def main():
# torch.manual_seed(0)
# torch.backends.cudnn.deterministic = True
# torch.backends.cudnn.benchmark = False
# np.random.seed(0)
args = parse_args()
cfg = Config.fromfile(args.config)
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
distributed = torch.cuda.device_count() > 1
if distributed:
if args.launcher == "pytorch":
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl", init_method="env://")
cfg.local_rank = args.local_rank
elif args.launcher == "slurm":
proc_id = int(os.environ["SLURM_PROCID"])
ntasks = int(os.environ["SLURM_NTASKS"])
node_list = os.environ["SLURM_NODELIST"]
num_gpus = torch.cuda.device_count()
cfg.gpus = num_gpus
torch.cuda.set_device(proc_id % num_gpus)
addr = subprocess.getoutput(
f"scontrol show hostname {node_list} | head -n1")
# specify master port
port = None
if port is not None:
os.environ["MASTER_PORT"] = str(port)
elif "MASTER_PORT" in os.environ:
pass # use MASTER_PORT in the environment variable
else:
# 29500 is torch.distributed default port
os.environ["MASTER_PORT"] = "29501"
# use MASTER_ADDR in the environment variable if it already exists
if "MASTER_ADDR" not in os.environ:
os.environ["MASTER_ADDR"] = addr
os.environ["WORLD_SIZE"] = str(ntasks)
os.environ["LOCAL_RANK"] = str(proc_id % num_gpus)
os.environ["RANK"] = str(proc_id)
dist.init_process_group(backend="nccl")
cfg.local_rank = int(os.environ["LOCAL_RANK"])
cfg.gpus = torch.distributed.get_world_size()
else:
cfg.gpus = args.gpus
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info("Distributed testing: {}".format(distributed))
logger.info(f"torch.backends.cudnn.benchmark: {torch.backends.cudnn.benchmark}")
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
if args.testset:
print("Use Test Set")
dataset = build_dataset(cfg.data.test)
else:
print("Use Val Set")
dataset = build_dataset(cfg.data.val)
data_loader = build_dataloader(
dataset,
batch_size=cfg.data.samples_per_gpu if not args.speed_test else 1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
)
checkpoint = load_checkpoint(model, args.checkpoint, map_location="cpu")
# put model on gpus
if distributed:
# model = apex.parallel.convert_syncbn_model(model)
model = DistributedDataParallel(
model.cuda(cfg.local_rank),
device_ids=[cfg.local_rank],
output_device=cfg.local_rank,
# broadcast_buffers=False,
find_unused_parameters=True,
)
else:
# model = fuse_bn_recursively(model)
model = model.cuda()
model.eval()
mode = "val"
prog_bar = None
logger.info(f"work dir: {args.work_dir}")
if cfg.local_rank == 0:
prog_bar = torchie.ProgressBar(len(data_loader.dataset) // cfg.gpus)
detections = {}
cpu_device = torch.device("cpu")
start = time.time()
start = int(len(dataset) / 3)
end = int(len(dataset) * 2 /3)
time_start = 0
time_end = 0
for i, data_batch in enumerate(data_loader):
if i == start:
torch.cuda.synchronize()
time_start = time.time()
if i == end:
torch.cuda.synchronize()
time_end = time.time()
with torch.no_grad():
outputs = batch_processor(
model, data_batch, train_mode=False, local_rank=args.local_rank,
)
for output in outputs:
token = output["metadata"]["token"]
for k, v in output.items():
if k not in [
"metadata",
]:
output[k] = v.to(cpu_device)
detections.update(
{token: output,}
)
if args.local_rank == 0:
if prog_bar is not None:
prog_bar.update()
synchronize()
all_predictions = all_gather(detections)
print("\n Total time per frame: ", (time_end - time_start) / (end - start))
if args.local_rank != 0:
return
predictions = {}
for p in all_predictions:
predictions.update(p)
if not os.path.exists(args.work_dir):
os.makedirs(args.work_dir)
save_pred(predictions, args.work_dir)
result_dict, _ = dataset.evaluation(copy.deepcopy(predictions), output_dir=args.work_dir, testset=args.testset)
if result_dict is not None:
for k, v in result_dict["results"].items():
print(f"Evaluation {k}: {v}")
if args.txt_result:
assert False, "No longer support kitti"
def main():
# torch.manual_seed(0)
# torch.backends.cudnn.deterministic = True
# torch.backends.cudnn.benchmark = False
# np.random.seed(0)
args = parse_args()
cfg = Config.fromfile(args.config)
cfg.local_rank = args.local_rank
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
distributed = False
if "WORLD_SIZE" in os.environ:
distributed = int(os.environ["WORLD_SIZE"]) > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
cfg.gpus = torch.distributed.get_world_size()
else:
cfg.gpus = args.gpus
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info("Distributed testing: {}".format(distributed))
