def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(
backend="nccl", init_method="env://"
)
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
logger = setup_logger("fcos_core", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg, args.local_rank, args.distributed)
if not args.skip_test:
run_test(cfg, model, args.distributed)
def validation(self, epoch):
# import pdb; pdb.set_trace()
print('Validation of epoch {}:'.format(epoch))
# if self.distributed:
# model = model.module
torch.cuda.empty_cache() # TODO check if it helps
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints", )
# output_folders = [None] * len(cfg.DATASETS.TEST)
# dataset_names = cfg.DATASETS.TEST
# if cfg.OUTPUT_DIR:
# for idx, dataset_name in enumerate(dataset_names):
# output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
# mkdir(output_folder)
# output_folders[idx] = output_folder
dataset_name = cfg.DATASETS.TEST[0]
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
self.val_loader = make_val_loader(cfg)
inference(
self.model,
self.val_loader,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.FCOS_ON or cfg.MODEL.RETINANET_ON else
cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
def run_test(cfg, model, distributed):
if distributed:
model = model.module
torch.cuda.empty_cache() # TODO check if it helps
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints", )
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.FCOS_ON or cfg.MODEL.RETINANET_ON else
cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
def run_test(cfg, model, distributed):
model_test = {}
if distributed:
model_test["backbone"] = model["backbone"].module
model_test["fcos"] = model["fcos"].module
torch.cuda.empty_cache() # TODO check if it helps
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints",)
dataset_name = cfg.DATASETS.TEST[0]
if cfg.OUTPUT_DIR:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
results = inference(
model_test,
data_loaders_val[0],
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.FCOS_ON or cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
results = all_gather(results)
# import pdb; pdb.set_trace()
return results
def run_test(cfg, model, distributed, test_epoch=None):
if distributed:
model = model.module
torch.cuda.empty_cache() # TODO check if it helps
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
inference_result = inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.FCOS_ON or cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
# import pdb; pdb.set_trace()
summaryStrs = get_neat_inference_result(inference_result[2][0])
# print('\n'.join(summaryStrs))
summaryStrFinal = '\n'.join(summaryStrs)
summaryStrFinal = '\n\nEpoch: ' + str(test_epoch) + '\n' + summaryStrFinal
# with open(output_folder+'/summaryStrs.txt', 'w') as f_summaryStrs:
with open(output_folder+'/summaryStrs.txt', 'a') as f_summaryStrs:
f_summaryStrs.write(summaryStrFinal)
def main():
parser = argparse.ArgumentParser(description="Test onnx models of FCOS")
parser.add_argument(
"--config-file",
default="/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--onnx-model",
default="fcos_imprv_R_50_FPN_1x.onnx",
metavar="FILE",
help="path to the onnx model",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
# The onnx model can only be used with DATALOADER.NUM_WORKERS = 0
cfg.DATALOADER.NUM_WORKERS = 0
cfg.freeze()
save_dir = ""
logger = setup_logger("fcos_core", save_dir, get_rank())
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = ONNX_FCOS(args.onnx_model, cfg)
model.to(cfg.MODEL.DEVICE)
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=False)
for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.FCOS_ON or cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("fcos_core", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox", ) + ("segm", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints", )
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.FCOS_ON or cfg.MODEL.SIPMASK_ON
or cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
)
synchronize()
def main():
# 这个就是解析命令行参数，如上面的--config-file configs/fcos/fcos_imprv_R_50_FPN_1x.yaml
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
