def main():
# Parse the command line arguments
opts = options.parse()
# torch.backends.cudnn.benchmark = False
device_ids = [0, 1]
# if opts.scan_gpus == True:
# # Scan the available GPUs to find one currently using less than 10Mb
# device_ids = sr_utils.wait_for_GPU(10)
# available_gpus = str(device_ids)[1:-1]
# print("Using GPUs {}".format(available_gpus))
# os.environ['CUDA_VISIBLE_DEVICES']=str(available_gpus)
#
#
# # If using synthetic data launch the subprocess that keeps creating sinograms
# if opts.synthetic_data == True:
# print("Launching the sinogram creation sub process")
# p = subprocess.Popen(["python", "create_sinos.py"])
# while(os.path.isfile("training_data.npy") == False):
# print("waiting for training data...")
# time.sleep(5)
# Create the Network trainer and train!
# device_ids = None
trainer = Network_Trainer(opts, device_ids)
trainer.train()
def main(self):
try:
opts = options.parse()
except(options.ParseError, options.MissingArgumentError):
print "Usage: digestive rainforestapp/digestive [email protected]"
exit(1)
digestive = Digestive(opts.username, opts.repository, opts.emails)
digestive.process()
def main():
args = options.parse()
# Create necessary directories if they do not exist.
for path in [HOME, CACHE]:
if not os.path.exists(path): os.mkdir(path)
# Determine the host from either a dns_name or ip_address provided as an argument.
# 'host' is either args.ip_address, args.dns_name, or args.cidr_range
#host = args.dns_name if args.dns_name else args.ip_address
#if host is None: raise Exception('ERROR: no domain/dns name or ip address provided')
# The api_url is specific to the type of API call (contingent on args.ip_address/cidr_range,
# or args.dns_name), and further, to A/MX records if dnsrecord API (--dns_name provided)is used.
# The results of each are different and require different JSON parsing.
common_prefix = args.api_site
common_suffix = ''.join(
('&apikey=', args.api_key, '&output=', args.api_output))
if args.ip_address: # reverseip
# Force forms to be appropriate: e.g., ip_address is an ip_pattern.
try:
ipaddr(args.ip_address).group()
except AttributeError:
sys.stdout.write(
'error: --ip-address requires a valid ip address. Please try again.\n'
)
sys.exit(1)
# Construct the url needed for the reverseip API call.
middle = ''.join(('reverseip/', '?host=', args.ip_address))
url = middle.join((common_prefix, common_suffix))
#try:
out = reverseip_lookup(url, JSON_REVERSEIP_RESPONSE_FILE, args.keyword)
#except ConnectionRefusedError: #noqa
# # Sleep? Try again? How many times?
# print('Connection refused.')
# return
elif args.dns_name: # dnsrecord
middle = ''.join(
('dnsrecord/', '?domain=', args.dns_name, '&recordtype=', 'A'))
url = middle.join((common_prefix, common_suffix))
out = dnsrecord_lookup(url, args.dns_name,
JSON_DNSRECORD_RESPONSE_FILE, args.keyword)
elif args.cidr_range:
# Should be same as ip_address (e.g., reverseip_lookup()), but will in a loop.
#startip, endip = args.cidr_range[0], args.cidr_range[1] #noqa
# cidrs = netaddr.iprange_to_cidrs(startip, endip)
pass
print(out) # Testing.
# Write to csv style output to OUTPUT_FILE.
with open(OUTPUT_FILE, 'a') as o:
o.write(out)
def main():
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)
opt = option.dict_to_nonedict(opt)
dataset_opt = opt['datasets']['test']
test_set = create_dataset(dataset_opt)
test_loader = create_dataloader(test_set, dataset_opt, opt, None)
model = Model(opt)
if test_loader is not None:
calc_lpips = PerceptualLossLPIPS()
if True:
avg_ssim = avg_psnr = avg_lpips = 0
print("Testing Starts!")
idx = 0
test_bar = tqdm(test_loader)
for test_data in test_bar:
idx += 1
img_name = os.path.splitext(os.path.basename(test_data['LQ_path'][0]))[0]
img_dir = '../test_results_' + opt['name']
util.mkdir(img_dir)
model.feed_data(test_data)
model.test()
visuals = model.get_current_visuals()
sr_img = util.tensor2img(visuals['SR']) # uint8
gt_img = util.tensor2img(visuals['GT']) # uint8
lq_img = util.tensor2img(visuals['LQ']) # uint8
# Save SR images for reference
save_sr_img_path = os.path.join(img_dir,
'{:s}_sr.png'.format(img_name))
util.save_img(sr_img, save_sr_img_path)
gt_img = gt_img / 255.
sr_img = sr_img / 255.
lq_img = lq_img / 255.
avg_psnr += util.calculate_psnr(sr_img * 255, gt_img * 255)
avg_ssim += util.calculate_ssim(sr_img * 255, gt_img * 255)
avg_lpips += calc_lpips(visuals['SR'], visuals['GT'])
avg_psnr = avg_psnr / idx
avg_ssim = avg_ssim / idx
avg_lpips = avg_lpips / idx
print('Test_Result_{:s} psnr: {:.4e} ssim: {:.4e} lpips: {:.4e}'.format(
opt['name'], avg_psnr, avg_ssim, avg_lpips))
def main():
args = parse()
print(args)
model, data, loss_func, opti, vis = initialization(args)
print(model, data, loss_func, opti, vis)
learning_framework = learning.Learning(model, data, opti, loss_func, vis)
learning_framework.train(10)
def main():
opt = options.parse()
opt.top_k = 5
opt.validation_ratio = 0.2
##########################################
# train
# clf = GradientBoostingClassifier(n_estimators=3000, learning_rate=0.05, max_depth=6, max_features='sqrt')
# clf = RandomForestClassifier()
clf = RandomForestClassifier(n_estimators=3500,
criterion='entropy',
max_depth=None,
max_features='sqrt',
min_samples_split=4,
min_samples_leaf=2,
n_jobs=4)
count = 0
test_predictions = None
for i in range(10):
dl = FeatureDataLoader(opt)
x_train, y_train, x_valid, y_valid, x_test, test_ids = get_data(dl)
clf.fit(x_train, y_train)
clf_probs = clf.predict_proba(x_valid)[:, 1]
score = log_loss(y_valid, clf_probs)
test_predictions = clf.predict_proba(x_test)[:, 1]
print(score)
# if score < 0.44:
# print('{}:{}'.format(i, score))
# if test_predictions is None:
# test_predictions = clf.predict_proba(x_test)[:, 1]
# else:
# test_predictions += clf.predict_proba(x_test)[:, 1]
# count += 1
#
# test_predictions = test_predictions / count
with open('submission_random_forest.csv', 'w') as f:
writer = csv.writer(f)
# write the header
for row in {'id': 'cancer'}.items():
writer.writerow(row)
# write the content
for row in zip(test_ids, test_predictions):
writer.writerow(row)
# print(log_loss(y_train, clf.predict_proba(x_train)))
# print(score)
# print(normalized_score)
test_predictions = clf.predict_proba(x_test)[:, 1]
def parse_options(is_train=True):
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt',
type=str,
required=True,
help='Path to options file.')
args = parser.parse_args()
opt = options.parse(args.opt, is_train=is_train)
return opt
def main():
args = parse()
print(args)
dataloader, dataloader_vis, dataloader_vid, model, vis, lr_scheduler, optimizer = initialization(
args)
################## training #######################
for epoch in range(100):
epoch_loss = 0
result = []
result = np.array(result)
model.train()
for i_batch, sample_batched in enumerate(dataloader):
batch_loss, result = pad_update(
model,
sample_batched,
with_attention_flag=args.with_attention_flag,
pad_flag=args.pad_flag)
epoch_loss += batch_loss
vis.plot_current_errors(
epoch, i_batch * input_batch_size / len(kitti_dataset),
batch_loss.data)
print(epoch, '******', i_batch, '*******', batch_loss)
batch_loss.backward()
optimizer.step()
data_length = len(kitti_dataset) // input_batch_size * input_batch_size
lr_scheduler.step()
with torch.no_grad():
if epoch % args.check_period == 0:
model.eval()
vis_para.vis = vis
vis_para.win_number = 0
vis_para.title = 'training'
train_error, train_loss = testing(dataloader_vis, vis_para)
vis_para.win_number = 10
vis_para.title = 'testing'
eval_error, eval_loss = testing(dataloader_vid, vid_para)
vis.plot_epoch_training_validing(epoch, train_loss, eval_loss)
vis.plot_epoch_training_validing_2(epoch, train_error[1][7],
eval_error[1][7], 22)
torch.save(
model.state_dict(), '../saved_model/model_' +
args.model_name + '_' + str(epoch).zfill(3) + '.pt')
def main():
#### setup options of three networks
parser = argparse.ArgumentParser()
parser.add_argument("-opt",
type=str,
help="Path to option YMAL file of Predictor.")
