def main():
# Create Model, Criterion and State
model, criterion, state = create_model(args)
print("=> Model and criterion are ready")
# Create Dataloader
if not args.test_only:
train_loader = get_train_loader(args)
val_loader = get_test_loader(args)
print("=> Dataloaders are ready")
# Create Logger
logger = Logger(args, state)
print("=> Logger is ready") # Create Trainer
trainer = Trainer(args, model, criterion, logger)
print("=> Trainer is ready")
if args.test_only:
test_summary = trainer.test(0, val_loader)
print("- Test: Acc %6.3f " % (test_summary['acc']))
else:
start_epoch = logger.state['epoch'] + 1
print("=> Start training")
# test_summary = trainer.test(0, val_loader)
for epoch in range(start_epoch, args.n_epochs + 1):
train_summary = trainer.train(epoch, train_loader)
test_summary = trainer.test(epoch, val_loader)
logger.record(epoch, train_summary, test_summary, model)
logger.final_print()
def eval_ckpt():
parser = argparse.ArgumentParser()
parser.add_argument("config_paths", nargs="+", help="path to config.yaml")
parser.add_argument("--weight", help="path to weight to evaluate.pth")
parser.add_argument("--result_dir", help="path to save the result file")
args, left_argv = parser.parse_known_args()
cfg = Config(*args.config_paths, default="cfgs/defaults.yaml")
cfg.argv_update(left_argv)
img_dir = Path(args.result_dir)
img_dir.mkdir(parents=True, exist_ok=True)
trn_transform, val_transform = setup_transforms(cfg)
g_kwargs = cfg.get('g_args', {})
gen = Generator(1, cfg.C, 1, **g_kwargs).cuda()
weight = torch.load(args.weight)
if "generator_ema" in weight:
weight = weight["generator_ema"]
gen.load_state_dict(weight)
test_dset, test_loader = get_test_loader(cfg, val_transform)
for batch in test_loader:
style_imgs = batch["style_imgs"].cuda()
char_imgs = batch["source_imgs"].unsqueeze(1).cuda()
out = gen.gen_from_style_char(style_imgs, char_imgs)
fonts = batch["fonts"]
chars = batch["chars"]
for image, font, char in zip(refine(out), fonts, chars):
(img_dir / font).mkdir(parents=True, exist_ok=True)
path = img_dir / font / f"{char}.png"
save_tensor_to_image(image, path)
def get_test_max_landmark_of_one_model(config, gi, best_model_idx, key_group):
test_img_list = gen_test_csv()
print('test_img_list ', len(test_img_list))
# result_set_whole = {}
# for img_id in test_img_list:
#初始化添加
# result_set_whole[img_id] = {}
test_data_set = get_test_loader(config, test_img_list,
get_transform(config, 'val'))
model = get_model(config, gi)
if torch.cuda.is_available():
model = model.cuda()
optimizer = get_optimizer(config, model.parameters())
checkpoint = utils.checkpoint.get_model_saved(config, gi, best_model_idx)
best_epoch, step = utils.checkpoint.load_checkpoint(
model, optimizer, checkpoint)
result_set = test_one_model(test_data_set, model, key_group)
#
result_list_whole = []
for img_ps in result_set.keys():
ps = result_set[img_ps]
max_p_key = max(ps, key=ps.get)
# result_set_whole[img_ps][max_p_key] = ps[max_p_key]
result_list_whole.append((img_ps, max_p_key, ps[max_p_key]))
test_pd = pd.DataFrame.from_records(
result_list_whole, columns=['img_id', 'landmark_id', 'pers'])
output_filename = os.path.join('./results/test/',
'test_img_land_' + str(gi) + '.csv')
test_pd.to_csv(output_filename, index=False)
return
def main():
'''
01, 02 - 2D spatial (images)
03, 04 - 3D geometric (3D images)
05, 06 - 3D temporal (3D optical flow)
07, 08 - 3D temporal (3D optical flow - no augmentation)
09, 10 - 2D temporal (2D optical flow)
------ If time:
- 2-stream concatenate lstm output
- 2-stream svm classifier
'''
print_config()
# Get network
net = torch.nn.DataParallel(NEURAL_NET).cuda()
# Get dataloaders
train_loader = get_train_loader()
test_loader = get_test_loader()
# Set up optimizer with auto-adjusting learning rate
parameters = [p for p in net.parameters() if p.requires_grad]
optimizer = optim.Adam(parameters, lr=0.001)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.5)
# Train
for epoch in range(NUM_EPOCHS):
scheduler.step()
train_acc = training_epoch(net, optimizer, epoch, train_loader)
