 2 shape ", lr_img.shape)
avg_psnr_sr += util.calculate_psnr2(sr_img, gt_img)
avg_psnr_lr += util.calculate_psnr2(lr_img, gt_img)
avg_ssim_lr += util.calculate_ssim2(lr_img, gt_img)
avg_ssim_sr += util.calculate_ssim2(sr_img, gt_img)
avg_ergas_lr += util.calculate_ergas(lr_img, gt_img, pixratio=ratio)
avg_ergas_sr += util.calculate_ergas(sr_img, gt_img, pixratio=ratio)
#avg_psnr += util.calculate_psnr2(cropped_sr_img, cropped_gt_img)
avg_psnr_sr = avg_psnr_sr / idx
avg_psnr_lr = avg_psnr_lr / idx
avg_psnr_dif = avg_psnr_lr - avg_psnr_sr
avg_ssim_lr = avg_ssim_lr / idx
avg_ssim_sr = avg_ssim_sr / idx
avg_ssim_dif = avg_ssim_lr - avg_ssim_sr
avg_ergas_lr = avg_ergas_lr / idx
avg_ergas_sr = avg_ergas_sr / idx
avg_ergas_dif = avg_ergas_lr - avg_ergas_sr
# print("IDX: ", idx)
# log VALIDATION
logger.info('# Validation # PSNR: {:.4e}'.format(avg_psnr_sr))
logger.info('# Validation # SSIM: {:.4e}'.format(avg_ssim_sr))
logger.info('# Validation # ERGAS: {:.4e}'.format(avg_ergas_sr))
logger_val = logging.getLogger('val') # validation logger
logger_val.info('<epoch:{:3d}, iter:{:8,d}> psnr_SR: {:.4e}'.format(
epoch, current_step, avg_psnr_sr))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> psnr_LR: {:.4e}'.format(
epoch, current_step, avg_psnr_lr))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> psnr_DIF: {:.4e}'.format(
epoch, current_step, avg_psnr_dif))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> ssim_LR: {:.4e}'.format(
epoch, current_step, avg_ssim_lr))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> ssim_SR: {:.4e}'.format(
epoch, current_step, avg_ssim_sr))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> ssim_DIF: {:.4e}'.format(
epoch, current_step, avg_ssim_dif))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> ergas_LR: {:.4e}'.format(
epoch, current_step, avg_ergas_lr))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> ergas_SR: {:.4e}'.format(
epoch, current_step, avg_ergas_sr))
logger_val.info('<epoch:{:3d}, iter:{:8,d}> ergas_DIF: {:.4e}'.format(
epoch, current_step, avg_ergas_dif))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger_val.add_scalar('dif_PSNR', avg_psnr_dif, current_step)
# tb_logger.add_scalar('psnr', avg_psnr, current_step)
tb_logger_val.add_scalar('dif_SSIM', avg_ssim_dif, current_step)
tb_logger_val.add_scalar('dif_ERGAS', avg_ergas_dif, current_step)
tb_logger_val.add_scalar('psnr_LR', avg_psnr_lr, current_step)
# tb_logger.add_scalar('psnr', avg_psnr, current_step)
tb_logger_val.add_scalar('ssim_LR', avg_ssim_lr, current_step)
tb_logger_val.add_scalar('ERGAS_LR', avg_ergas_lr, current_step)
tb_logger_val.add_scalar('psnr_SR', avg_psnr_sr, current_step)
# tb_logger.add_scalar('psnr', avg_psnr, current_step)
tb_logger_val.add_scalar('ssim_SR', avg_ssim_sr, current_step)
tb_logger_val.add_scalar('ERGAS_SR', avg_ergas_sr, current_step)
print("****** SR_IMG: ", sr_img.shape)
print("****** LR_IMG: ", lr_img.shape)
print("****** GT_IMG: ", gt_img.shape)
fig1,ax1 = ep.plot_rgb(sr_img, rgb=[2, 1, 0], stretch=True)
tb_logger_val.add_figure("SR_plt", fig1, current_step,close=True)
fig2, ax2 = ep.plot_rgb(gt_img, rgb=[2, 1, 0], stretch=True)
tb_logger_val.add_figure("GT_plt", fig2, current_step, close=True)
fig3, ax3 = ep.plot_rgb(lr_img, rgb=[2, 1, 0], stretch=True)
tb_logger_val.add_figure("LR_plt", fig3, current_step, close=True)
# print("TERMINO GUARDAR IMG TB")
# save models and training states
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
# ii=ii+1
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
def main():
#### options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
default='options/train/train_EDVR_woTSA_M.yml',
help='Path to option YAML file.')