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)
# convert to NoneDict, which returns None for missing keys
opt = option.dict_to_nonedict(opt)
# choose small opt for SFTMD test, fill path of pre-trained model_F
#### set random seed
seed = opt["train"]["manual_seed"]
if seed is None:
seed = random.randint(1, 10000)
util.set_random_seed(seed)
# load PCA matrix of enough kernel
print("load PCA matrix")
pca_matrix = torch.load(opt["pca_matrix_path"],
map_location=lambda storage, loc: storage)
print("PCA matrix shape: {}".format(pca_matrix.shape))
#### distributed training settings
if args.launcher == "none": # disabled distributed training
opt["dist"] = False
opt["dist"] = False
rank = -1
print("Disabled distributed training.")
else:
opt["dist"] = True
opt["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["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 0-7)
if resume_state is None:
# Predictor path
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))
os.system("rm ./log")
os.symlink(os.path.join(opt["path"]["experiments_root"], ".."),
"./log")
# 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="log/tb_logger/" + opt["name"])
else:
util.setup_logger("base",
opt["path"]["log"],
"train",
level=logging.INFO,
screen=True)
logger = logging.getLogger("base")
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
assert val_loader is not None
#### create model
model = create_model(opt) # load pretrained model of SFTMD
#### 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
prepro = util.SRMDPreprocessing(
opt["scale"],
pca_matrix,
random=True,
para_input=opt["code_length"],
kernel=opt["kernel_size"],
noise=False,
cuda=True,
sig=None,
sig_min=opt["sig_min"],
sig_max=opt["sig_max"],
rate_iso=1.0,
scaling=3,
rate_cln=0.2,
noise_high=0.0,
)
#### 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
#### preprocessing for LR_img and kernel map
LR_img, ker_map = prepro(train_data["GT"])
LR_img = (LR_img * 255).round() / 255
#### training Predictor
model.feed_data(LR_img, train_data["GT"], ker_map)
model.optimize_parameters(current_step)
model.update_learning_rate(current_step,
warmup_iter=opt["train"]["warmup_iter"])
visuals = model.get_current_visuals()
#### log of model_P
if current_step % opt["logger"]["print_freq"] == 0:
logs = model.get_current_log()
message = "Predictor <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, to produce ker_map_list(fake)
if current_step % opt["train"]["val_freq"] == 0 and rank <= 0:
avg_psnr = 0.0
idx = 0
for _, val_data in enumerate(val_loader):
# LR_img, ker_map = prepro(val_data['GT'])
LR_img = val_data["LQ"]
lr_img = util.tensor2img(
LR_img) # save LR image for reference
# valid Predictor
model.feed_data(LR_img, val_data["GT"])
model.test()
visuals = model.get_current_visuals()
# Save images for reference
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)
# img_dir = os.path.join(opt['path']['val_images'], str(current_step), '_', str(step))
util.mkdir(img_dir)
save_lr_path = os.path.join(img_dir,
"{:s}_LR.png".format(img_name))
util.save_img(lr_img, save_lr_path)
sr_img = util.tensor2img(visuals["SR"]) # uint8
gt_img = util.tensor2img(visuals["GT"]) # 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)
# calculate PSNR
crop_size = opt["scale"]
gt_img = gt_img / 255.0
sr_img = sr_img / 255.0
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)
idx += 1
avg_psnr = avg_psnr / idx
# log
logger.info("# Validation # PSNR: {:.6f}".format(avg_psnr))
logger_val = logging.getLogger("val") # validation logger
logger_val.info(
"<epoch:{:3d}, iter:{:8,d}, psnr: {:.6f}".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 Predictor and Corrector training.")
tb_logger.close()
def main():
# parameters and flags
args = parse()
valid_period = 5
visualize_training_period = 5
save_visualize_training_period = 5
input_batch_size = args.batch_size
finetune_flag = False
coor_layer_flag = False
use_gpu_flag = False
data_balance_flag = False
color_flag = False
rpe_flag = False
camera_parameter = [640, 180, 640, 640, 320, 90]
image_size = (camera_parameter[1], camera_parameter[0])
################## init model###########################
model = VONet.SPADVONet(coor_layer_flag=coor_layer_flag,
color_flag=color_flag)
model = model.float()
print(model)
if use_gpu_flag:
# uncomment this to use multi-gpu
#model = nn.DataParallel(model.cuda())
model = model.cuda()
if finetune_flag:
model.load_state_dict(torch.load(args.model_load))
optimizer = optim.Adam(model.parameters(), lr=0.001, weight_decay=0)
lr_scheduler = optim.lr_scheduler.LambdaLR(optimizer,
lr_lambda=LambdaLR(200, 0,
50).step)
print(optimizer)
################### load data####################
# training data
motion_files_path = args.motion_path
path_files_path = args.image_list_path
print(motion_files_path)
print(path_files_path)
# transform
if color_flag:
transforms_ = [
transforms.Resize(image_size),
transforms.ColorJitter(brightness=0.1,
contrast=0.1,
saturation=0.1,
hue=0.1),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]
else:
transforms_ = [
transforms.Resize(image_size),
transforms.ColorJitter(brightness=0.1,
contrast=0.1,
saturation=0.1,
hue=0.1),
transforms.ToTensor()
]
kitti_dataset = data_loader.SepeDataset(
path_to_poses_files=motion_files_path,
path_to_image_lists=path_files_path,
transform_=transforms_,
camera_parameter=camera_parameter,
coor_layer_flag=coor_layer_flag,
color_flag=color_flag)
dataloader = DataLoader(kitti_dataset,
batch_size=input_batch_size,
shuffle=True,
num_workers=4,
drop_last=True)
if data_balance_flag:
print('data balance by prob')
dataloader = DataLoader(kitti_dataset,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True,
sampler=kitti_dataset.sampler)
else:
print('no data balance')
dataloader_vis = DataLoader(kitti_dataset,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True)
# testing data
motion_files_path_test = args.motion_path_test
path_files_path_test = args.image_list_path_test
print(motion_files_path_test)
print(path_files_path_test)
# transform
if color_flag:
transforms_ = [
transforms.Resize(image_size),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]
else:
transforms_ = [transforms.Resize(image_size), transforms.ToTensor()]
kitti_dataset_test = data_loader.SepeDataset(
path_to_poses_files=motion_files_path_test,
path_to_image_lists=path_files_path_test,
transform_=transforms_,
camera_parameter=camera_parameter,
norm_flag=1,
coor_layer_flag=coor_layer_flag,
color_flag=color_flag)
dataloader_vid = DataLoader(kitti_dataset_test,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True)
print(len(kitti_dataset), len(kitti_dataset_test))
training_loss_data = open(
'../checkpoint/saved_result/' + args.model_name + '_training.loss',
'a')
testing_loss_data = open(
'../checkpoint/saved_result/' + args.model_name + '_testing.loss', 'a')
training_ate_data = open(
'../checkpoint/saved_result/' + args.model_name + '_training.ate', 'a')
testing_ate_data = open(
'../checkpoint/saved_result/' + args.model_name + '_testing.ate', 'a')
################## training #######################
for epoch in range(101):
epoch_loss = 0
result = []
result = np.array(result)
model.train()
for i_batch, sample_batched in enumerate(dataloader):
batch_loss, result = pad_update(model,
sample_batched,
use_gpu_flag=use_gpu_flag)
epoch_loss += batch_loss
