def main_worker(cfg):
# create tensorboard and logs
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
tb_logdir = build_log_dir(cfg)
writer = SummaryWriter(log_dir=tb_logdir)
else:
writer = None
cfg.freeze()
# create model
model = get_model(cfg)
model = deploy_model(model, cfg)
# create dataset and dataloader
test_loader = build_dataloader_test(cfg)
eval_path = cfg.CONFIG.LOG.EVAL_DIR
if not os.path.exists(eval_path):
os.makedirs(eval_path)
criterion = nn.CrossEntropyLoss().cuda()
file = os.path.join(eval_path, str(cfg.DDP_CONFIG.GPU_WORLD_RANK) + '.txt')
test_classification(model, test_loader, criterion, cfg, file)
torch.distributed.barrier()
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
print("Start merging results...")
merge(eval_path, cfg)
else:
print(cfg.DDP_CONFIG.GPU_WORLD_RANK, "Evaluation done!")
def main_worker(cfg):
# create tensorboard and logs
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
tb_logdir = build_log_dir(cfg)
writer = SummaryWriter(log_dir=tb_logdir)
else:
writer = None
cfg.freeze()
# create model
model = get_model(cfg)
model = deploy_model(model, cfg)
# create dataset and dataloader
val_loader, _ = build_dataloader_val(cfg)
if cfg.CONFIG.MODEL.LOAD:
model, _ = load_model(model, cfg, load_fc=True)
criterion = nn.CrossEntropyLoss().cuda()
# adversarial_classification(model, val_loader, -1, criterion, cfg, writer)
validation_classification(model, val_loader, -1, criterion, cfg, writer)
if writer is not None:
writer.close()
def main_worker(cfg):
# create tensorboard and logs
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
tb_logdir = build_log_dir(cfg)
writer = SummaryWriter(log_dir=tb_logdir)
else:
writer = None
cfg.freeze()
# create model
model = get_model(cfg)
model = deploy_model(model, cfg)
# create dataset and dataloader
train_loader, val_loader, train_sampler, val_sampler, mg_sampler = build_dataloader(
cfg)
optimizer = torch.optim.SGD(model.parameters(),
lr=cfg.CONFIG.TRAIN.LR,
momentum=cfg.CONFIG.TRAIN.MOMENTUM,
weight_decay=cfg.CONFIG.TRAIN.W_DECAY)
if cfg.CONFIG.MODEL.LOAD:
model, _ = load_model(model, optimizer, cfg, load_fc=True)
scheduler = torch.optim.lr_scheduler.MultiStepLR(
optimizer,
milestones=cfg.CONFIG.TRAIN.LR_MILESTONE,
gamma=cfg.CONFIG.TRAIN.STEP)
criterion = nn.CrossEntropyLoss().cuda()
base_iter = 0
for epoch in range(cfg.CONFIG.TRAIN.EPOCH_NUM):
if cfg.DDP_CONFIG.DISTRIBUTED:
train_sampler.set_epoch(epoch)
base_iter = train_classification(base_iter,
model,
train_loader,
epoch,
criterion,
optimizer,
cfg,
writer=writer)
scheduler.step()
if epoch % cfg.CONFIG.VAL.FREQ == 0 or epoch == cfg.CONFIG.TRAIN.EPOCH_NUM - 1:
validation_classification(model, val_loader, epoch, criterion, cfg,
writer)
if epoch % cfg.CONFIG.LOG.SAVE_FREQ == 0:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
save_model(model, optimizer, epoch, cfg)
if writer is not None:
writer.close()
def main_worker(cfg):
# create tensorboard and logs
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