logger.info(
f"torch.backends.cudnn.benchmark: {torch.backends.cudnn.benchmark}")
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
if args.testset:
print("Use Test Set")
dataset = build_dataset(cfg.data.test)
else:
print("Use Val Set")
dataset = build_dataset(cfg.data.val)
data_loader = build_dataloader(
dataset,
batch_size=cfg.data.samples_per_gpu if not args.speed_test else 1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
)
checkpoint = load_checkpoint(model, args.checkpoint, map_location="cpu")
# put model on gpus
if distributed:
model = apex.parallel.convert_syncbn_model(model)
model = DistributedDataParallel(
model.cuda(cfg.local_rank),
device_ids=[cfg.local_rank],
output_device=cfg.local_rank,
# broadcast_buffers=False,
find_unused_parameters=True,
)
else:
# model = fuse_bn_recursively(model)
model = model.cuda()
model.eval()
mode = "val"
logger.info(f"work dir: {args.work_dir}")
if cfg.local_rank == 0:
prog_bar = torchie.ProgressBar(len(data_loader.dataset) // cfg.gpus)
detections = {}
cpu_device = torch.device("cpu")
start = time.time()
start = int(len(dataset) / 3)
end = int(len(dataset) * 2 / 3)
time_start = 0
time_end = 0
for i, data_batch in enumerate(data_loader):
if i == start:
torch.cuda.synchronize()
time_start = time.time()
if i == end:
torch.cuda.synchronize()
time_end = time.time()
with torch.no_grad():
outputs = batch_processor(
model,
data_batch,
train_mode=False,
local_rank=args.local_rank,
)
for output in outputs:
token = output["metadata"]["token"]
for k, v in output.items():
if k not in [
"metadata",
]:
output[k] = v.to(cpu_device)
detections.update({
token: output,
})
if args.local_rank == 0:
prog_bar.update()
synchronize()
all_predictions = all_gather(detections)
print("\n Total time per frame: ", (time_end - time_start) / (end - start))
if args.local_rank != 0:
return
predictions = {}
for p in all_predictions:
predictions.update(p)
if not os.path.exists(args.work_dir):
os.makedirs(args.work_dir)
save_pred(predictions, args.work_dir)
with open(os.path.join(args.work_dir, 'prediction.pkl'), 'rb') as f:
predictions = pickle.load(f)
result_dict, _ = dataset.evaluation(copy.deepcopy(predictions),
output_dir=args.work_dir,
testset=args.testset)
if result_dict is not None:
for k, v in result_dict["results"].items():
print(f"Evaluation {k}: {v}")
if args.txt_result:
assert False, "No longer support kitti"
def main():
# torch.manual_seed(0)
# torch.backends.cudnn.deterministic = True
# torch.backends.cudnn.benchmark = False
# np.random.seed(0)
args = parse_args()
cfg = Config.fromfile(args.config)
cfg.local_rank = args.local_rank
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
distributed = False
if "WORLD_SIZE" in os.environ:
distributed = int(os.environ["WORLD_SIZE"]) > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
cfg.gpus = torch.distributed.get_world_size()
else:
cfg.gpus = args.gpus
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info("Distributed testing: {}".format(distributed))
logger.info(
f"torch.backends.cudnn.benchmark: {torch.backends.cudnn.benchmark}")
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
dataset = build_dataset(cfg.data.val)
data_loader = build_dataloader(
dataset,
batch_size=cfg.data.samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
)
checkpoint = load_checkpoint(model, args.checkpoint, map_location="cpu")
# put model on gpus
if distributed:
model = apex.parallel.convert_syncbn_model(model)
model = DistributedDataParallel(
model.cuda(cfg.local_rank),
device_ids=[cfg.local_rank],
output_device=cfg.local_rank,
# broadcast_buffers=False,
find_unused_parameters=True,
)
else:
model = model.cuda()
model.eval()
mode = "val"
logger.info(f"work dir: {args.work_dir}")
if cfg.local_rank == 0:
prog_bar = torchie.ProgressBar(len(data_loader.dataset) // cfg.gpus)
detections = {}
cpu_device = torch.device("cpu")
for i, data_batch in enumerate(data_loader):
with torch.no_grad():
outputs = batch_processor(
model,
data_batch,
train_mode=False,
local_rank=args.local_rank,
)
for output in outputs:
token = output["metadata"]["token"]
for k, v in output.items():
if k not in [
"metadata",
]:
output[k] = v.to(cpu_device)
detections.update({
token: output,
})
if args.local_rank == 0:
prog_bar.update()
synchronize()
all_predictions = all_gather(detections)
if args.local_rank != 0:
return
predictions = {}
for p in all_predictions:
predictions.update(p)
result_dict, _ = dataset.evaluation(predictions, output_dir=args.work_dir)
for k, v in result_dict["results"].items():