print(epoch, '******', i_batch, '/', len(dataloader), '*******',
batch_loss.item())
batch_loss.backward()
optimizer.step()
data_length = len(kitti_dataset) // input_batch_size * input_batch_size
epoch_loss_mean = epoch_loss * input_batch_size / data_length
lr_scheduler.step()
####Visualization Path###############################################################
with torch.no_grad():
if epoch % valid_period == 0:
model.eval()
forward_visual_result = []
ground_truth = []
epoch_loss_visu = 0
for i_batch, sample_batched in enumerate(dataloader_vis):
print('visu************** i_batch', i_batch,
'******************')
model.zero_grad()
batch_loss, result = pad_update(model,
sample_batched,
use_gpu_flag=use_gpu_flag)
#batch_loss.backward()
batch_loss.detach_()
training_loss_data.write(
str(batch_loss.cpu().data.tolist()) + '\n')
training_loss_data.flush()
epoch_loss_visu += batch_loss
temp_f = weighted_mean_motion(result)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
if i_batch > 100:
break
data_length = len(
kitti_dataset) // input_batch_size * input_batch_size
forward_visual_result = forward_visual_result.reshape(
-1, 6) * kitti_dataset.motion_stds
#forward_visual_result[:,no_motion_flag]=0
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset.motion_stds+kitti_dataset.motion_means
ground_truth = ground_truth.reshape(
-1, 6) * kitti_dataset.motion_stds
forward_visual_result_m = tf.eular2pose(forward_visual_result)
ground_truth_m = tf.eular2pose(ground_truth)
if rpe_flag:
rot_train, tra_train = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
training_ate_data.write(
str(np.mean(tra_train)) + ' ' +
str(np.mean(rot_train)) + '\n')
training_ate_data.flush()
torch.save(
model.state_dict(), '../checkpoint/saved_model/model_' +
args.model_name + '_' + str(epoch).zfill(3) + '.pt')
####Vilidation Path###############################################################
model.eval()
forward_visual_result = []
backward_visual_result = []
ground_truth = []
forward_visual_opti = []
for i_batch, sample_batched in enumerate(dataloader_vid):
#opti vis
print('test************** i_batch', i_batch,
'******************')
batch_loss_eval, predicted_result_eval = pad_update(
model, sample_batched, use_gpu_flag=use_gpu_flag)
batch_loss_eval.detach_()
testing_loss_data.write(
str(batch_loss_eval.cpu().data.tolist()) + '\n')
testing_loss_data.flush()
temp_f = weighted_mean_motion(predicted_result_eval)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
data_length = len(
kitti_dataset_test) // input_batch_size * input_batch_size
forward_visual_result = forward_visual_result.reshape(
data_length, 6) * kitti_dataset_test.motion_stds
#forward_visual_result[:,no_motion_flag]=0
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset_test.motion_stds+kitti_dataset_test.motion_means
ground_truth = ground_truth.reshape(
data_length, 6) * kitti_dataset_test.motion_stds
forward_visual_result_m = tf.eular2pose(forward_visual_result)
ground_truth_m = tf.eular2pose(ground_truth)
plot_path([ground_truth_m, forward_visual_result_m], epoch,
args)
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
if rpe_flag:
rot_eval, tra_eval = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
testing_ate_data.write(
str(np.mean(tra_eval)) + ' ' + str(np.mean(rot_eval)) +
'\n')
testing_ate_data.flush()
default="options/test/SFTMD/test_SFTMD_x4.yml",
help="Path to options YMAL file.",
)
parser.add_argument(
"-opt_P",
type=str,
default="options/test/Predictor/test_Predictor_x4.yml",
help="Path to options YMAL file.",
)
parser.add_argument(
"-opt_C",
type=str,
default="options/test/Corrector/test_Corrector_x4.yml",
help="Path to options YMAL file.",
)
opt_F = option.parse(parser.parse_args().opt_F, is_train=False)
opt_P = option.parse(parser.parse_args().opt_P, is_train=False)
opt_C = option.parse(parser.parse_args().opt_C, is_train=False)
opt_F = option.dict_to_nonedict(opt_F)
opt_P = option.dict_to_nonedict(opt_P)
opt_C = option.dict_to_nonedict(opt_C)
#### mkdir and logger
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))
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))
def main(args):
flist, opt = options.parse(__version__, args)
print "options:"
pprint.pprint(opt)
pprint.pprint(flist)
import torch
import options as option
sys.path.insert(0, "../../")
import utils as util
parser = argparse.ArgumentParser()
parser.add_argument(
"-opt",
type=str,
default="options/setting1/train/train_setting1_x4.yml",
help="Path to options YMAL file.",
)
args = parser.parse_args()
opt = option.parse(args.opt, is_train=True)
setting = opt["degradation"]
is_iso = True if setting["rate_iso"] == 1 else False
batch_ker = util.random_batch_kernel(
batch=30000,
l=setting["ksize"],
sig_min=setting["sig_min"],
sig_max=setting["sig_max"],
rate_iso=setting["rate_iso"],
random_disturb=setting["random_disturb"],
tensor=False,
)
print("batch kernel shape: {}".format(batch_ker.shape))
def main():
# parameters and flags
args = parse()
valid_period = 5
visualize_training_period = 5
save_visualize_training_period = 5
input_batch_size = args.batch_size
finetune_flag = False
coor_layer_flag = args.coor_layer_flag
pad_flag = args.pad_flag
with_attention_flag = args.with_attention_flag
print(coor_layer_flag, pad_flag, with_attention_flag)
use_gpu_flag = True
#motion_flag = [2,4]
motion_flag = [0, 1, 2, 3, 4, 5]
data_balance_flag = False
color_flag = False
vis_flag = False
ate_flag = True
debug_flag = False
args.color_flag = color_flag
args.data_balance_flag = data_balance_flag
args.coor_layer_flag = coor_layer_flag
no_motion_flag = [d not in motion_flag for d in range(0, 6)]
print(motion_flag, no_motion_flag)
#camera_parameter=[450,180,225,225,225,90]
#camera_parameter=[651,262,651,651,320,130]
camera_parameter = [640, 180, 640, 640, 320, 90]
image_size = (camera_parameter[1], camera_parameter[0])
args.camera_parameter = camera_parameter
args.image_size = image_size
################## init model###########################
model = models.VONet.PADVONet(coor_layer_flag=coor_layer_flag,
color_flag=color_flag)
model = model.float()
if use_gpu_flag:
#model = nn.DataParallel(model.cuda())
model = model.cuda()
if finetune_flag:
model.load_state_dict(torch.load(args.model_load))
optimizer = optim.Adam(model.parameters(), lr=0.001, weight_decay=0)
lr_scheduler = optim.lr_scheduler.LambdaLR(optimizer,
lr_lambda=LambdaLR(200, 0,
50).step)
print(optimizer)
#ego_pre = ep.EgomotionPrediction()
################### load data####################
dataloader, dataloader_vis, dataloader_vid = dataloader_init(args)
epoch_loss_visu_mean = 0
epoch_loss_eval_mean = 0
if vis_flag:
vis = visualizer.Visualizer(args.visdom_ip, args.visdom_port)
print('vis', args.visdom_ip, args.visdom_port)
training_loss_data = open(
'../checkpoint/saved_result/' + args.model_name + '_training.loss',
'a')
testing_loss_data = open(
'../checkpoint/saved_result/' + args.model_name + '_testing.loss', 'a')
training_ate_data = open(
'../checkpoint/saved_result/' + args.model_name + '_training.ate', 'a')
testing_ate_data = open(
'../checkpoint/saved_result/' + args.model_name + '_testing.ate', 'a')
################## training #######################
for epoch in range(101):
epoch_loss = 0
result = []
result = np.array(result)
model.train()
for i_batch, sample_batched in enumerate(dataloader):
batch_loss, result = pad_update(
