##### get model version and data version
exp_name = cfg.config.split('/')[-1][:-5]
model_name = exp_name.split('_')[0]
data_name = exp_name.split('_')[-1]
##### model
logger.info('=> creating model ...')
logger.info('Classes: {}'.format(cfg.classes))
if model_name == 'pointgroup':
from model.pointgroup.pointgroup import PointGroup as Network
from model.pointgroup.pointgroup import model_fn_decorator
else:
print("Error: no model version " + model_name)
exit(0)
model = Network(cfg)
use_cuda = torch.cuda.is_available()
logger.info('cuda available: {}'.format(use_cuda))
assert use_cuda
model = model.cuda()
# logger.info(model)
logger.info('#classifier parameters (model): {}'.format(
sum([x.nelement() for x in model.parameters()])))
##### model_fn (criterion)
model_fn = model_fn_decorator(test=True)
##### load model
utils.checkpoint_restore(
exp_name = cfg.config.split('/')[-1][:-5]
model_name = exp_name.split('_')[0]
data_name = exp_name.split('_')[-1]
cfg.dataset='train_weakly'
##### model
#logger.info('=> creating model ...')
##logger.info('Classes: {}'.format(cfg.classes))
if model_name == 'pointgroup':
from model.pointgroup.pointgroup import PointGroup as Network
from model.pointgroup.pointgroup import model_fn_decorator
else:
print("Error: no model version " + model_name)
exit(0)
model = Network(cfg)
use_cuda = torch.cuda.is_available()
#logger.info('cuda available: {}'.format(use_cuda))
assert use_cuda
model = model.cuda()
# logger.info(model)
#logger.info('#classifier parameters (model): {}'.format(sum([x.nelement() for x in model.parameters()])))
##### model_fn (criterion)
model_fn = model_fn_decorator(test=True)
##### load model
utils.checkpoint_restore(model, cfg.exp_path, cfg.config.split('/')[-1][:-5], use_cuda, cfg.test_epoch, dist=False, f=cfg.pretrain) # resume from the latest epoch, or specify the epoch to restore
##### get model version and data version
exp_name = cfg.config.split('/')[-1][:-5]
model_name = exp_name.split('_')[0]
data_name = exp_name.split('_')[-1]
##### model
logger.info('=> creating model ...')
logger.info('Classes: {}'.format(cfg.classes))
if model_name == 'pointgroup':
from model.pointgroup.pointgroup import PointGroup as Network
from model.pointgroup.pointgroup import model_fn_decorator
else:
print("Error: no model version " + model_name)
exit(0)
model = Network(cfg)
use_cuda = torch.cuda.is_available()
logger.info('cuda available: {}'.format(use_cuda))
assert use_cuda
model = model.cuda()
# logger.info(model)
logger.info('#classifier parameters (model): {}'.format(sum([x.nelement() for x in model.parameters()])))
##### model_fn (criterion)
model_fn = model_fn_decorator(test=True)
##### load model
utils.checkpoint_restore(model, cfg.exp_path, cfg.config.split('/')[-1][:-5], use_cuda, cfg.test_epoch, dist=False, f=cfg.pretrain) # resume from the latest epoch, or specify the epoch to restore
##### get model version and data version
exp_name = cfg.config.split('/')[-1][:-5]
model_name = exp_name.split('_')[0]
data_name = exp_name.split('_')[-1]
##### model
logger.info('=> creating model ...')
if model_name == 'pointgroup':
from model.pointgroup.pointgroup import PointGroup as Network
from model.pointgroup.pointgroup import model_fn_decorator
else:
print("Error: no model - " + model_name)
exit(0)
model = Network(cfg)
use_cuda = torch.cuda.is_available()
logger.info('cuda available: {}'.format(use_cuda))
assert use_cuda
model = model.cuda()
# logger.info(model)
logger.info('#classifier parameters: {}'.format(sum([x.nelement() for x in model.parameters()])))
##### optimizer
if cfg.optim == 'Adam':
optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr=cfg.lr)
elif cfg.optim == 'SGD':
optimizer = optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=cfg.lr, momentum=cfg.momentum, weight_decay=cfg.weight_decay)