tb_logdir = build_log_dir(cfg)
writer = SummaryWriter(log_dir=tb_logdir)
else:
writer = None
cfg.freeze()
# create model
# model = get_model(cfg)
model = directpose_resnet_lpf_fpn(cfg)
model = deploy_model(model, cfg)
# create dataset and dataloader
# train_loader, val_loader, train_sampler, val_sampler, mg_sampler = build_pose_train_loader(cfg)
train_loader = build_pose_train_loader(cfg)
val_loader = build_pose_test_loader(cfg, cfg.CONFIG.DATA.DATASET.VAL[0])
optimizer = build_pose_optimizer(cfg, model)
scheduler = build_lr_scheduler(cfg, optimizer)
# if cfg.CONFIG.MODEL.LOAD:
# model, _ = load_model(model, optimizer, cfg, load_fc=True)
# criterion = nn.CrossEntropyLoss().cuda()
pipeline = DirectposePipeline(0,
cfg.CONFIG.TRAIN.ITER_NUM,
model,
train_loader,
optimizer,
scheduler,
cfg,
writer=writer)
while pipeline.base_iter < pipeline.max_iter:
pipeline.train_step()
if pipeline.base_iter % cfg.CONFIG.VAL.EVAL_PERIOD == 0 or pipeline.base_iter == pipeline.max_iter:
pipeline.validate(val_loader)
if pipeline.base_iter % cfg.CONFIG.TRAIN.CHECKPOINT_PERIOD == 0:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
pipeline.save_model()
if writer is not None:
writer.close()
def main_worker(cfg):
# create tensorboard and logs
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
tb_logdir = build_log_dir(cfg)
writer = SummaryWriter(log_dir=tb_logdir)
else:
writer = None
cfg.freeze()
logger = get_logger(tb_logdir, "trainer", log_file=True)
# create model
model = get_model(cfg)
model = deploy_model(model, cfg)
# create dataset and dataloader
data_path_dict = create_dataloader_path(
cfg.CONFIG.COOT_DATA.DATA_PATH,
cfg.CONFIG.COOT_DATA.DATASET_NAME,
video_feature_name=cfg.CONFIG.COOT_DATA.FEATURE)
train_set, val_set = create_datasets(data_path_dict, cfg,
cfg.CONFIG.COOT_DATA.VIDEO_PRELOAD,
cfg.CONFIG.COOT_DATA.TEXT_PRELOAD)
train_loader, val_loader = create_loaders(train_set, val_set,
cfg.CONFIG.TRAIN.BATCH_SIZE,
cfg.CONFIG.DATA.NUM_WORKERS)
optimizer = RAdam(model.get_params(),
lr=cfg.CONFIG.TRAIN.LR,
betas=(cfg.CONFIG.TRAIN.MOMENTUM,
cfg.CONFIG.TRAIN.ADAM_BETA2),
eps=cfg.CONFIG.TRAIN.ADAM_EPS,
weight_decay=cfg.CONFIG.TRAIN.W_DECAY)
if cfg.CONFIG.MODEL.LOAD:
model, _ = load_model(model, optimizer, cfg, load_fc=True)
if cfg.CONFIG.TRAIN.LR_POLICY == 'Step':
scheduler = torch.optim.lr_scheduler.MultiStepLR(
optimizer,
milestones=cfg.CONFIG.TRAIN.LR_MILESTONE,
gamma=cfg.CONFIG.TRAIN.STEP)
elif cfg.CONFIG.TRAIN.LR_POLICY == 'Cosine':
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer,
T_max=cfg.CONFIG.TRAIN.EPOCH_NUM - cfg.CONFIG.TRAIN.WARMUP_EPOCHS,
eta_min=0,
last_epoch=cfg.CONFIG.TRAIN.RESUME_EPOCH)
elif cfg.CONFIG.TRAIN.LR_POLICY == 'LR_Warmup':
scheduler = ReduceLROnPlateauWarmup(optimizer,
cfg.CONFIG.TRAIN.WARMUP_EPOCHS,
mode="max",
patience=cfg.CONFIG.TRAIN.PATIENCE,
cooldown=cfg.CONFIG.TRAIN.COOLDOWN)
else:
print(
'Learning rate schedule %s is not supported yet. Please use Step or Cosine.'