model,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
#att_0 = result[1]
#vis.plot_heat_map(att_0[0,0,:,:])
epoch_loss += batch_loss
if vis_flag:
vis.plot_current_errors(
epoch, i_batch * input_batch_size / len(kitti_dataset),
batch_loss.data)
print(epoch, '******', i_batch, '/', len(dataloader), '*******',
batch_loss.item())
batch_loss.backward()
optimizer.step()
if debug_flag:
if i_batch > 10:
break
epoch_loss_mean = epoch_loss / len(dataloader)
if vis_flag:
vis.plot_epoch_current_errors(epoch, epoch_loss_mean.data)
lr_scheduler.step()
####Visualization Path###############################################################
with torch.no_grad():
if epoch % valid_period == 0:
model.eval()
forward_visual_result = []
ground_truth = []
epoch_loss_visu = 0
for i_batch, sample_batched in enumerate(dataloader_vis):
print('visu************** i_batch', i_batch,
'******************')
model.zero_grad()
batch_loss, result = pad_update(
model,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
att_0 = result[1]
if vis_flag:
vis.plot_heat_map(att_0[0, 0, :, :])
#batch_loss.backward()
batch_loss.detach_()
training_loss_data.write(
str(batch_loss.cpu().data.tolist()) + '\n')
training_loss_data.flush()
epoch_loss_visu += batch_loss
temp_f = weighted_mean_motion(result, with_attention_flag)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
if debug_flag:
if i_batch * input_batch_size > 1500:
break
data_length = len(dataloader_vis) * input_batch_size
epoch_loss_visu_mean = epoch_loss_visu / len(dataloader_vis)
forward_visual_result = forward_visual_result.reshape(
-1, 6) * dataloader_vis.dataset.motion_stds
forward_visual_result[:, no_motion_flag] = 0
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset.motion_stds+kitti_dataset.motion_means
ground_truth = ground_truth.reshape(
-1, 6) * dataloader_vis.dataset.motion_stds
forward_visual_result_m = tf.eular2pose(forward_visual_result)
ground_truth_m = tf.eular2pose(ground_truth)
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
if ate_flag:
rot_train, tra_train = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
training_ate_data.write(
str(np.mean(tra_train)) + ' ' +
str(np.mean(rot_train)) + '\n')
training_ate_data.flush()
if vis_flag:
vis.plot_path_with_gt(forward_visual_result_m,
ground_truth_m, 5,
'training set forward')
torch.save(
model.state_dict(), '../checkpoint/saved_model/model_' +
args.model_name + '_' + str(epoch).zfill(3) + '.pt')
####Vilidation Path###############################################################
model.eval()
forward_visual_result = []
backward_visual_result = []
ground_truth = []
epoch_loss_eval = 0
forward_visual_opti = []
for i_batch, sample_batched in enumerate(dataloader_vid):
#opti vis
print('test************** i_batch', i_batch,
'******************')
batch_loss_eval, predicted_result_eval = pad_update(
model,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
batch_loss_eval.detach_()
testing_loss_data.write(
str(batch_loss_eval.cpu().data.tolist()) + '\n')
testing_loss_data.flush()
epoch_loss_eval += batch_loss_eval
temp_f = weighted_mean_motion(predicted_result_eval,
with_attention_flag)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
if debug_flag:
if i_batch * input_batch_size > 1500:
break
data_length = len(dataloader_vid) * input_batch_size
epoch_loss_eval_mean = epoch_loss_eval / len(dataloader_vid)
forward_visual_result = forward_visual_result.reshape(
-1, 6) * dataloader_vid.dataset.motion_stds
forward_visual_result[:, no_motion_flag] = 0
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset_test.motion_stds+kitti_dataset_test.motion_means
ground_truth = ground_truth.reshape(
-1, 6) * dataloader_vid.dataset.motion_stds
forward_visual_result_m = tf.eular2pose(forward_visual_result)
ground_truth_m = tf.eular2pose(ground_truth)
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
rpe = None
if ate_flag:
rot_eval, tra_eval = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
testing_ate_data.write(
str(np.mean(tra_eval)) + ' ' + str(np.mean(rot_eval)) +
'\n')
testing_ate_data.flush()
rpe = str(np.mean(rot_eval)) + ' ' + str(np.mean(tra_eval))
if vis_flag:
vis.plot_two_path_with_gt(forward_visual_result_m,
forward_visual_result_m,
ground_truth_m, 10,
'testing set forward')
vis.plot_epoch_training_validing(
epoch,
epoch_loss_visu_mean.detach().cpu().numpy(),
epoch_loss_eval_mean.detach().cpu().numpy())
if ate_flag:
vis.plot_epoch_training_validing_2(
epoch, np.mean(tra_train), np.mean(tra_eval), 22)
plot_path([ground_truth_m, forward_visual_result_m], epoch,
args, rpe)
import gradio as gr
import os
from PIL import Image
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'
#### options
parser = argparse.ArgumentParser()
parser.add_argument("-opt",
type=str,
default="test_setting2.yml",
help="Path to options YMAL file.")
parser.add_argument("-input_dir", type=str, default="../../../data_samples/")
parser.add_argument("-output_dir", type=str, default="../../../data_samples/")
args = parser.parse_args()
opt = option.parse(args.opt, is_train=False)
opt = option.dict_to_nonedict(opt)
model = create_model(opt)
if not osp.exists(args.output_dir):
os.makedirs(args.output_dir)
def predict(img):
# img = cv2.imread(args.input_dir)[:, :, [2, 1, 0]]
img = img.transpose(2, 0, 1)[None] / 255
img_t = torch.as_tensor(np.ascontiguousarray(img)).float()
model.feed_data(img_t)
model.test()
sr = model.fake_SR.detach().float().cpu()[0]
sr_im = tensor2img(sr)
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, required=True,
help='Path to options file.')
opt = options.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 = options.dict_to_nonedict(opt)
util.setup_logger(None, opt['path']['log'],
'test.log', level=logging.INFO, screen=True)
logger = logging.getLogger('base')
logger.info(options.dict2str(opt))
# Create test dataset and dataloader
test_loaders = []
znorm = False # TMP
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['in_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 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)
top_img = tensor2np(visuals['top_fake']) # uint8
bot_img = tensor2np(visuals['bottom_fake']) # uint8
# save images
suffix = opt['suffix']
if suffix:
save_img_path = os.path.join(
dataset_dir, img_name + suffix)
else:
save_img_path = os.path.join(dataset_dir, img_name)
util.save_img(top_img, save_img_path + '_top.png')
util.save_img(bot_img, save_img_path + '_bot.png')
#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))
#weighted average
att_temp_f_e = -att_temp_f*np.exp(att_temp_f)
#att_temp_f_e = np.exp(att_temp_f)
#print(temp_f.shape,att_temp_f_e.shape)
temp_f_w = temp_f*att_temp_f_e
#print('temp_f_w',temp_f_w)
temp_f_w_s = np.sum(np.sum(temp_f_w,2),2)
att_temp_s = np.sum(np.sum(att_temp_f_e,2),2)
temp_f = temp_f_w_s/att_temp_s
#print('temp',temp_f.shape)
return temp_f
if __name__ == '__main__':
args = parse()
valid_period = 5
visualize_training_period = 5
save_visualize_training_period = 5
input_batch_size = args.batch_size
finetune_flag = True
use_gpu_flag = True
with_attention_flag = True
coor_layer_flag = True
no_pad_flag = False
################## init model###########################
model = models.VONet.PADVOFeature(coor_layer_flag = coor_layer_flag)
model = model.float()
# normalization parameter
# model and optimization
if use_gpu_flag:
def main():