parser.add_argument('--set',
dest='set_opt',
default=None,
nargs=argparse.REMAINDER,
help='set options')
args = parser.parse_args()
opt = option.parse(args.opt, args.set_opt, is_train=True)
#### loading resume state if exists
if opt['path'].get('resume_state', None):
# distributed resuming: all load into default GPU
print('Training from state: {}'.format(opt['path']['resume_state']))
device_id = torch.cuda.current_device()
resume_state = torch.load(
opt['path']['resume_state'],
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt, resume_state['iter']) # check resume options
elif opt['auto_resume']:
exp_dir = opt['path']['experiments_root']
# first time run: create dirs
if not os.path.exists(exp_dir):
os.makedirs(exp_dir)
os.makedirs(opt['path']['models'])
os.makedirs(opt['path']['training_state'])
os.makedirs(opt['path']['val_images'])
os.makedirs(opt['path']['tb_logger'])
resume_state = None
else:
# detect experiment directory and get the latest state
state_dir = opt['path']['training_state']
state_files = [
x for x in os.listdir(state_dir) if x.endswith('state')
]
# no valid state detected
if len(state_files) < 1:
print(
'No previous training state found, train from start state')
resume_state = None
else:
state_files = sorted(state_files,
key=lambda x: int(x.split('.')[0]))
latest_state = state_files[-1]
print('Training from lastest state: {}'.format(latest_state))
latest_state_file = os.path.join(state_dir, latest_state)
opt['path']['resume_state'] = latest_state_file
device_id = torch.cuda.current_device()
resume_state = torch.load(
latest_state_file,
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt, resume_state['iter'])
else:
resume_state = None
if resume_state is None and not opt['auto_resume'] and not opt['no_log']:
util.mkdir_and_rename(
opt['path']
['experiments_root']) # rename experiment folder if exists
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'experiments_root'
and 'pretrain_model' not in key and 'resume' not in key))
# config loggers. Before it, the log will not work
util.setup_logger('base',
opt['path']['log'],
'train_' + opt['name'],
level=logging.INFO,
screen=True,
tofile=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
version = float(torch.__version__[0:3])
if version >= 1.2: # PyTorch 1.1
from torch.utils.tensorboard import SummaryWriter
else:
logger.info(
'You are using PyTorch {}. Tensorboard will use [tensorboardX]'
.format(version))
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir=opt['path']['tb_logger'])
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
#### random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
logger.info('Random seed: {}'.format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
#### create train and val dataloader
if opt['datasets']['train']['ratio']:
dataset_ratio = opt['datasets']['train']['ratio']
else:
dataset_ratio = 200 # enlarge the size of each epoch
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
total_iters = int(opt['train']['niter'])
total_epochs = int(
math.ceil(total_iters / (train_size * dataset_ratio)))
if dataset_opt['mode'] in ['MetaREDS', 'MetaREDSOnline']:
train_sampler = MetaIterSampler(train_set,
dataset_opt['batch_size'],
len(opt['scale']),
dataset_ratio)
elif dataset_opt['mode'] in ['REDS', 'MultiREDS']:
train_sampler = IterSampler(train_set,
dataset_opt['batch_size'],
dataset_ratio)
else:
train_sampler = None
train_loader = create_dataloader(train_set, dataset_opt, opt,
train_sampler)
logger.info('Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt, opt, None)
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
#### create model
model = create_model(opt)
#### resume training
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
#### training
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs + 1):
train_sampler.set_epoch(epoch)
for _, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
#### update learning rate
model.update_learning_rate(current_step,
warmup_iter=opt['train']['warmup_iter'])
#### training
model.feed_data(train_data)
model.optimize_parameters(current_step)
#### log
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '[epoch:{:3d}, iter:{:8,d}, lr:('.format(
epoch, current_step)
for v in model.get_current_learning_rate():
message += '{:.3e},'.format(v)
message += ')] '
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar(k, v, current_step)
logger.info(message)
print("PROGRESS: {:02d}%".format(
int(current_step / total_iters * 100)))
#### validation
if opt['datasets'].get(
'val',
None) and current_step % opt['train']['val_freq'] == 0:
pbar = util.ProgressBar(len(val_loader))
psnr_rlt = {} # with border and center frames
psnr_rlt_avg = {}
psnr_total_avg = 0.
for val_data in val_loader:
folder = val_data['folder'][0]
idx_d = val_data['idx'].item()
# border = val_data['border'].item()
if psnr_rlt.get(folder, None) is None:
psnr_rlt[folder] = []
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
rlt_img = util.tensor2img(visuals['rlt']) # uint8
gt_img = util.tensor2img(visuals['GT']) # uint8
# calculate PSNR
psnr = util.calculate_psnr(rlt_img, gt_img)
psnr_rlt[folder].append(psnr)
pbar.update('Test {} - {}'.format(folder, idx_d))
for k, v in psnr_rlt.items():
psnr_rlt_avg[k] = sum(v) / len(v)
psnr_total_avg += psnr_rlt_avg[k]
psnr_total_avg /= len(psnr_rlt)
log_s = '# Validation # PSNR: {:.4e}:'.format(psnr_total_avg)
for k, v in psnr_rlt_avg.items():
log_s += ' {}: {:.4e}'.format(k, v)
logger.info(log_s)
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr_avg', psnr_total_avg,
current_step)
for k, v in psnr_rlt_avg.items():
tb_logger.add_scalar(k, v, current_step)
#### save models and training states
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
tb_logger.close()
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument("-opt", type=str, help="Path to option YAML file.")
parser.add_argument("--launcher",
choices=["none", "pytorch"],
default="none",
help="job launcher")
parser.add_argument("--local_rank", type=int, default=0)
args = parser.parse_args()
opt = option.parse(args.opt, is_train=True)
# distributed training settings
if args.launcher == "none": # disabled distributed training
opt["dist"] = False
rank = -1
print("Disabled distributed training.")