# 这个参数是torch.distributed.launch传递过来的，我们设置位置参数来接受
# local_rank代表当前程序进程使用的GPU标号
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# 判断机器上GPU的数量，大于1时自动使用分布式训练
# WORLD_SIZE 由torch.distributed.launch.py产生
# 具体数值为 nproc_per_node*node(node就是主机数)
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
# 参数默认是在fcos_core/config/defaults.py中，其余由config_file，opts覆盖
cfg.merge_from_file(args.config_file) # 从yaml文件中读取参数
cfg.merge_from_list(args.opts) # 也可以从命令行参数重写
cfg.freeze() # 冻住参数，为了防止之后被不小心更改，cfg被传入train()
# 可以在这里打印cfg看看，我以fcos_R_50_FPN_1x.yaml为例
output_dir = cfg.OUTPUT_DIR # 创建输出文件夹，存放一些日志信息
if output_dir:
mkdir(output_dir)
# 写入日志文件，包括GPU数量，系统环境，配置文件参数等
logger = setup_logger("fcos_core", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
# 这句话是下一个入口，关注train()方法，里面第一步就是构建模型
model = train(cfg, args.local_rank, args.distributed)
if not args.skip_test:
run_test(cfg, model, args.distributed)
def main():
# 解析命令行参数，例如--config-file
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file", #配置文件
default="",
metavar="FILE",
help="path to config file",
type=str,
)
#此参数是通过torch.distributed.launch传递过来的，我们设置位置参数来接受
# local_rank代表当前程序进程使用的GPU标号
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER, #所有剩余的命令行参数都被收集到一个列表中
)
args = parser.parse_args()
#判断机器上gpu的数量，大于1时自动使用分布式训练
#world_size是由torch.distributed.launch.py产生
# 具体数值为 nproc_per_node*node(node就是主机数)
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1 #判断当前系统环境变量中是否有"WORLD_SIZE" 如果没有num_gpus=1
args.distributed = num_gpus > 1 #False
if args.distributed: #False
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group\
(
backend="nccl", init_method="env://"
)
synchronize()
#yacs的具体用法 可以参考印象笔记
#参数默认在fcos_core/config_defaults.py中 其余参数由config_file opts覆盖
cfg.merge_from_file(args.config_file) #从yaml文件中读取参数 即configs/fcos/fcos_R_50_FPN_1x.yaml
cfg.merge_from_list(args.opts) #也可以从命令行进行参数重写
cfg.freeze() #冻结参数 防止不小心被更改 cfg被传入train()
output_dir = cfg.OUTPUT_DIR #输出模型路径 存放一些日志信息
if output_dir:
mkdir(output_dir) #创建对应的输出路径
#写入日志文件 包括gpu数量，系统环境，配置文件参数等
logger = setup_logger("fcos_core", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg, args.local_rank, args.distributed) #local_rank=0 distributed=False
if not args.skip_test:
run_test(cfg, model, args.distributed)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument("--device_ids", type=list, default=[0])
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"--use-tensorboard",
dest="use_tensorboard",
help="Use tensorboardX logger (Requires tensorboardX installed)",
action="store_true",
default=False)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
# set devices_ids according to num gpus
num_gpus = len(os.environ["CUDA_VISIBLE_DEVICES"].split(","))
args.device_ids = list(map(str, range(num_gpus)))
# do not use torch.distributed
args.distributed = False
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
logger = setup_logger("fad_core", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg,
args.local_rank,
args.distributed,
args.device_ids,
use_tensorboard=args.use_tensorboard)
if not args.skip_test:
run_test(cfg, model, args.distributed)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
args.distributed = num_gpus > 1
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
# add distance loss warmup iters
cfg.SOLVER.MAX_ITER += cfg.MODEL.LABELENC.DISTANCE_LOSS_WARMUP_ITERS
cfg.SOLVER.STEPS = tuple([
i + cfg.MODEL.LABELENC.DISTANCE_LOSS_WARMUP_ITERS
for i in cfg.SOLVER.STEPS
])
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
logger = setup_logger("fcos_core", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
model = train(cfg, args.local_rank, args.distributed)
if not args.skip_test:
run_test(cfg, model, args.distributed)
if args.distributed:
model = model.module
if not args.distributed or dist.get_rank() == 0:
label_encoding_function = model.label_encoding_function.state_dict()
rpn = model.rpn.state_dict()
saved_weights = {
'label_encoding_function': label_encoding_function,
'rpn': rpn
}
if model.roi_heads:
roi_heads = model.roi_heads.state_dict()
saved_weights.update({'roi_heads': roi_heads})
torch.save(saved_weights,
os.path.join(cfg.OUTPUT_DIR, "label_encoding_function.pth"))
logger.info("Successfully save label encoding function weights to " + \
os.path.join(cfg.OUTPUT_DIR, "label_encoding_function.pth"))
synchronize()