obj.dimensions.y = w
obj.dimensions.z = _h
objects_msg.objects.append(obj)
if flag is True:
pub.publish(objects_msg)
stop = timeit.default_timer()
print('Time: ', stop - start)
if __name__ == '__main__':
rospack = rospkg.RosPack()
package_path = rospack.get_path('super_fast_object_detection')
configs = parse_demo_configs()
configs.pretrained_path = package_path + '/checkpoints/fpn_resnet_18/fpn_resnet_18_epoch_300.pth'
model = create_model(configs)
print('\n\n' + '-*=' * 30 + '\n\n')
assert os.path.isfile(configs.pretrained_path), "No file at {}".format(
configs.pretrained_path)
model.load_state_dict(
torch.load(configs.pretrained_path, map_location='cuda:0'))
print('Loaded weights from {}\n'.format(configs.pretrained_path))
configs.device = torch.device(
'cpu' if configs.no_cuda else 'cuda:{}'.format(configs.gpu_idx))
model = model.to(device=configs.device)
model.eval()
print("Started Node")
rospy.init_node('SuperFastObjectDetection', anonymous=True)
pub = rospy.Publisher('detected_objects',
DetectedObjectArray,
def main_worker(gpu_idx, configs):
configs.gpu_idx = gpu_idx
configs.device = torch.device('cpu' if configs.gpu_idx is None else 'cuda:{}'.format(configs.gpu_idx))
if configs.distributed:
if configs.dist_url == "env://" and configs.rank == -1:
configs.rank = int(os.environ["RANK"])
if configs.multiprocessing_distributed:
# For multiprocessing distributed training, rank needs to be the
# global rank among all the processes
configs.rank = configs.rank * configs.ngpus_per_node + gpu_idx
dist.init_process_group(backend=configs.dist_backend, init_method=configs.dist_url,
world_size=configs.world_size, rank=configs.rank)
configs.subdivisions = int(64 / configs.batch_size / configs.ngpus_per_node)
else:
configs.subdivisions = int(64 / configs.batch_size)
configs.is_master_node = (not configs.distributed) or (
configs.distributed and (configs.rank % configs.ngpus_per_node == 0))
if configs.is_master_node:
logger = Logger(configs.logs_dir, configs.saved_fn)
logger.info('>>> Created a new logger')
logger.info('>>> configs: {}'.format(configs))
tb_writer = SummaryWriter(log_dir=os.path.join(configs.logs_dir, 'tensorboard'))
else:
logger = None
tb_writer = None
# model
model = create_model(configs)
# load weight from a checkpoint
if configs.pretrained_path is not None:
assert os.path.isfile(configs.pretrained_path), "=> no checkpoint found at '{}'".format(configs.pretrained_path)
model.load_state_dict(torch.load(configs.pretrained_path, map_location='cpu'))
if logger is not None:
logger.info('loaded pretrained model at {}'.format(configs.pretrained_path))
# resume weights of model from a checkpoint
if configs.resume_path is not None:
assert os.path.isfile(configs.resume_path), "=> no checkpoint found at '{}'".format(configs.resume_path)
model.load_state_dict(torch.load(configs.resume_path, map_location='cpu'))
if logger is not None:
logger.info('resume training model from checkpoint {}'.format(configs.resume_path))
# Data Parallel
model = make_data_parallel(model, configs)
# Make sure to create optimizer after moving the model to cuda
optimizer = create_optimizer(configs, model)
lr_scheduler = create_lr_scheduler(optimizer, configs)
configs.step_lr_in_epoch = False if configs.lr_type in ['multi_step', 'cosin', 'one_cycle'] else True
# resume optimizer, lr_scheduler from a checkpoint
if configs.resume_path is not None:
utils_path = configs.resume_path.replace('Model_', 'Utils_')
assert os.path.isfile(utils_path), "=> no checkpoint found at '{}'".format(utils_path)
utils_state_dict = torch.load(utils_path, map_location='cuda:{}'.format(configs.gpu_idx))
optimizer.load_state_dict(utils_state_dict['optimizer'])
lr_scheduler.load_state_dict(utils_state_dict['lr_scheduler'])
configs.start_epoch = utils_state_dict['epoch'] + 1
if configs.is_master_node:
num_parameters = get_num_parameters(model)
logger.info('number of trained parameters of the model: {}'.format(num_parameters))
if logger is not None:
logger.info(">>> Loading dataset & getting dataloader...")
# Create dataloader
train_dataloader, train_sampler = create_train_dataloader(configs)
if logger is not None:
logger.info('number of batches in training set: {}'.format(len(train_dataloader)))
if configs.evaluate:
val_dataloader = create_val_dataloader(configs)
val_loss = validate(val_dataloader, model, configs)
print('val_loss: {:.4e}'.format(val_loss))
return
for epoch in range(configs.start_epoch, configs.num_epochs + 1):
if logger is not None:
logger.info('{}'.format('*-' * 40))
logger.info('{} {}/{} {}'.format('=' * 35, epoch, configs.num_epochs, '=' * 35))
logger.info('{}'.format('*-' * 40))
logger.info('>>> Epoch: [{}/{}]'.format(epoch, configs.num_epochs))
if configs.distributed:
train_sampler.set_epoch(epoch)
# train for one epoch
train_one_epoch(train_dataloader, model, optimizer, lr_scheduler, epoch, configs, logger, tb_writer)
if (not configs.no_val) and (epoch % configs.checkpoint_freq == 0):
val_dataloader = create_val_dataloader(configs)
print('number of batches in val_dataloader: {}'.format(len(val_dataloader)))
val_loss = validate(val_dataloader, model, configs)
print('val_loss: {:.4e}'.format(val_loss))
if tb_writer is not None:
tb_writer.add_scalar('Val_loss', val_loss, epoch)
# Save checkpoint
if configs.is_master_node and ((epoch % configs.checkpoint_freq) == 0):
model_state_dict, utils_state_dict = get_saved_state(model, optimizer, lr_scheduler, epoch, configs)
save_checkpoint(configs.checkpoints_dir, configs.saved_fn, model_state_dict, utils_state_dict, epoch)
if not configs.step_lr_in_epoch:
lr_scheduler.step()
if tb_writer is not None:
tb_writer.add_scalar('LR', lr_scheduler.get_lr()[0], epoch)
if tb_writer is not None:
tb_writer.close()
if configs.distributed:
cleanup()