# options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, required=True, help='Path to options file.')
opt = options.parse(parser.parse_args().opt, is_train=False)
util.mkdirs((path for key, path in opt['path'].items() if not key == 'pretrain_model_G'))
logger = util.get_root_logger(None, opt['path']['log'], 'test.log', level=logging.INFO, screen=True)
logger = logging.getLogger('base')
logger.info(options.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))
def main():
# setting arguments and logger
parser = argparse.ArgumentParser(description='Arguments')
parser.add_argument('--opt',
type=str,
required=True,
help='path to json or yaml file')
parser.add_argument('--name',
type=str,
required=True,
help='save_dir prefix name')
parser.add_argument('--scale',
type=int,
required=True,
help='scale factor')
parser.add_argument('--ps', type=int, default=None, help='patch size')
parser.add_argument('--bs', type=int, default=None, help='batch_size')
parser.add_argument('--lr', type=float, default=None, help='learning rate')
parser.add_argument('--train_Y',
action='store_true',
default=False,
help='convert rgb to yuv and only train on Y channel')
parser.add_argument('--gpu_ids',
type=str,
default=None,
help='which gpu to use')
parser.add_argument('--use_chop',
action='store_true',
default=False,
help='whether to use split_forward in test phase')
parser.add_argument('--pretrained',
default=None,
help='checkpoint path to resume from')
args = parser.parse_args()
args, lg = parse(args)
# Tensorboard curve
pretrained = args['solver']['pretrained']
train_path = '../Tensorboard/train_{}'.format(args['name'])
val_path = '../Tensorboard/val_{}'.format(args['name'])
psnr_path = '../Tensorboard/psnr_{}'.format(args['name'])
ssim_path = '../Tensorboard/ssim_{}'.format(args['name'])
if pretrained is None:
if osp.exists(train_path):
lg.info('Remove dir: [{}]'.format(train_path))
shutil.rmtree(train_path, True)
if osp.exists(val_path):
lg.info('Remove dir: [{}]'.format(val_path))
shutil.rmtree(val_path, True)
if osp.exists(psnr_path):
lg.info('Remove dir: [{}]'.format(psnr_path))
shutil.rmtree(psnr_path, True)
if osp.exists(ssim_path):
lg.info('Remove dir: [{}]'.format(ssim_path))
shutil.rmtree(ssim_path, True)
train_writer = SummaryWriter(train_path)
val_writer = SummaryWriter(val_path)
psnr_writer = SummaryWriter(psnr_path)
ssim_writer = SummaryWriter(ssim_path)
# random seed
seed = args['solver']['manual_seed']
random.seed(seed)
torch.manual_seed(seed)
# create train and val dataloader
for phase, dataset_opt in args['datasets'].items():
if phase == 'train':
train_dataset = create_dataset(dataset_opt)
train_loader = create_loader(train_dataset, dataset_opt)
length = len(train_dataset)
lg.info(
'Number of train images: [{}], iters each epoch: [{}]'.format(
length, len(train_loader)))
elif phase == 'val':
val_dataset = create_dataset(dataset_opt)
val_loader = create_loader(val_dataset, dataset_opt)
length = len(val_dataset)
lg.info(
'Number of val images: [{}], iters each epoch: [{}]'.format(
length, len(val_loader)))
elif phase == 'test':
test_dataset = create_dataset(dataset_opt)
test_loader = create_loader(test_dataset, dataset_opt)
length = len(test_dataset)
lg.info(
'Number of test images: [{}], iters each epoch: [{}]'.format(
length, len(test_loader)))
# create solver
solver = create_solver(args)
# training prepare
solver_log = solver.get_current_log()
NUM_EPOCH = args['solver']['num_epochs']
cur_iter = -1
start_epoch = solver_log['epoch']
scale = args['scale']
lg.info('Start Training from [{}] Epoch'.format(start_epoch))
print_freq = args['print']['print_freq']
val_step = args['solver']['val_step']
# training
for epoch in range(start_epoch, NUM_EPOCH + 1):
solver_log['epoch'] = epoch
train_loss_list = []
for iter, data in enumerate(train_loader):
cur_iter += 1
solver.feed_data(data)
iter_loss = solver.optimize_step()
train_loss_list.append(iter_loss)
# show on screen
if (cur_iter % print_freq) == 0:
lg.info(
'Epoch: {:4} | iter: {:3} | train_loss: {:.4f} | lr: {}'.
format(epoch, iter, iter_loss,
solver.get_current_learning_rate()))
train_loss = round(sum(train_loss_list) / len(train_loss_list), 4)
train_writer.add_scalar('loss', train_loss, epoch)
solver_log['train_records']['train_loss'].append(train_loss)
solver_log['train_records']['lr'].append(
solver.get_current_learning_rate())
epoch_is_best = False
if (epoch % val_step) == 0:
# Validation
lg.info('Start Validation...')
pbar = ProgressBar(len(val_loader))
psnr_list = []
ssim_list = []
val_loss_list = []
for iter, data in enumerate(val_loader):
solver.feed_data(data)
loss = solver.test()
val_loss_list.append(loss)
# calculate evaluation metrics
visuals = solver.get_current_visual(need_np=True)
psnr, ssim = calc_metrics(visuals['SR'],
visuals['HR'],
crop_border=scale,
test_Y=True)
psnr_list.append(psnr)
ssim_list.append(ssim)
pbar.update('')
# save image
solver.save_current_visual(epoch)
avg_psnr = round(sum(psnr_list) / len(psnr_list), 2)
avg_ssim = round(sum(ssim_list) / len(ssim_list), 4)
val_loss = round(sum(val_loss_list) / len(val_loss_list), 4)
val_writer.add_scalar('loss', val_loss, epoch)
psnr_writer.add_scalar('psnr', avg_psnr, epoch)
ssim_writer.add_scalar('ssim', avg_ssim, epoch)
solver_log['val_records']['val_loss'].append(val_loss)
solver_log['val_records']['psnr'].append(avg_psnr)
solver_log['val_records']['ssim'].append(avg_ssim)
# record the best epoch
if solver_log['best_pred'] < avg_psnr:
solver_log['best_pred'] = avg_psnr
epoch_is_best = True
solver_log['best_epoch'] = epoch
lg.info(
'PSNR: {:.2f} | SSIM: {:.4f} | Loss: {:.4f} | Best_PSNR: {:.2f} in Epoch: [{}]'
.format(avg_psnr, avg_ssim, val_loss, solver_log['best_pred'],
solver_log['best_epoch']))
solver.set_current_log(solver_log)
solver.save_checkpoint(epoch, epoch_is_best)
solver.save_current_log()
# update lr
solver.update_learning_rate(epoch)
lg.info('===> Finished !')
def main():
# parameters and flags
args = parse()
valid_period = 5
visualize_training_period = 5
save_visualize_training_period = 5
input_batch_size = args.batch_size
finetune_flag = False
coor_layer_flag = False
pad_flag = False
with_attention_flag = False
rpw_flag = False
use_gpu_flag = True
vis_flag = False
motion_flag = [2, 4]
data_balance_flag = False
no_motion_flag = [d not in motion_flag for d in range(0, 6)]
print(motion_flag, no_motion_flag)
#camera_parameter=[450,180,225,225,225,90]
#camera_parameter=[651,262,651,651,320,130]
camera_parameter = [640, 180, 640, 640, 320, 90]
image_size = (camera_parameter[1], camera_parameter[0])
################## init model###########################
model = models.VONet.PADVONet(coor_layer_flag=coor_layer_flag)
model = model.float()
if use_gpu_flag:
#model = nn.DataParallel(model.cuda())
model = model.cuda()
print(model)
if finetune_flag:
model.load_state_dict(torch.load(args.model_load))
# bn or gn, we can increase lr
'''
for name, child in model.named_children():
if name[0:3]=='att':
print(name + ' is unfrozen')
for param in child.parameters():
param.requires_grad = True
else:
print(name + ' is frozen')
for param in child.parameters():
param.requires_grad = False
'''
optimizer = optim.Adam(model.parameters(), lr=0.001)
lr_scheduler = optim.lr_scheduler.LambdaLR(optimizer,
lr_lambda=LambdaLR(200, 0,
50).step)
print(optimizer)
#ego_pre = ep.EgomotionPrediction()
################### load data####################
# training data
motion_files_path = args.motion_path
path_files_path = args.image_list_path
print(motion_files_path)
print(path_files_path)
# transform
transforms_ = [
transforms.Resize(image_size),
transforms.ColorJitter(brightness=0.1,
contrast=0.1,
saturation=0.1,
hue=0.1),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]
kitti_dataset_t = dlr.SepeDataset(path_to_poses_files=motion_files_path,
path_to_image_lists=path_files_path,
transform_=transforms_,
camera_parameter=camera_parameter,
coor_layer_flag=coor_layer_flag)