else:
opt["dist"] = True
init_dist()
world_size = torch.distributed.get_world_size()
rank = torch.distributed.get_rank()
# loading resume state if exists
if opt["path"].get("resume_state", None):
# distributed resuming: all load into default GPU
device_id = torch.cuda.current_device()
resume_state = torch.load(
opt["path"]["resume_state"],
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt, resume_state["iter"]) # check resume options
else:
resume_state = None
# mkdir and loggers
if rank <= 0: # normal training (rank -1) OR distributed training (rank 0)
if resume_state is None:
util.mkdir_and_rename(
opt["path"]
["experiments_root"]) # rename experiment folder if exists
util.mkdirs(
(path for key, path in opt["path"].items()
if not key == "experiments_root"
and "pretrain_model" not in key and "resume" not in key))
# config loggers. Before it, the log will not work
util.setup_logger("base",
opt["path"]["log"],
"train_" + opt["name"],
level=logging.INFO,
screen=True,
tofile=True)
logger = logging.getLogger("base")
logger.info(option.dict2str(opt))
# tensorboard logger
if opt["use_tb_logger"] and "debug" not in opt["name"]:
version = float(torch.__version__[0:3])
if version >= 1.1: # PyTorch 1.1
from torch.utils.tensorboard import SummaryWriter
else:
logger.info("You are using PyTorch {}. \
Tensorboard will use [tensorboardX]".format(
version))
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir="../tb_logger/" + opt["name"])
else:
util.setup_logger("base",
opt["path"]["log"],
"train",
level=logging.INFO,
screen=True)
logger = logging.getLogger("base")
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
# random seed
seed = opt["train"]["manual_seed"]
if seed is None:
seed = random.randint(1, 10000)
if rank <= 0:
logger.info("Random seed: {}".format(seed))
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
# create train and val dataloader
dataset_ratio = 200 # enlarge the size of each epoch
for phase, dataset_opt in opt["datasets"].items():
if phase == "train":
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt["batch_size"]))
total_iters = int(opt["train"]["niter"])
total_epochs = int(math.ceil(total_iters / train_size))
if opt["dist"]:
train_sampler = DistIterSampler(train_set, world_size, rank,
dataset_ratio)
total_epochs = int(
math.ceil(total_iters / (train_size * dataset_ratio)))
else:
train_sampler = None
train_loader = create_dataloader(train_set, dataset_opt, opt,
train_sampler)
if rank <= 0:
logger.info(
"Number of train images: {:,d}, iters: {:,d}".format(
len(train_set), train_size))
logger.info("Total epochs needed: {:d} for iters {:,d}".format(
total_epochs, total_iters))
elif phase == "val":
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt, opt, None)
if rank <= 0:
logger.info("Number of val images in [{:s}]: {:d}".format(
dataset_opt["name"], len(val_set)))
else:
raise NotImplementedError(
"Phase [{:s}] is not recognized.".format(phase))
assert train_loader is not None
# create model
model = create_model(opt)
print("Model created!")
# resume training
if resume_state:
logger.info("Resuming training from epoch: {}, iter: {}.".format(
resume_state["epoch"], resume_state["iter"]))
start_epoch = resume_state["epoch"]
current_step = resume_state["iter"]
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
# training
logger.info("Start training from epoch: {:d}, iter: {:d}".format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs + 1):
if opt["dist"]:
train_sampler.set_epoch(epoch)
for _, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
# update learning rate
model.update_learning_rate(current_step,
warmup_iter=opt["train"]["warmup_iter"])
# training
model.feed_data(train_data)
model.optimize_parameters(current_step)
# log
if current_step % opt["logger"]["print_freq"] == 0:
logs = model.get_current_log()
message = "[epoch:{:3d}, iter:{:8,d}, lr:(".format(
epoch, current_step)
for v in model.get_current_learning_rate():
message += "{:.3e},".format(v)
message += ")] "
for k, v in logs.items():
message += "{:s}: {:.4e} ".format(k, v)
# tensorboard logger
if opt["use_tb_logger"] and "debug" not in opt["name"]:
if rank <= 0:
tb_logger.add_scalar(k, v, current_step)
if rank <= 0:
logger.info(message)
# validation
if opt["datasets"].get(
"val",
None) and current_step % opt["train"]["val_freq"] == 0:
# image restoration validation
if opt["model"] in ["sr", "srgan"] and rank <= 0:
# does not support multi-GPU validation
pbar = util.ProgressBar(len(val_loader))
avg_psnr = 0.0
idx = 0
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data["LQ_path"][0]))[0]
img_dir = os.path.join(opt["path"]["val_images"],
img_name)
util.mkdir(img_dir)
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2img(visuals["rlt"]) # uint8
gt_img = util.tensor2img(visuals["GT"]) # uint8
# Save SR images for reference
save_img_path = os.path.join(
img_dir,
"{:s}_{:d}.png".format(img_name, current_step))
util.save_img(sr_img, save_img_path)
# calculate PSNR
sr_img, gt_img = util.crop_border([sr_img, gt_img],
opt["scale"])
avg_psnr += util.calculate_psnr(sr_img, gt_img)
pbar.update("Test {}".format(img_name))
avg_psnr = avg_psnr / idx
# log
logger.info("# Validation # PSNR: {:.4e}".format(avg_psnr))
# tensorboard logger
if opt["use_tb_logger"] and "debug" not in opt["name"]:
tb_logger.add_scalar("psnr", avg_psnr, current_step)
else: # video restoration validation
if opt["dist"]:
# multi-GPU testing
psnr_rlt = {} # with border and center frames
if rank == 0:
pbar = util.ProgressBar(len(val_set))
for idx in range(rank, len(val_set), world_size):
val_data = val_set[idx]
val_data["LQs"].unsqueeze_(0)
val_data["GT"].unsqueeze_(0)
folder = val_data["folder"]
idx_d, max_idx = val_data["idx"].split("/")
idx_d, max_idx = int(idx_d), int(max_idx)
if psnr_rlt.get(folder, None) is None:
psnr_rlt[folder] = torch.zeros(
max_idx,
dtype=torch.float32,
device="cuda")
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
rlt_img = util.tensor2img(visuals["rlt"]) # uint8
gt_img = util.tensor2img(visuals["GT"]) # uint8
# calculate PSNR
psnr_rlt[folder][idx_d] = util.calculate_psnr(
rlt_img, gt_img)
if rank == 0:
for _ in range(world_size):
pbar.update("Test {} - {}/{}".format(
folder, idx_d, max_idx))
# collect data
for _, v in psnr_rlt.items():
dist.reduce(v, 0)