# Checkpoint results
model_file = 'torch_models/torch_model_experiment_{:02}_epoch_{:02}'.format(
EXPERIMENT_NUM, epoch)
torch.save(net.state_dict(), model_file)
# net.load_state_dict(torch.load(model_file))
# valid_acc = test_epoch(net, test_loader, desc="Validation (epoch {:02})".format(epoch))
# print('Epoch {:02} top-1 validation accuracy: {:.1f}%'.format(epoch, valid_acc))
# Save results
model_file = 'torch_models/torch_model_experiment_{:02}'.format(
EXPERIMENT_NUM)
torch.save(net.state_dict(), model_file)
# Test
# net.load_state_dict(torch.load('torch_models/torch_model_experiment_{:02}'.format(EXPERIMENT_NUM)))
test_acc = test_epoch(net, test_loader, desc="Testing")
print('Experiment {:02} test-set accuracy: {:.2f}%'.format(
EXPERIMENT_NUM, test_acc))
for tta in ttas:
logger.info("#" * 20)
logger.info(tta["name"])
_config = config.copy()
_config["transforms"]["valid"] = [tta]
val_loader = datasets.get_train_loader(val_df,
tp,
fp,
train_audio,
_config,
phase="valid")
_config["transforms"]["test"] = [tta]
loader = datasets.get_test_loader(test_all, test_audio, _config)
if config["inference"]["prediction_type"] == "strong":
##################################################
# OOF #
##################################################
logger.info("*" * 20)
logger.info(f"OOF prediction for fold{i}")
logger.info("*" * 20)
recording_ids = []
batch_predictions = []
indices = []
for batch in tqdm(val_loader, leave=True):
recording_ids.extend(batch["recording_id"])
indices.extend(batch["index"].numpy())
input_ = batch[global_params["input_key"]].to(device)
}
},
"loader": {
"valid": {
"batch_size": 1,
"shuffle": False,
"num_workers": 20
},
"test": {
"batch_size": 1,
"shuffle": False,
"num_workers": 20
}
}
}
soft_test_loader = datasets.get_test_loader(
test_all, test_audio, soft_inference_config)
soft_oof_dir = expdir / "soft_oof"
soft_oof_dir.mkdir(exist_ok=True, parents=True)
soft_prediction_dir = expdir / "soft_prediction"
soft_prediction_dir.mkdir(exist_ok=True, parents=True)
soft_predictions = {}
# validation
splitter = training.get_split(config)
##################################################
# Main Loop #
##################################################
input_size = args.input_size
train_transform = get_train_transforms(input_size)
valid_transform = get_valid_transforms(input_size)
if args.dataset == "JRDR":
dataset_dir = os.path.join("data", "JRDR")
test_dir = os.path.join("data", "JRDR")
train_data = JRDR(root=dataset_dir, transform=train_transform)
valid_data = JRDR(root=dataset_dir, transform=valid_transform)
test_data = JRDR(root=test_dir, split="test", transform=valid_transform)
else:
raise NotImplementedError(args.dataset)
train_loader, valid_loader = get_train_valid_loader(train_data,
valid_data,
show_sample=False)
test_loader = get_test_loader(test_data)
model = DerainCNNModular(
input_size=input_size,
channel_mul=args.channel_mul,
depth=args.depth,
center_depth=args.center_depth,
attention_type=args.attention_type,
reduction=args.reduction,
lr=args.lr,
gamma=args.gamma,
)
exp_id = os.path.join(args.dataset, args.id)
logdir = args.logdir
checkpoints_dir = _logdir_high / "checkpoints"
checkpoints_dir.mkdir(exist_ok=True, parents=True)
train_writer = SummaryWriter(log_dir=_logdir_high / "train_log")
valid_writer = SummaryWriter(log_dir=_logdir_high / "valid_log")
config["dataset"]["train"]["params"]["frequency_range"] = "high"
config["dataset"]["valid"]["params"]["frequency_range"] = "high"
config["dataset"]["test"]["params"]["frequency_range"] = "high"
loaders = {
phase: datasets.get_train_loader(df_, tp, fp, train_audio, config,
phase)
for df_, phase in zip([trn_df, val_df], ["train", "valid"])
}
test_loader = datasets.get_test_loader(test_all, test_audio, config)
soft_inference_config = {
"loader": {
"test": {
"batch_size": 1,
"shuffle": False,
"num_workers": config["loader"]["test"]["num_workers"]
}
},
"dataset": {
"test": {
"name": "LimitedFrequencySampleWiseSpectrogramTestDataset",
"params": config["dataset"]["test"]["params"]
}
},