kitti_dataset_tv = dl.SepeDataset(path_to_poses_files=motion_files_path,
path_to_image_lists=path_files_path,
transform_=transforms_,
camera_parameter=camera_parameter,
coor_layer_flag=coor_layer_flag)
#dataloader = DataLoader(kitti_dataset, batch_size=input_batch_size,shuffle=False ,num_workers=4,drop_last=True,sampler=kitti_dataset.sampler)
dataloader = DataLoader(kitti_dataset_t,
batch_size=input_batch_size,
shuffle=True,
num_workers=4,
drop_last=True)
if data_balance_flag:
print('data balance by prob')
dataloader = DataLoader(kitti_dataset_t,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True,
sampler=kitti_dataset.sampler)
else:
print('no data balance')
dataloader_vis = DataLoader(kitti_dataset_tv,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True)
# testing data
motion_files_path_test = args.motion_path_test
path_files_path_test = args.image_list_path_test
print(motion_files_path_test)
print(path_files_path_test)
# transform
transforms_ = [
transforms.Resize(image_size),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]
kitti_dataset_test = dl.SepeDataset(
path_to_poses_files=motion_files_path_test,
path_to_image_lists=path_files_path_test,
transform_=transforms_,
camera_parameter=camera_parameter,
norm_flag=1,
coor_layer_flag=coor_layer_flag)
dataloader_vid = DataLoader(kitti_dataset_test,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True)
print(len(kitti_dataset_t), len(kitti_dataset_test))
epoch_loss_visu_mean = 0
epoch_loss_eval_mean = 0
if vis_flag:
vis = visualizer.Visualizer(args.visdom_ip, args.visdom_port)
print('vis', args.visdom_ip, args.visdom_port)
training_loss_data = open(
'../saved_new/' + args.model_name + '_training.loss', 'a')
testing_loss_data = open(
'../saved_new/' + args.model_name + '_testing.loss', 'a')
training_ate_data = open(
'../saved_new/' + args.model_name + '_training.ate', 'a')
testing_ate_data = open('../saved_new/' + args.model_name + '_testing.ate',
'a')
################## training #######################
for epoch in range(101):
epoch_loss = 0
result = []
result = np.array(result)
model.train()
for i_batch, sample_batched in enumerate(dataloader):
batch_loss, result = pad_update(
model,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
#att_0 = result[1]
#vis.plot_heat_map(att_0[0,0,:,:])
epoch_loss += batch_loss
if vis_flag:
vis.plot_current_errors(
epoch, i_batch * input_batch_size / len(kitti_dataset_t),
batch_loss.data)
print(epoch, '******', i_batch, '/', len(dataloader), '*******',
batch_loss.item())
batch_loss.backward()
optimizer.step()
data_length = len(
kitti_dataset_t) // input_batch_size * input_batch_size
epoch_loss_mean = epoch_loss * input_batch_size / data_length
if vis_flag:
vis.plot_epoch_current_errors(epoch, epoch_loss_mean.data)
lr_scheduler.step()
####Visualization Path###############################################################
with torch.no_grad():
if epoch % valid_period == 0:
model.eval()
forward_visual_result = []
ground_truth = []
epoch_loss_visu = 0
for i_batch, sample_batched in enumerate(dataloader_vis):
print('visu************** i_batch', i_batch,
'******************')
model.zero_grad()
batch_loss, result = pad_update(
model,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
att_0 = result[1]
if vis_flag:
vis.plot_heat_map(att_0[0, 0, :, :])
#batch_loss.backward()
batch_loss.detach_()
training_loss_data.write(
str(batch_loss.cpu().data.tolist()) + '\n')
training_loss_data.flush()
epoch_loss_visu += batch_loss
temp_f = weighted_mean_motion(result, with_attention_flag)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
data_length = len(
kitti_dataset_tv) // input_batch_size * input_batch_size
epoch_loss_visu_mean = epoch_loss_visu * input_batch_size / data_length
forward_visual_result = forward_visual_result.reshape(
data_length, 6) * kitti_dataset_t.motion_stds
forward_visual_result[:, no_motion_flag] = 0
#forward_visual_result[:,2]=1
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset.motion_stds+kitti_dataset.motion_means
ground_truth = ground_truth.reshape(
data_length, 6) * kitti_dataset_t.motion_stds
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
forward_visual_result_m = tf.eular2pose(forward_visual_result)
ground_truth_m = tf.eular2pose(ground_truth)
if vis_flag:
vis.plot_path_with_gt(forward_visual_result_m,
ground_truth_m, 5,
'training set forward')
rot_train, tra_train = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
training_ate_data.write(
str(np.mean(tra_train)) + ' ' + str(np.mean(rot_train)) +
'\n')
training_ate_data.flush()
torch.save(
model.state_dict(), '../saved_model/model_' +
args.model_name + '_' + str(epoch).zfill(3) + '.pt')
####Vilidation Path###############################################################
model.eval()
forward_visual_result = []
backward_visual_result = []
ground_truth = []
epoch_loss_eval = 0
forward_visual_opti = []
for i_batch, sample_batched in enumerate(dataloader_vid):
#opti vis
print('test************** i_batch', i_batch,
'******************')
batch_loss_eval, predicted_result_eval = pad_update(
model,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
batch_loss_eval.detach_()
testing_loss_data.write(
str(batch_loss_eval.cpu().data.tolist()) + '\n')
testing_loss_data.flush()
epoch_loss_eval += batch_loss_eval
temp_f = weighted_mean_motion(predicted_result_eval,
with_attention_flag)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
data_length = len(
kitti_dataset_test) // input_batch_size * input_batch_size
epoch_loss_eval_mean = epoch_loss_eval * input_batch_size / data_length
forward_visual_result = forward_visual_result.reshape(
data_length, 6) * kitti_dataset_test.motion_stds
forward_visual_result[:, no_motion_flag] = 0
#forward_visual_result[:,2]=1
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset_test.motion_stds+kitti_dataset_test.motion_means
ground_truth = ground_truth.reshape(
data_length, 6) * kitti_dataset_test.motion_stds
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
forward_visual_result_m = tf.eular2pose(forward_visual_result)
ground_truth_m = tf.eular2pose(ground_truth)
rot_eval, tra_eval = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
testing_ate_data.write(
str(np.mean(tra_eval)) + ' ' + str(np.mean(rot_eval)) +
'\n')
testing_ate_data.flush()
if vis_flag:
vis.plot_two_path_with_gt(forward_visual_result_m,
forward_visual_result_m,
ground_truth_m, 10,
'testing set forward')
vis.plot_epoch_training_validing(
epoch,
epoch_loss_visu_mean.detach().cpu().numpy(),
epoch_loss_eval_mean.detach().cpu().numpy())
vis.plot_epoch_training_validing_2(epoch,
np.mean(tra_train),
np.mean(tra_eval), 22)
def main():
# parameters and flags
args = parse()
valid_period = 5
visualize_training_period = 5
save_visualize_training_period = 5
input_batch_size = args.batch_size
finetune_flag = False
coor_layer_flag = False
pad_flag = False
with_attention_flag = False
rpe_flag = True
use_gpu_flag = True
motion_flag = [0, 1, 2, 3, 4, 5]
data_balance_flag = False
no_motion_flag = [d not in motion_flag for d in range(0, 6)]
print(motion_flag, no_motion_flag)
#camera_parameter=[450,180,225,225,225,90]
#camera_parameter=[651,262,651,651,320,130]
camera_parameter = [640, 180, 640, 640, 320, 90]
image_size = (camera_parameter[1], camera_parameter[0])
################## init model###########################
vo_predictor = DCVO()
#ego_pre = ep.EgomotionPrediction()
################### load data####################
# training data
motion_files_path = args.motion_path
path_files_path = args.image_list_path
print(motion_files_path)
print(path_files_path)
# transform
transforms_ = [
transforms.Resize(image_size),
transforms.ColorJitter(brightness=0.1,
contrast=0.1,
saturation=0.1,
hue=0.1),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]
kitti_dataset = data.data_loader.SepeDataset(
path_to_poses_files=motion_files_path,
path_to_image_lists=path_files_path,
transform_=transforms_,
camera_parameter=camera_parameter,
coor_layer_flag=coor_layer_flag)