dist.barrier()
if rank == 0:
psnr_rlt_avg = {}
psnr_total_avg = 0.0
for k, v in psnr_rlt.items():
psnr_rlt_avg[k] = torch.mean(v).cpu().item()
psnr_total_avg += psnr_rlt_avg[k]
psnr_total_avg /= len(psnr_rlt)
log_s = "# Validation # PSNR: {:.4e}:".format(
psnr_total_avg)
for k, v in psnr_rlt_avg.items():
log_s += " {}: {:.4e}".format(k, v)
logger.info(log_s)
if opt["use_tb_logger"] and "debug" not in opt[
"name"]:
tb_logger.add_scalar("psnr_avg",
psnr_total_avg,
current_step)
for k, v in psnr_rlt_avg.items():
tb_logger.add_scalar(k, v, current_step)
else:
pbar = util.ProgressBar(len(val_loader))
psnr_rlt = {} # with border and center frames
psnr_rlt_avg = {}
psnr_total_avg = 0.0
for val_data in val_loader:
folder = val_data["folder"][0]
idx_d, max_id = val_data["idx"][0].split("/")
# border = val_data['border'].item()
if psnr_rlt.get(folder, None) is None:
psnr_rlt[folder] = []
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
rlt_img = util.tensor2img(visuals["rlt"]) # uint8
gt_img = util.tensor2img(visuals["GT"]) # uint8
lq_img = util.tensor2img(visuals["LQ"][2]) # uint8
img_dir = opt["path"]["val_images"]
util.mkdir(img_dir)
save_img_path = os.path.join(
img_dir, "{}.png".format(idx_d))
util.save_img(np.hstack((lq_img, rlt_img, gt_img)),
save_img_path)
# calculate PSNR
psnr = util.calculate_psnr(rlt_img, gt_img)
psnr_rlt[folder].append(psnr)
pbar.update("Test {} - {}".format(folder, idx_d))
for k, v in psnr_rlt.items():
psnr_rlt_avg[k] = sum(v) / len(v)
psnr_total_avg += psnr_rlt_avg[k]
psnr_total_avg /= len(psnr_rlt)
log_s = "# Validation # PSNR: {:.4e}:".format(
psnr_total_avg)
for k, v in psnr_rlt_avg.items():
log_s += " {}: {:.4e}".format(k, v)
logger.info(log_s)
if opt["use_tb_logger"] and "debug" not in opt["name"]:
tb_logger.add_scalar("psnr_avg", psnr_total_avg,
current_step)
for k, v in psnr_rlt_avg.items():
tb_logger.add_scalar(k, v, current_step)
# save models and training states
if current_step % opt["logger"]["save_checkpoint_freq"] == 0:
if rank <= 0:
logger.info("Saving models and training states.")
model.save(current_step)
model.save_training_state(epoch, current_step)
if rank <= 0:
logger.info("Saving the final model.")
model.save("latest")
logger.info("End of training.")
tb_logger.close()
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to option JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=True)
util.mkdir_and_rename(
opt['path']['experiments_root']) # rename old experiments if exists
util.mkdirs((path for key, path in opt['path'].items() if not key == 'experiments_root' and \
not key == 'pretrain_model_G' and not key == 'pretrain_model_D'))
option.save(opt)
opt = option.dict_to_nonedict(
opt) # Convert to NoneDict, which return None for missing key.
# print to file and std_out simultaneously
sys.stdout = PrintLogger(opt['path']['log'])
# random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
print("Random Seed: ", seed)
random.seed(seed)
torch.manual_seed(seed)
# create train and val dataloader
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
print('Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
total_iters = int(opt['train']['niter'])
total_epoches = int(math.ceil(total_iters / train_size))
print('Total epoches needed: {:d} for iters {:,d}'.format(
total_epoches, total_iters))
train_loader = create_dataloader(train_set, dataset_opt)
elif phase == 'val':
val_dataset_opt = dataset_opt
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt)
print('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
# Create model
model = create_model(opt)
# create logger
logger = Logger(opt)
current_step = 0
start_time = time.time()
print('---------- Start training -------------')
for epoch in range(total_epoches):
for i, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
# training
model.feed_data(train_data)
model.optimize_parameters(current_step)
time_elapsed = time.time() - start_time
start_time = time.time()
# log
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
print_rlt = OrderedDict()
print_rlt['model'] = opt['model']
print_rlt['epoch'] = epoch
print_rlt['iters'] = current_step
print_rlt['time'] = time_elapsed
for k, v in logs.items():
print_rlt[k] = v
print_rlt['lr'] = model.get_current_learning_rate()
logger.print_format_results('train', print_rlt)
# save models
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
print('Saving the model at the end of iter {:d}.'.format(
current_step))
model.save(current_step)
# validation
if current_step % opt['train']['val_freq'] == 0:
print('---------- validation -------------')
start_time = time.time()
avg_psnr = 0.0
idx = 0
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data['LR_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'], img_name)
util.mkdir(img_dir)
model.feed_data(val_data)
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2img(visuals['SR']) # uint8
gt_img = util.tensor2img(visuals['HR']) # uint8
# Save SR images for reference
save_img_path = os.path.join(img_dir, '{:s}_{:d}.png'.format(\
img_name, current_step))
util.save_img(sr_img, save_img_path)
# calculate PSNR
if opt['crop_scale'] is not None:
crop_size = opt['crop_scale']
else:
crop_size = opt['scale']
if crop_size <= 0:
cropped_sr_img = sr_img.copy()
cropped_gt_img = gt_img.copy()
else:
if len(gt_img.shape) < 3:
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size]
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size]
else:
cropped_sr_img = sr_img[crop_size:-crop_size,
crop_size:-crop_size, :]
cropped_gt_img = gt_img[crop_size:-crop_size,
crop_size:-crop_size, :]
#avg_psnr += util.psnr(cropped_sr_img, cropped_gt_img)
cropped_sr_img_y = bgr2ycbcr(cropped_sr_img, only_y=True)
cropped_gt_img_y = bgr2ycbcr(cropped_gt_img, only_y=True)
avg_psnr += util.psnr(
cropped_sr_img_y,
cropped_gt_img_y) ##########only y channel
avg_psnr = avg_psnr / idx
time_elapsed = time.time() - start_time
# Save to log
print_rlt = OrderedDict()
print_rlt['model'] = opt['model']
print_rlt['epoch'] = epoch
print_rlt['iters'] = current_step
print_rlt['time'] = time_elapsed
print_rlt['psnr'] = avg_psnr
logger.print_format_results('val', print_rlt)
print('-----------------------------------')
# update learning rate
model.update_learning_rate()
print('Saving the final model.')
