def main():
opt = OptInit().get_args()
logging.info('===> Creating dataloader ...')
train_dataset = GeoData.S3DIS(opt.data_dir,
opt.area,
True,
pre_transform=T.NormalizeScale())
train_loader = DenseDataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=4)
test_dataset = GeoData.S3DIS(opt.data_dir,
opt.area,
train=False,
pre_transform=T.NormalizeScale())
test_loader = DenseDataLoader(test_dataset,
batch_size=opt.batch_size,
shuffle=False,
num_workers=0)
opt.n_classes = train_loader.dataset.num_classes
logging.info('===> Loading the network ...')
model = DenseDeepGCN(opt).to(opt.device)
if opt.multi_gpus:
model = DataParallel(DenseDeepGCN(opt)).to(opt.device)
logging.info('===> loading pre-trained ...')
model, opt.best_value, opt.epoch = load_pretrained_models(
model, opt.pretrained_model, opt.phase)
logging.info(model)
logging.info('===> Init the optimizer ...')
criterion = torch.nn.CrossEntropyLoss().to(opt.device)
optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, opt.lr_adjust_freq,
opt.lr_decay_rate)
optimizer, scheduler, opt.lr = load_pretrained_optimizer(
opt.pretrained_model, optimizer, scheduler, opt.lr)
logging.info('===> Init Metric ...')
opt.losses = AverageMeter()
opt.test_value = 0.
logging.info('===> start training ...')
for _ in range(opt.epoch, opt.total_epochs):
opt.epoch += 1
logging.info('Epoch:{}'.format(opt.epoch))
train(model, train_loader, optimizer, scheduler, criterion, opt)
if opt.epoch % opt.eval_freq == 0 and opt.eval_freq != -1:
test(model, test_loader, opt)
scheduler.step()
logging.info('Saving the final model.Finish!')
def main():
opt = OptInit().get_args()
logging.info('===> Creating dataloader...')
test_dataset = GeoData.S3DIS(opt.data_dir,
opt.area,
train=False,
pre_transform=T.NormalizeScale())
test_loader = DenseDataLoader(test_dataset,
batch_size=opt.batch_size,
shuffle=False,
num_workers=0)
opt.n_classes = test_loader.dataset.num_classes
if opt.no_clutter:
opt.n_classes -= 1
logging.info('===> Loading the network ...')
model = DenseDeepGCN(opt).to(opt.device)
model, opt.best_value, opt.epoch = load_pretrained_models(
model, opt.pretrained_model, opt.phase)
logging.info('===> Start Evaluation ...')
test(model, test_loader, opt)
filename = '{}/{}_model.pth'.format(opt.ckpt_dir,
opt.jobname + '-' + name_post)
model_cpu = {k: v.cpu() for k, v in model.state_dict().items()}
state = {
'epoch': opt.epoch,
'state_dict': model_cpu,
'optimizer_state_dict': optimizer.state_dict(),
'scheduler_state_dict': scheduler.state_dict(),
'best_value': opt.best_value,
}
torch.save(state, filename)
logging.info('save a new best model into {}'.format(filename))
if __name__ == '__main__':
opt = OptInit()._get_args()
logging.info('===> Creating dataloader ...')
train_dataset = PartNet(opt.data_dir, 'sem_seg_h5', opt.category,
opt.level, 'train')
train_loader = DenseDataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=8)
test_dataset = PartNet(opt.data_dir, 'sem_seg_h5', opt.category, opt.level,
'test')
test_loader = DenseDataLoader(test_dataset,
batch_size=opt.test_batch_size,
shuffle=False,
num_workers=8)
def main():
opt = OptInit().get_args()
logging.info('===> Creating dataloader ...')
train_dataset = GeoData.S3DIS(opt.data_dir,
opt.area,
True,
pre_transform=T.NormalizeScale())
train_loader = DenseDataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=4)
test_dataset = GeoData.S3DIS(opt.data_dir,
opt.area,
train=False,
pre_transform=T.NormalizeScale())
test_loader = DenseDataLoader(test_dataset,
batch_size=opt.batch_size,
shuffle=False,
num_workers=0)
opt.n_classes = train_loader.dataset.num_classes
logging.info('===> Loading the network ...')