#dataloader = DataLoader(kitti_dataset, batch_size=input_batch_size,shuffle=False ,num_workers=4,drop_last=True,sampler=kitti_dataset.sampler)
dataloader = DataLoader(kitti_dataset,
batch_size=input_batch_size,
shuffle=True,
num_workers=2,
drop_last=True)
if data_balance_flag:
print('data balance by prob')
dataloader = DataLoader(kitti_dataset,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True,
sampler=kitti_dataset.sampler)
else:
print('no data balance')
dataloader_vis = DataLoader(kitti_dataset,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True)
# testing data
motion_files_path_test = args.motion_path_test
path_files_path_test = args.image_list_path_test
print(motion_files_path_test)
print(path_files_path_test)
# transform
transforms_ = [
transforms.Resize(image_size),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]
kitti_dataset_test = data.data_loader.SepeDataset(
path_to_poses_files=motion_files_path_test,
path_to_image_lists=path_files_path_test,
transform_=transforms_,
camera_parameter=camera_parameter,
norm_flag=1,
coor_layer_flag=coor_layer_flag)
dataloader_vid = DataLoader(kitti_dataset_test,
batch_size=input_batch_size,
shuffle=False,
num_workers=4,
drop_last=True)
print(len(kitti_dataset), len(kitti_dataset_test))
epoch_loss_visu_mean = 0
epoch_loss_eval_mean = 0
vis = visualizer.Visualizer(args.visdom_ip, args.visdom_port)
print('vis', args.visdom_ip, args.visdom_port)
training_loss_data = open(
'../saved_new/' + args.model_name + '_training.loss', 'a')
testing_loss_data = open(
'../saved_new/' + args.model_name + '_testing.loss', 'a')
training_ate_data = open(
'../saved_new/' + args.model_name + '_training.ate', 'a')
testing_ate_data = open('../saved_new/' + args.model_name + '_testing.ate',
'a')
################## training #######################
for epoch in range(101):
epoch_loss = 0
result = []
result = np.array(result)
vo_predictor.train()
for i_batch, sample_batched in enumerate(dataloader):
batch_loss, result = dc_update(
vo_predictor,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
#att_0 = result[1]
#vis.plot_heat_map(att_0[0,0,:,:])
epoch_loss += batch_loss
vis.plot_current_errors(
epoch, i_batch * input_batch_size / len(kitti_dataset),
batch_loss.data)
print(epoch, '******', i_batch, '/', len(dataloader), '*******',
batch_loss.item())
batch_loss.backward()
vo_predictor.step()
data_length = len(kitti_dataset) // input_batch_size * input_batch_size
epoch_loss_mean = epoch_loss * input_batch_size / data_length
vis.plot_epoch_current_errors(epoch, epoch_loss_mean.data)
vo_predictor.lstep()
####Visualization Path###############################################################
with torch.no_grad():
if epoch % valid_period == 0:
vo_predictor.eval()
forward_visual_result = []
ground_truth = []
epoch_loss_visu = 0
for i_batch, sample_batched in enumerate(dataloader_vis):
print('visu************** i_batch', i_batch,
'******************')
vo_predictor.zero_grad()
batch_loss, result = dc_update(
vo_predictor,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
att_0 = result[1]
vis.plot_heat_map(att_0[0, 0, :, :])
#batch_loss.backward()
batch_loss.detach_()
training_loss_data.write(
str(batch_loss.cpu().data.tolist()) + '\n')
training_loss_data.flush()
epoch_loss_visu += batch_loss
temp_f = weighted_mean_motion(result, with_attention_flag)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
data_length = len(
kitti_dataset) // input_batch_size * input_batch_size
epoch_loss_visu_mean = epoch_loss_visu * input_batch_size / data_length
forward_visual_result = forward_visual_result.reshape(
data_length, 6) * kitti_dataset.motion_stds
forward_visual_result[:, no_motion_flag] = 0
if no_motion_flag[2] == True:
forward_visual_result[:, 2] = 1
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset.motion_stds+kitti_dataset.motion_means
ground_truth = ground_truth.reshape(
data_length, 6) * kitti_dataset.motion_stds
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
forward_visual_result_m = tf.eular2pose2(
forward_visual_result, 1)
ground_truth_m = tf.eular2pose2(ground_truth, 1)
if rpe_flag:
rot_train, tra_train = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
training_ate_data.write(
str(np.mean(tra_train)) + ' ' +
str(np.mean(rot_train)) + '\n')
training_ate_data.flush()
vis.plot_path_with_gt(forward_visual_result_m, ground_truth_m,
5, 'training set forward')
#torch.save(model.state_dict(), '../saved_model/model_'+args.model_name+'_'+str(epoch).zfill(3)+'.pt')
vo_predictor.save(args.model_name, epoch)
####Vilidation Path###############################################################
vo_predictor.eval()
forward_visual_result = []
backward_visual_result = []
ground_truth = []
epoch_loss_eval = 0
forward_visual_opti = []
for i_batch, sample_batched in enumerate(dataloader_vid):
#opti vis
print('test************** i_batch', i_batch,
'******************')
batch_loss_eval, predicted_result_eval = dc_update(
vo_predictor,
sample_batched,
with_attention_flag=with_attention_flag,
pad_flag=pad_flag,
motion_flag=motion_flag)
batch_loss_eval.detach_()
testing_loss_data.write(
str(batch_loss_eval.cpu().data.tolist()) + '\n')
testing_loss_data.flush()
epoch_loss_eval += batch_loss_eval
temp_f = weighted_mean_motion(predicted_result_eval,
with_attention_flag)
gt_f_12 = sample_batched['motion_f_01'].numpy()
forward_visual_result = np.append(forward_visual_result,
temp_f)
ground_truth = np.append(ground_truth, gt_f_12)
data_length = len(
kitti_dataset_test) // input_batch_size * input_batch_size
epoch_loss_eval_mean = epoch_loss_eval * input_batch_size / data_length
forward_visual_result = forward_visual_result.reshape(
data_length, 6) * kitti_dataset_test.motion_stds
forward_visual_result[:, no_motion_flag] = 0
if no_motion_flag[2] == True:
forward_visual_result[:, 2] = 1
#ground_truth = ground_truth.reshape(data_length,6)*kitti_dataset_test.motion_stds+kitti_dataset_test.motion_means
ground_truth = ground_truth.reshape(
data_length, 6) * kitti_dataset_test.motion_stds
#forward_visual_result_m = tf.ses2poses(forward_visual_result)
#ground_truth_m = tf.ses2poses(ground_truth)
forward_visual_result_m = tf.eular2pose2(
forward_visual_result, 1)
ground_truth_m = tf.eular2pose2(ground_truth, 1)
vis.plot_two_path_with_gt(forward_visual_result_m,
forward_visual_result_m,
ground_truth_m, 10,
'testing set forward')
vis.plot_epoch_training_validing(
epoch,
epoch_loss_visu_mean.detach().cpu().numpy(),
epoch_loss_eval_mean.detach().cpu().numpy())
if rpe_flag:
rot_eval, tra_eval = evaluate.evaluate(
ground_truth_m, forward_visual_result_m)
testing_ate_data.write(
str(np.mean(tra_eval)) + ' ' + str(np.mean(rot_eval)) +
'\n')
testing_ate_data.flush()
vis.plot_epoch_training_validing_2(epoch,
np.mean(tra_train),
np.mean(tra_eval), 22)
parser = argparse.ArgumentParser(description='FSRCNN Demo')
parser.add_argument('--opt', required=True)
parser.add_argument('--name', required=True)
parser.add_argument('--scale', default=3, type=int)
parser.add_argument('--ps', default=48, type=int, help='patch_size')
parser.add_argument('--bs', default=16, type=int, help='batch_size')
parser.add_argument('--lr', default=1e-3, type=float, help='learning rate')
parser.add_argument('--gpu_ids', default=None)
parser.add_argument('--resume', action='store_true', default=False)
parser.add_argument('--resume_path', default=None)
parser.add_argument('--qat', action='store_true', default=False)
parser.add_argument('--qat_path', default=None)
args = parser.parse_args()
args, lg = parse(args)
# Tensorboard save directory
resume = args['solver']['resume']
tensorboard_path = 'Tensorboard/{}'.format(args['name'])
if resume == False:
if osp.exists(tensorboard_path):
shutil.rmtree(tensorboard_path, True)
lg.info('Remove dir: [{}]'.format(tensorboard_path))
writer = SummaryWriter(tensorboard_path)
# create dataset
train_data = DIV2K(args['datasets']['train'])
lg.info('Create train dataset successfully!')