model.save('latest')
print('End of training.')
def main():
#### options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, help='Path to option YAML file.')
parser.add_argument('--launcher',
choices=['none', 'pytorch'],
default='none',
help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
opt = option.parse(args.opt, is_train=True)
#### distributed training settings
if args.launcher == 'none': # disabled distributed training
opt['dist'] = False
rank = -1
print('Disabled distributed training.')
else:
opt['dist'] = True
init_dist()
world_size = torch.distributed.get_world_size()
rank = torch.distributed.get_rank()
#### loading resume state if exists
if opt['path'].get('resume_state', None):
# distributed resuming: all load into default GPU
device_id = torch.cuda.current_device()
resume_state = torch.load(
opt['path']['resume_state'],
map_location=lambda storage, loc: storage.cuda(device_id))
option.check_resume(opt, resume_state['iter']) # check resume options
else:
resume_state = None
#### mkdir and loggers
if rank <= 0: # normal training (rank -1) OR distributed training (rank 0)
if resume_state is None:
util.mkdir_and_rename(
opt['path']
['experiments_root']) # rename experiment folder if exists
util.mkdirs(
(path for key, path in opt['path'].items() if
not key == 'experiments_root' and 'pretrain_model' not in key
and 'resume' not in key and 'wandb_load_run_path' not in key))
# config loggers. Before it, the log will not work
util.setup_logger('base',
opt['path']['log'],
'train_' + opt['name'],
level=logging.INFO,
screen=True,
tofile=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
version = float(torch.__version__[0:3])
if version >= 1.1: # PyTorch 1.1
from torch.utils.tensorboard import SummaryWriter
else:
logger.info(
'You are using PyTorch {}. Tensorboard will use [tensorboardX]'
.format(version))
from tensorboardX import SummaryWriter
tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt['name'])
if opt['use_wandb_logger'] and 'debug' not in opt['name']:
json_path = os.path.join(os.path.expanduser('~'),
'.wandb_api_keys.json')
if os.path.exists(json_path):
with open(json_path, 'r') as j:
json_file = json.loads(j.read())
os.environ['WANDB_API_KEY'] = json_file['ryul99']
wandb.init(project="mmsr", config=opt, sync_tensorboard=True)
else:
util.setup_logger('base',
opt['path']['log'],
'train',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
#### random seed
seed = opt['train']['manual_seed']
if seed is None:
seed = random.randint(1, 10000)
if rank <= 0:
logger.info('Random seed: {}'.format(seed))
if opt['use_wandb_logger'] and 'debug' not in opt['name']:
wandb.config.update({'random_seed': seed})
util.set_random_seed(seed)
torch.backends.cudnn.benchmark = True
# torch.backends.cudnn.deterministic = True
#### create train and val dataloader
dataset_ratio = 200 # enlarge the size of each epoch
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)
train_size = int(
math.ceil(len(train_set) / dataset_opt['batch_size']))
total_iters = int(opt['train']['niter'])
total_epochs = int(math.ceil(total_iters / train_size))
if opt['dist']:
train_sampler = DistIterSampler(train_set, world_size, rank,
dataset_ratio)
total_epochs = int(
math.ceil(total_iters / (train_size * dataset_ratio)))
else:
train_sampler = None
train_loader = create_dataloader(train_set, dataset_opt, opt,
train_sampler)
if rank <= 0:
logger.info(
'Number of train images: {:,d}, iters: {:,d}'.format(
len(train_set), train_size))
logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
total_epochs, total_iters))
elif phase == 'val':
val_set = create_dataset(dataset_opt)
val_loader = create_dataloader(val_set, dataset_opt, opt, None)
if rank <= 0:
logger.info('Number of val images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(val_set)))
else:
raise NotImplementedError(
'Phase [{:s}] is not recognized.'.format(phase))
assert train_loader is not None
#### create model
model = create_model(opt)
#### resume training
if resume_state:
logger.info('Resuming training from epoch: {}, iter: {}.'.format(
resume_state['epoch'], resume_state['iter']))
start_epoch = resume_state['epoch']
current_step = resume_state['iter']
model.resume_training(resume_state) # handle optimizers and schedulers
else:
current_step = 0
start_epoch = 0
#### training
logger.info('Start training from epoch: {:d}, iter: {:d}'.format(
start_epoch, current_step))
for epoch in range(start_epoch, total_epochs + 1):
if opt['dist']:
train_sampler.set_epoch(epoch)
for _, train_data in enumerate(train_loader):
current_step += 1
if current_step > total_iters:
break
#### update learning rate
model.update_learning_rate(current_step,
warmup_iter=opt['train']['warmup_iter'])
#### training
model.feed_data(train_data,
noise_mode=opt['datasets']['train']['noise_mode'],
noise_rate=opt['datasets']['train']['noise_rate'])
model.optimize_parameters(current_step)
#### log
if current_step % opt['logger']['print_freq'] == 0:
logs = model.get_current_log()
message = '[epoch:{:3d}, iter:{:8,d}, lr:('.format(
epoch, current_step)
for v in model.get_current_learning_rate():
message += '{:.3e},'.format(v)
message += ')] '
for k, v in logs.items():
message += '{:s}: {:.4e} '.format(k, v)
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
if rank <= 0:
tb_logger.add_scalar(k, v, current_step)
if opt['use_wandb_logger'] and 'debug' not in opt['name']:
if rank <= 0:
wandb.log({k: v}, step=current_step)
if rank <= 0:
logger.info(message)
#### validation
if opt['datasets'].get(
'val',
None) and current_step % opt['train']['val_freq'] == 0:
if opt['model'] in [
'sr', 'srgan'
] and rank <= 0: # image restoration validation
# does not support multi-GPU validation
pbar = util.ProgressBar(len(val_loader))
avg_psnr = 0.