)
criterion_cycleconsistency = CycleConsistencyCootLoss(num_samples=1,
use_cuda=True)
criterion_alignment = MaxMarginRankingLoss(use_cuda=True)
base_iter = 0
det_best_field_best = 0
for epoch in range(cfg.CONFIG.TRAIN.EPOCH_NUM):
## ======== Training step ===============
base_iter = train_coot(cfg, base_iter, model, train_loader, epoch,
criterion_alignment, criterion_cycleconsistency,
optimizer, writer, logger)
## ======= Validation step ================
if epoch % cfg.CONFIG.VAL.FREQ == 0 or epoch == cfg.CONFIG.TRAIN.EPOCH_NUM - 1:
vid_metrics, clip_metrics = validate_coot(
cfg, model, val_loader, epoch, criterion_alignment,
criterion_cycleconsistency, writer, logger, True)
# Check if the performance of model is improving
logger.info("---------- Validating epoch {} ----------".format(epoch))
c2s_res, s2c_res, clip_best_at_1 = None, None, None
if clip_metrics is not None:
c2s_res, s2c_res, clip_best_at_1 = clip_metrics
# find field which determines is_best
det_best_field_current = clip_best_at_1
# check if best
is_best = compare_metrics(det_best_field_current, det_best_field_best)
if is_best:
det_best_field_best = det_best_field_current
best_epoch = epoch
# step lr scheduler
scheduler.step_rop(det_best_field_current, True)
logger.info(f"ROP: model improved: {is_best}, "
f"value {det_best_field_current:.3f},"
f"new LR: {optimizer.param_groups[0]['lr']:5.3e}")
if epoch % cfg.CONFIG.LOG.SAVE_FREQ == 0:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
model.save_model(optimizer, epoch, cfg)
# check if model did not improve for too long
term_after = 15
if epoch - best_epoch > term_after:
logger.info(f"NO improvements for {term_after} epochs (current "
f"{epoch} best {best_epoch}) STOP training.")
break
if writer is not None:
writer.close()
if logger is not None:
close_logger(logger)
def main_worker(cfg):
# create tensorboard and logs
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0:
tb_logdir = build_log_dir(cfg)
writer = SummaryWriter(log_dir=tb_logdir)
else:
writer = None
cfg.freeze()
# create model
model = get_model(cfg)
model = deploy_model(model, cfg)
# create dataset and dataloader
train_loader, val_loader, train_sampler, val_sampler, mg_sampler = build_dataloader(
cfg)
optimizer = torch.optim.SGD(model.parameters(),
lr=cfg.CONFIG.TRAIN.LR,
momentum=cfg.CONFIG.TRAIN.MOMENTUM,
weight_decay=cfg.CONFIG.TRAIN.W_DECAY)
if cfg.CONFIG.MODEL.LOAD:
model, _ = load_model(model, optimizer, cfg, load_fc=True)
if cfg.CONFIG.TRAIN.LR_POLICY == 'Step':
scheduler = torch.optim.lr_scheduler.MultiStepLR(
optimizer,
milestones=cfg.CONFIG.TRAIN.LR_MILESTONE,
gamma=cfg.CONFIG.TRAIN.STEP)
elif cfg.CONFIG.TRAIN.LR_POLICY == 'Cosine':
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer,
T_max=cfg.CONFIG.TRAIN.EPOCH_NUM - cfg.CONFIG.TRAIN.WARMUP_EPOCHS,
eta_min=0,
last_epoch=cfg.CONFIG.TRAIN.RESUME_EPOCH)
else:
print(
'Learning rate schedule %s is not supported yet. Please use Step or Cosine.'
)
if cfg.CONFIG.TRAIN.USE_WARMUP:
scheduler_warmup = GradualWarmupScheduler(
optimizer,
multiplier=(cfg.CONFIG.TRAIN.WARMUP_END_LR / cfg.CONFIG.TRAIN.LR),
total_epoch=cfg.CONFIG.TRAIN.WARMUP_EPOCHS,
after_scheduler=scheduler)
criterion = nn.CrossEntropyLoss().cuda()
base_iter = 0
for epoch in range(cfg.CONFIG.TRAIN.EPOCH_NUM):
if cfg.DDP_CONFIG.DISTRIBUTED:
train_sampler.set_epoch(epoch)
base_iter = train_classification(base_iter,
model,
train_loader,
epoch,
criterion,
optimizer,
cfg,
writer=writer)
if cfg.CONFIG.TRAIN.USE_WARMUP:
scheduler_warmup.step()
else:
scheduler.step()
if cfg.CONFIG.TRAIN.MULTIGRID.USE_LONG_CYCLE:
if epoch in cfg.CONFIG.TRAIN.MULTIGRID.LONG_CYCLE_EPOCH:
mg_sampler.step_long_cycle()
if epoch % cfg.CONFIG.VAL.FREQ == 0 or epoch == cfg.CONFIG.TRAIN.EPOCH_NUM - 1:
validation_classification(model, val_loader, epoch, criterion, cfg,
writer)
if epoch % cfg.CONFIG.LOG.SAVE_FREQ == 0:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
save_model(model, optimizer, epoch, cfg)
if writer is not None:
writer.close()