model = DenseDeepGCN(opt).to(opt.device)
if opt.multi_gpus:
model = DataParallel(DenseDeepGCN(opt)).to(opt.device)
logging.info('===> loading pre-trained ...')
model, opt.best_value, opt.epoch = load_pretrained_models(
model, opt.pretrained_model, opt.phase)
logging.info(model)
logging.info('===> Init the optimizer ...')
criterion = torch.nn.CrossEntropyLoss().to(opt.device)
optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, opt.lr_adjust_freq,
opt.lr_decay_rate)
optimizer, scheduler, opt.lr = load_pretrained_optimizer(
opt.pretrained_model, optimizer, scheduler, opt.lr)
logging.info('===> Init Metric ...')
opt.losses = AverageMeter()
opt.test_value = 0.
logging.info('===> start training ...')
for _ in range(opt.epoch, opt.total_epochs):
opt.epoch += 1
logging.info('Epoch:{}'.format(opt.epoch))
train(model, train_loader, optimizer, criterion, opt)
if opt.epoch % opt.eval_freq == 0 and opt.eval_freq != -1:
test(model, test_loader, opt)
scheduler.step()
# ------------------ save checkpoints
# min or max. based on the metrics
is_best = (opt.test_value < opt.best_value)
opt.best_value = max(opt.test_value, opt.best_value)
model_cpu = {k: v.cpu() for k, v in model.state_dict().items()}
save_checkpoint(
{
'epoch': opt.epoch,
'state_dict': model_cpu,
'optimizer_state_dict': optimizer.state_dict(),
'scheduler_state_dict': scheduler.state_dict(),
'best_value': opt.best_value,
}, is_best, opt.ckpt_dir, opt.exp_name)
# ------------------ tensorboard log
info = {
'loss': opt.losses.avg,
'test_value': opt.test_value,
'lr': scheduler.get_lr()[0]
}
opt.writer.add_scalars('epoch', info, opt.iter)
logging.info('Saving the final model.Finish!')
cur_shape_iou_tot += I/U
cur_shape_iou_cnt += 1.
if cur_shape_iou_cnt > 0:
cur_shape_miou = cur_shape_iou_tot / cur_shape_iou_cnt
shape_iou_tot += cur_shape_miou
shape_iou_cnt += 1.
shape_mIoU = shape_iou_tot / shape_iou_cnt
part_iou = np.divide(part_intersect[1:], part_union[1:])
mean_part_iou = np.mean(part_iou)
logging.info("===> Finish Testing! Category {}-{}, Part mIOU is {:.4f} \n\n\n ".format(
opt.category_no, opt.category, mean_part_iou))
if __name__ == '__main__':
opt = OptInit()._get_args()
logging.info('===> Creating dataloader ...')
test_dataset = PartNet(opt.data_dir, 'sem_seg_h5', opt.category, opt.level, 'test')
test_loader = DenseDataLoader(test_dataset, batch_size=1, shuffle=True, num_workers=1)
opt.n_classes = test_loader.dataset.num_classes
logging.info('===> Loading the network ...')
model = DeepGCN(opt).to(opt.device)
logging.info('===> loading pre-trained ...')
model, opt.best_value, opt.epoch = load_pretrained_models(model, opt.pretrained_model, opt.phase)
test(model, test_loader, opt)
filename = '{}/{}_model.pth'.format(opt.ckpt_dir,
opt.jobname + '-' + name_post)
model_cpu = {k: v.cpu() for k, v in model.state_dict().items()}
state = {
'epoch': opt.epoch,
'state_dict': model_cpu,
'optimizer_state_dict': optimizer.state_dict(),
'scheduler_state_dict': scheduler.state_dict(),
'best_value': opt.best_value,
}
torch.save(state, filename)
logging.info('save a new best model into {}'.format(filename))
if __name__ == '__main__':
opt = OptInit()._get_args()
logging.info('===> Creating dataloader ...')
train_loader = DataLoader(ModelNet40(data_dir=opt.data_dir,
partition='train',
num_points=opt.num_points),
num_workers=8,
batch_size=opt.batch_size,
shuffle=True,
drop_last=True)
test_loader = DataLoader(ModelNet40(data_dir=opt.data_dir,
partition='test',
num_points=opt.num_points),
num_workers=8,
batch_size=opt.test_batch_size,
shuffle=True,