idx = 0
for val_data in val_loader:
idx += 1
img_name = os.path.splitext(
os.path.basename(val_data['LQ_path'][0]))[0]
img_dir = os.path.join(opt['path']['val_images'],
img_name)
util.mkdir(img_dir)
model.feed_data(
val_data,
noise_mode=opt['datasets']['val']['noise_mode'],
noise_rate=opt['datasets']['val']['noise_rate'])
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2img(visuals['rlt']) # uint8
gt_img = util.tensor2img(visuals['GT']) # uint8
# Save SR images for reference
save_img_path = os.path.join(
img_dir,
'{:s}_{:d}.png'.format(img_name, current_step))
util.save_img(sr_img, save_img_path)
# calculate PSNR
sr_img, gt_img = util.crop_border([sr_img, gt_img],
opt['scale'])
avg_psnr += util.calculate_psnr(sr_img, gt_img)
pbar.update('Test {}'.format(img_name))
avg_psnr = avg_psnr / idx
# log
logger.info('# Validation # PSNR: {:.4e}'.format(avg_psnr))
# tensorboard logger
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr', avg_psnr, current_step)
if opt['use_wandb_logger'] and 'debug' not in opt['name']:
wandb.log({'psnr': avg_psnr}, step=current_step)
else: # video restoration validation
if opt['dist']:
# multi-GPU testing
psnr_rlt = {} # with border and center frames
if rank == 0:
pbar = util.ProgressBar(len(val_set))
for idx in range(rank, len(val_set), world_size):
val_data = val_set[idx]
val_data['LQs'].unsqueeze_(0)
val_data['GT'].unsqueeze_(0)
folder = val_data['folder']
idx_d, max_idx = val_data['idx'].split('/')
idx_d, max_idx = int(idx_d), int(max_idx)
if psnr_rlt.get(folder, None) is None:
psnr_rlt[folder] = torch.zeros(
max_idx,
dtype=torch.float32,
device='cuda')
# tmp = torch.zeros(max_idx, dtype=torch.float32, device='cuda')
model.feed_data(val_data,
noise_mode=opt['datasets']['val']
['noise_mode'],
noise_rate=opt['datasets']['val']
['noise_rate'])
model.test()
visuals = model.get_current_visuals()
rlt_img = util.tensor2img(visuals['rlt']) # uint8
gt_img = util.tensor2img(visuals['GT']) # uint8
# calculate PSNR
psnr_rlt[folder][idx_d] = util.calculate_psnr(
rlt_img, gt_img)
if rank == 0:
for _ in range(world_size):
pbar.update('Test {} - {}/{}'.format(
folder, idx_d, max_idx))
# # collect data
for _, v in psnr_rlt.items():
dist.reduce(v, 0)
dist.barrier()
if rank == 0:
psnr_rlt_avg = {}
psnr_total_avg = 0.
for k, v in psnr_rlt.items():
psnr_rlt_avg[k] = torch.mean(v).cpu().item()
psnr_total_avg += psnr_rlt_avg[k]
psnr_total_avg /= len(psnr_rlt)
log_s = '# Validation # PSNR: {:.4e}:'.format(
psnr_total_avg)
for k, v in psnr_rlt_avg.items():
log_s += ' {}: {:.4e}'.format(k, v)
logger.info(log_s)
if opt['use_tb_logger'] and 'debug' not in opt[
'name']:
tb_logger.add_scalar('psnr_avg',
psnr_total_avg,
current_step)
for k, v in psnr_rlt_avg.items():
tb_logger.add_scalar(k, v, current_step)
if opt['use_wandb_logger'] and 'debug' not in opt[
'name']:
lq_img, rlt_img, gt_img = map(
util.tensor2img, [
visuals['LQ'], visuals['rlt'],
visuals['GT']
])
wandb.log({'psnr_avg': psnr_total_avg},
step=current_step)
wandb.log(psnr_rlt_avg, step=current_step)
wandb.log(
{
'Validation Image': [
wandb.Image(lq_img[:, :,
[2, 1, 0]],
caption='LQ'),
wandb.Image(rlt_img[:, :,
[2, 1, 0]],
caption='output'),
wandb.Image(gt_img[:, :,
[2, 1, 0]],
caption='GT'),
]
},
step=current_step)
else:
pbar = util.ProgressBar(len(val_loader))
psnr_rlt = {} # with border and center frames
psnr_rlt_avg = {}
psnr_total_avg = 0.