lg.info('Training: [{}] iterations for each epoch'.format(len(train_data)))
return l1, l2
def save_network(self):
print("saving network parameters")
folder_path = os.path.join(self.opts.output_path, 'model')
if not os.path.exists(folder_path):
os.makedirs(folder_path)
torch.save(
self.network.state_dict(),
os.path.join(folder_path, "model_dict_{}".format(self.model_num)))
self.model_num += 1
if self.model_num >= 5: self.model_num = 0
if __name__ == '__main__':
opts = options.parse()
# net = UNet(opts).cuda()
# Change loading module for single test
net = Sino_repair_net(opts, [0, 1], load_model=True)
net.cuda()
# print(net)
import matplotlib.pylab as plt
import numpy as np
def plot_img(img):
# Pass in the index to read one of the sinogram
fig, ax = plt.subplots(1, 1, figsize=(10, 10))
ax.set_title("Original (Sinogram)")
ax.set_xlabel("Projection position (pixels)")
ax.set_ylabel("Projection angle (deg)")
from __future__ import print_function
import csv
import os
import numpy as np
import tensorflow as tf
import options
import importlib
opt = options.parse()
opt.data = 'stage1' #Defaulting to stage1 data
dl = (importlib.import_module("dataloader." + opt.data)).get_data_loader(opt)
# Dir to save the log
log_dir = "oldLogs/"
model_dir = "cnn10-1/"
if not os.path.exists(log_dir + model_dir):
os.makedirs(os.path.dirname(log_dir + model_dir))
def expand_last_dim(*input_data):
res = []
for in_data in input_data:
res.append(np.expand_dims(in_data, axis=len(in_data.shape)))
if len(res) == 1:
return res[0]
else:
return res
def conv_bn_relu(input, kernel_shape, stride, bias_shape, is_training):
def main(args):
curses.wrapper(CLI(options.parse(args)).run)
import numpy as np
import torch
from IPython import embed
import options as option
from models import create_model
sys.path.insert(0, "../../")
import utils as util
from data import create_dataloader, create_dataset
from data.util import bgr2ycbcr
#### options
parser = argparse.ArgumentParser()
parser.add_argument("-opt", type=str, required=True, help="Path to options YMAL file.")
opt = option.parse(parser.parse_args().opt, is_train=False)
opt = option.dict_to_nonedict(opt)
#### mkdir and logger
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
)
)
os.system("rm ./result")
@app.route('/')
def index():
return flask.templating.render_template('index.html',
transports=transports)
@socketio.on('start')
def start(data):
life = Life.from_file(opts.input_file) \
if opts.input_file \
else Life.random(int(data['height']), int(data['width']))
flask_socketio.emit('generation', life.matrix.tolist())
@socketio.on('next')
def next(grid):
life = Life(grid)
life = life.next(opts.style)
flask_socketio.emit('generation', life.matrix.tolist())
if __name__ == "__main__":
socketio.run(app)
else:
args = sys.argv[sys.argv.index('--') + 1:] \
if '--' in sys.argv \
else sys.argv[1:]
opts = options.parse(args)
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:
print(opt['path'])
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 path is not None))
# 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
trial = 0
while os.path.isdir('../Loggers/' + opt['name'] + '/' + str(trial)):
trial += 1
tb_logger = SummaryWriter(log_dir='../Loggers/' + opt['name'] + '/' + str(trial))
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)
# -------------------------------------------- ADDED --------------------------------------------
l1_loss = torch.nn.L1Loss()
mse_loss = torch.nn.MSELoss()
calc_lpips = PerceptualLossLPIPS()
if torch.cuda.is_available():
l1_loss = l1_loss.cuda()
mse_loss = mse_loss.cuda()
# -----------------------------------------------------------------------------------------------
#### 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.benckmark = 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 = 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)
train_bar = tqdm(train_loader, desc='[%d/%d]' % (epoch, total_epochs))
for bus, train_data in enumerate(train_bar):
# validation
if epoch % opt['train']['val_freq'] == 0 and bus == 0 and rank <= 0:
avg_ssim = avg_psnr = avg_lpips = val_pix_err_f = val_pix_err_nf = val_mean_color_err = 0.0
print("into validation!")
idx = 0
val_bar = tqdm(val_loader, desc='[%d/%d]' % (epoch, total_epochs))
for val_data in val_bar:
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
lq_img = util.tensor2img(visuals['LQ']) # uint8
#nr_img = util.tensor2img(visuals['NR']) # uint8
#nf_img = util.tensor2img(visuals['NF']) # uint8
#nh_img = util.tensor2img(visuals['NH']) # uint8
#print("Great! images got into here.")
# Save SR images for reference
save_sr_img_path = os.path.join(img_dir,
'{:s}_{:d}_sr.png'.format(img_name, current_step))
save_nr_img_path = os.path.join(img_dir,
'{:s}_{:d}_lq.png'.format(img_name, current_step))
#save_nf_img_path = os.path.join(img_dir,
# 'bs_{:s}_{:d}_nr.png'.format(img_name, current_step))
#save_nh_img_path = os.path.join(img_dir,
# 'bs_{:s}_{:d}_nh.png'.format(img_name, current_step))
util.save_img(sr_img, save_sr_img_path)
util.save_img(lq_img, save_nr_img_path)
#util.save_img(nf_img, save_nf_img_path)
#util.save_img(nh_img, save_nh_img_path)
#print("Saved")
# calculate PSNR
gt_img = gt_img / 255.
sr_img = sr_img / 255.
#nf_img = nf_img / 255.
lq_img = lq_img / 255.
#cropped_lq_img = lq_img[crop_size:-crop_size, crop_size:-crop_size, :]
#cropped_nr_img = nr_img[crop_size:-crop_size, crop_size:-crop_size, :]
avg_psnr += util.calculate_psnr(sr_img * 255, gt_img * 255)
avg_ssim += util.calculate_ssim(sr_img * 255, gt_img * 255)
avg_lpips += calc_lpips(visuals['SR'], visuals['GT'])
#avg_psnr_n += util.calculate_psnr(cropped_lq_img * 255, cropped_nr_img * 255)
# ----------------------------------------- ADDED -----------------------------------------
val_pix_err_nf += l1_loss(visuals['SR'], visuals['GT'])
val_mean_color_err += mse_loss(visuals['SR'].mean(2).mean(1), visuals['GT'].mean(2).mean(1))
# -----------------------------------------------------------------------------------------
avg_psnr = avg_psnr / idx
avg_ssim = avg_ssim / idx
avg_lpips = avg_lpips / idx
val_pix_err_f /= idx
val_pix_err_nf /= idx
val_mean_color_err /= idx
# log
logger.info('# Validation # PSNR: {:.4e},'.format(avg_psnr))
logger.info('# Validation # SSIM: {:.4e},'.format(avg_ssim))
logger.info('# Validation # LPIPS: {:.4e},'.format(avg_lpips))
logger_val = logging.getLogger('val') # validation logger
logger_val.info('<epoch:{:3d}, iter:{:8,d}> psnr: {:.4e} ssim: {:.4e} lpips: {:.4e}'.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('val_psnr', avg_psnr, current_step)
tb_logger.add_scalar('val_ssim', avg_ssim, current_step)
tb_logger.add_scalar('val_lpips', avg_lpips, current_step)
tb_logger.add_scalar('val_pix_err_nf', val_pix_err_nf, current_step)
tb_logger.add_scalar('val_mean_color_err', val_mean_color_err, current_step)
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)
model.clear_data()
#### tb_logger
if current_step % opt['logger']['tb_freq'] == 0:
logs = model.get_current_log()
if opt['use_tb_logger'] and 'debug' not in opt['name']:
for k, v in logs.items():
if rank <= 0:
tb_logger.add_scalar(k, v, current_step)
#### logger
if epoch % opt['logger']['print_freq'] == 0 and epoch != 0 and bus == 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)
if rank <= 0:
logger.info(message)
#### save models and training states
if epoch % opt['logger']['save_checkpoint_freq'] == 0 and epoch != 0 and bus == 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.')