print(f"Evaluation {k}: {v}")
if args.txt_result:
res_dir = os.path.join(os.getcwd(), "predictions")
for k, dt in predictions.items():
with open(
os.path.join(res_dir,
"%06d.txt" % int(dt["metadata"]["token"])),
"w") as fout:
lines = kitti.annos_to_kitti_label(dt)
for line in lines:
fout.write(line + "\n")
ap_result_str, ap_dict = kitti_evaluate(
"/data/Datasets/KITTI/Kitti/object/training/label_2",
res_dir,
label_split_file="/data/Datasets/KITTI/Kitti/ImageSets/val.txt",
current_class=0,
)
print(ap_result_str)
def main():
# torch.manual_seed(0)
# torch.backends.cudnn.deterministic = True
# torch.backends.cudnn.benchmark = False
# np.random.seed(0)
args = parse_args()
cfg = Config.fromfile(args.config)
cfg.local_rank = args.local_rank
# update configs according to CLI args
if args.work_dir is not None:
cfg.work_dir = args.work_dir
distributed = False
if "WORLD_SIZE" in os.environ:
distributed = int(os.environ["WORLD_SIZE"]) > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
cfg.gpus = torch.distributed.get_world_size()
else:
cfg.gpus = args.gpus
# init logger before other steps
logger = get_root_logger(cfg.log_level)
logger.info("Distributed testing: {}".format(distributed))
logger.info(
f"torch.backends.cudnn.benchmark: {torch.backends.cudnn.benchmark}")
torch.cuda.empty_cache()
model = build_detector(cfg.nohead_model,
train_cfg=None,
test_cfg=cfg.test_cfg)
if args.testset:
print("Use Test Set")
dataset = build_dataset(cfg.data.test)
else:
print("Use Val Set")
dataset = build_dataset(cfg.data.val)
data_loader = build_dataloader(
dataset,
batch_size=cfg.data.samples_per_gpu if not args.speed_test else 1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
)
checkpoint = load_checkpoint(model, args.checkpoint, map_location="cpu")
# put model on gpus
# model = fuse_bn_recursively(model)
model = model.cuda()
model.eval()
mode = "val"
logger.info(f"work dir: {args.work_dir}")
if cfg.local_rank == 0:
prog_bar = torchie.ProgressBar(len(data_loader.dataset) // cfg.gpus)
detections = {}
cpu_device = torch.device("cpu")
start = time.time()
start = int(len(dataset) / 3)
end = int(len(dataset) * 2 / 3)
time_start = 0
time_end = 0
device = torch.device(args.local_rank)
POINTS_NUM = 2
for i, data_batch in enumerate(data_loader):
if i == start:
torch.cuda.synchronize()
time_start = time.time()
if i == end:
torch.cuda.synchronize()
time_end = time.time()
with torch.no_grad():
sample = example_to_device(data_batch, device=device)
for i in range(len(sample["metadata"])):
sample["metadata"][i]['image_prefix'] = None
del sample["metadata"]
del sample["points"]
#del sample["shape"]
sample["shape"] = torch.tensor(sample["shape"])
sample["voxels"] = sample["voxels"][0:POINTS_NUM, :, :]
sample["num_points"] = sample["num_points"][0:POINTS_NUM]
sample["coordinates"] = sample["coordinates"][0:POINTS_NUM, :]
outputs = model(sample, return_loss=False)
#outputs = batch_processor(
# model, data_batch, train_mode=False, local_rank=args.local_rank,
#)
for k, t in sample.items():
print("====", k)
print(t.shape)
print("============== start =============")
register_custom_op_symbolic("spconv::get_indice_pairs_3d",
symbolic_get_indice_pairs_3d, 11)
torch.onnx.export(
model, # model being run
sample, # model input (or a tuple for multiple inputs)
"/workspace/data/center_point.onnx", # where to save the model (can be a file or file-like object)
export_params=
True, # store the trained parameter weights inside the model file
opset_version=11, # the ONNX version to export the model to
do_constant_folding=True
) # whether to execute constant folding for optimization
print("============== finish =============")
break
for output in outputs:
token = output["metadata"]["token"]
for k, v in output.items():
if k not in [
"metadata",
]:
output[k] = v.to(cpu_device)
detections.update({
token: output,
})
if args.local_rank == 0:
prog_bar.update()
synchronize()
all_predictions = all_gather(detections)
print("\n Total time per frame: ", (time_end - time_start) / (end - start))
if args.local_rank != 0:
return
predictions = {}
for p in all_predictions:
predictions.update(p)
if not os.path.exists(args.work_dir):
os.makedirs(args.work_dir)
save_pred(predictions, args.work_dir)
result_dict, _ = dataset.evaluation(copy.deepcopy(predictions),
output_dir=args.work_dir,
testset=args.testset)
if result_dict is not None:
for k, v in result_dict["results"].items():
print(f"Evaluation {k}: {v}")
if args.txt_result:
assert False, "No longer support kitti"