for val_data in val_loader:
folder = val_data['folder'][0]
idx_d = val_data['idx'].item()
# border = val_data['border'].item()
if psnr_rlt.get(folder, None) is None:
psnr_rlt[folder] = []
model.feed_data(val_data,
noise_mode=opt['datasets']['val']
['noise_mode'],
noise_rate=opt['datasets']['val']
['noise_rate'])
model.test()
visuals = model.get_current_visuals()
rlt_img = util.tensor2img(visuals['rlt']) # uint8
gt_img = util.tensor2img(visuals['GT']) # uint8
# calculate PSNR
psnr = util.calculate_psnr(rlt_img, gt_img)
psnr_rlt[folder].append(psnr)
pbar.update('Test {} - {}'.format(folder, idx_d))
for k, v in psnr_rlt.items():
psnr_rlt_avg[k] = sum(v) / len(v)
psnr_total_avg += psnr_rlt_avg[k]
psnr_total_avg /= len(psnr_rlt)
log_s = '# Validation # PSNR: {:.4e}:'.format(
psnr_total_avg)
for k, v in psnr_rlt_avg.items():
log_s += ' {}: {:.4e}'.format(k, v)
logger.info(log_s)
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.add_scalar('psnr_avg', psnr_total_avg,
current_step)
for k, v in psnr_rlt_avg.items():
tb_logger.add_scalar(k, v, current_step)
if opt['use_wandb_logger'] and 'debug' not in opt[
'name']:
lq_img, rlt_img, gt_img = map(
util.tensor2img,
[visuals['LQ'], visuals['rlt'], visuals['GT']])
wandb.log({'psnr_avg': psnr_total_avg},
step=current_step)
wandb.log(psnr_rlt_avg, step=current_step)
wandb.log(
{
'Validation Image': [
wandb.Image(lq_img[:, :, [2, 1, 0]],
caption='LQ'),
wandb.Image(rlt_img[:, :, [2, 1, 0]],
caption='output'),
wandb.Image(gt_img[:, :, [2, 1, 0]],
caption='GT'),
]
},
step=current_step)
#### save models and training states
if current_step % opt['logger']['save_checkpoint_freq'] == 0:
if rank <= 0:
logger.info('Saving models and training states.')
model.save(current_step)
model.save_training_state(epoch, current_step)
if rank <= 0:
logger.info('Saving the final model.')
model.save('latest')
logger.info('End of training.')
if opt['use_tb_logger'] and 'debug' not in opt['name']:
tb_logger.close()
import utils.util as util
from data.util import bgr2ycbcr
from data import create_dataset, create_dataloader
from models import create_model
if __name__ == '__main__':
# options
parser = argparse.ArgumentParser()
parser.add_argument('--opt',
type=str,
default="options/test/test_ESRGAN.json",
help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=False)
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'pretrain_model_G'))
opt = option.dict_to_nonedict(opt)
util.setup_logger(None,
opt['path']['log'],
'test.log',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
# Create test dataset and dataloader
test_loaders = []
for phase, dataset_opt in sorted(opt['datasets'].items()):
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
logger.info('Number of test images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(test_set)))
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to options JSON file.')
opt = option.parse(parser.parse_args().opt, is_train=False)
util.mkdirs((path for key, path in opt['path'].items()
if not key == 'pretrain_model_G'))
opt = option.dict_to_nonedict(opt)
util.setup_logger(None,
opt['path']['log'],
'test.log',
level=logging.INFO,
screen=True)
logger = logging.getLogger('base')
logger.info(option.dict2str(opt))
scale = opt.get('scale', 4)
# Create test dataset and dataloader
test_loaders = []
znorm = False #TMP
# znorm_list = []
'''
video_list = os.listdir(cfg.testset_dir)
for idx_video in range(len(video_list)):
video_name = video_list[idx_video]
# dataloader
test_set = TestsetLoader(cfg, video_name)
test_loader = DataLoader(test_set, num_workers=1, batch_size=1, shuffle=False)
'''
for phase, dataset_opt in sorted(opt['datasets'].items()):
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt)
logger.info('Number of test images in [{:s}]: {:d}'.format(
dataset_opt['name'], len(test_set)))
test_loaders.append(test_loader)
# Temporary, will turn znorm on for all the datasets. Will need to introduce a variable for each dataset and differentiate each one later in the loop.
# if dataset_opt.get['znorm'] and znorm == False:
# znorm = True
znorm = dataset_opt.get('znorm', False)
# znorm_list.apped(znorm)
# Create model
model = create_model(opt)
for test_loader in test_loaders:
test_set_name = test_loader.dataset.opt['name']
logger.info('\nTesting [{:s}]...'.format(test_set_name))
test_start_time = time.time()
dataset_dir = os.path.join(opt['path']['results_root'], test_set_name)
util.mkdir(dataset_dir)
test_results = OrderedDict()
test_results['psnr'] = []
test_results['ssim'] = []
test_results['psnr_y'] = []
test_results['ssim_y'] = []
for data in test_loader:
need_HR = False if test_loader.dataset.opt[
'dataroot_HR'] is None else True
img_path = data['LR_path'][0]
img_name = os.path.splitext(os.path.basename(img_path))[0]
# tmp_vis(data['LR'][:,1,:,:,:], True)
if opt.get('chop_forward', None):
# data
if len(data['LR'].size()) == 4:
b, n_frames, h_lr, w_lr = data['LR'].size()
LR_y_cube = data['LR'].view(b, -1, 1, h_lr,
w_lr) # b, t, c, h, w
elif len(data['LR'].size()
) == 5: #for networks that work with 3 channel images
_, n_frames, _, _, _ = data['LR'].size()
LR_y_cube = data['LR'] # b, t, c, h, w
# print(LR_y_cube.shape)
# print(data['LR_bicubic'].shape)
# crop borders to ensure each patch can be divisible by 2
#TODO: this is modcrop, not sure if really needed, check (the dataloader already does modcrop)
_, _, _, h, w = LR_y_cube.size()
h = int(h // 16) * 16
w = int(w // 16) * 16
LR_y_cube = LR_y_cube[:, :, :, :h, :w]
if isinstance(data['LR_bicubic'], torch.Tensor):
# SR_cb = data['LR_bicubic'][:, 1, :, :][:, :, :h * scale, :w * scale]
SR_cb = data['LR_bicubic'][:, 1, :h * scale, :w * scale]
# SR_cr = data['LR_bicubic'][:, 2, :, :][:, :, :h * scale, :w * scale]
SR_cr = data['LR_bicubic'][:, 2, :h * scale, :w * scale]
SR_y = chop_forward(LR_y_cube, model, scale,
need_HR=need_HR).squeeze(0)
# SR_y = np.array(SR_y.data.cpu())
if test_loader.dataset.opt.get('srcolors', None):
print(SR_y.shape, SR_cb.shape, SR_cr.shape)
sr_img = ycbcr_to_rgb(torch.stack((SR_y, SR_cb, SR_cr),
-3))
else:
sr_img = SR_y
else:
# data
model.feed_data(data, need_HR=need_HR)
# SR_y = net(LR_y_cube).squeeze(0)
model.test() # test
visuals = model.get_current_visuals(need_HR=need_HR)
# ds = torch.nn.AvgPool2d(2, stride=2, count_include_pad=False)
# tmp_vis(ds(visuals['SR']), True)
# tmp_vis(visuals['SR'], True)
if test_loader.dataset.opt.get(
'y_only', None) and test_loader.dataset.opt.get(
'srcolors', None):
SR_cb = data['LR_bicubic'][:, 1, :, :]
SR_cr = data['LR_bicubic'][:, 2, :, :]
# tmp_vis(ds(SR_cb), True)
# tmp_vis(ds(SR_cr), True)
sr_img = ycbcr_to_rgb(
torch.stack((visuals['SR'], SR_cb, SR_cr), -3))
else:
sr_img = visuals['SR']
#if znorm the image range is [-1,1], Default: Image range is [0,1] # testing, each "dataset" can have a different name (not train, val or other)
sr_img = tensor2np(sr_img, denormalize=znorm) # uint8
# save images
suffix = opt['suffix']
if suffix:
save_img_path = os.path.join(dataset_dir,
img_name + suffix + '.png')
else:
save_img_path = os.path.join(dataset_dir, img_name + '.png')
util.save_img(sr_img, save_img_path)
#TODO: update to use metrics functions
# calculate PSNR and SSIM
if need_HR:
#if znorm the image range is [-1,1], Default: Image range is [0,1] # testing, each "dataset" can have a different name (not train, val or other)
gt_img = tensor2img(visuals['HR'], denormalize=znorm) # uint8
gt_img = gt_img / 255.
sr_img = sr_img / 255.
crop_border = test_loader.dataset.opt['scale']
cropped_sr_img = sr_img[crop_border:-crop_border,
crop_border:-crop_border, :]
cropped_gt_img = gt_img[crop_border:-crop_border,
crop_border:-crop_border, :]
psnr = util.calculate_psnr(cropped_sr_img * 255,
cropped_gt_img * 255)
ssim = util.calculate_ssim(cropped_sr_img * 255,
cropped_gt_img * 255)
test_results['psnr'].append(psnr)
test_results['ssim'].append(ssim)
if gt_img.shape[2] == 3: # RGB image
sr_img_y = bgr2ycbcr(sr_img, only_y=True)
gt_img_y = bgr2ycbcr(gt_img, only_y=True)
cropped_sr_img_y = sr_img_y[crop_border:-crop_border,
crop_border:-crop_border]
cropped_gt_img_y = gt_img_y[crop_border:-crop_border,
crop_border:-crop_border]
psnr_y = util.calculate_psnr(cropped_sr_img_y * 255,
cropped_gt_img_y * 255)
ssim_y = util.calculate_ssim(cropped_sr_img_y * 255,
cropped_gt_img_y * 255)
test_results['psnr_y'].append(psnr_y)
test_results['ssim_y'].append(ssim_y)
logger.info('{:20s} - PSNR: {:.6f} dB; SSIM: {:.6f}; PSNR_Y: {:.6f} dB; SSIM_Y: {:.6f}.'\
.format(img_name, psnr, ssim, psnr_y, ssim_y))
else:
logger.info(
'{:20s} - PSNR: {:.6f} dB; SSIM: {:.6f}.'.format(
img_name, psnr, ssim))
else:
logger.info(img_name)
#TODO: update to use metrics functions
if need_HR: # metrics
# Average PSNR/SSIM results
ave_psnr = sum(test_results['psnr']) / len(test_results['psnr'])
ave_ssim = sum(test_results['ssim']) / len(test_results['ssim'])
logger.info('----Average PSNR/SSIM results for {}----\n\tPSNR: {:.6f} dB; SSIM: {:.6f}\n'\
.format(test_set_name, ave_psnr, ave_ssim))
if test_results['psnr_y'] and test_results['ssim_y']:
ave_psnr_y = sum(test_results['psnr_y']) / len(
test_results['psnr_y'])
ave_ssim_y = sum(test_results['ssim_y']) / len(
test_results['ssim_y'])
logger.info('----Y channel, average PSNR/SSIM----\n\tPSNR_Y: {:.6f} dB; SSIM_Y: {:.6f}\n'\
.format(ave_psnr_y, ave_ssim_y))
