def fuse_conv(self):
self.conv_3x3 = fuse_conv_bn(self.conv_3x3)
self.conv_1x1 = fuse_conv_bn(self.conv_1x1)
# self.conv = nn.ModuleList([self.conv_kxk_fuse, self.conv_kx1_fuse, self.conv_1xk_fuse])
self.conv_3x3.conv.weight[:, :, self.kernel_size //
2:self.kernel_size // 2 + 1,
self.kernel_size // 2:self.kernel_size // 2 +
1] += self.conv_1x1.conv.weight
self.conv_3x3.conv.bias = torch.nn.Parameter(self.conv_1x1.conv.bias +
self.conv_3x3.conv.bias)
if self.stride == 1 and self.in_ch == self.out_ch:
short_cut_weight = torch.nn.Parameter(
torch.eye(self.in_ch).reshape(
self.in_ch, self.in_ch, 1,
1)).to(self.conv_3x3.conv.weight.device)
self.conv_3x3.conv.weight[:, :, self.kernel_size //
2:self.kernel_size // 2 + 1,
self.kernel_size //
2:self.kernel_size // 2 +
1] += short_cut_weight
self.conv = nn.ModuleList([self.conv_3x3])
def fuse_conv(self):
self.conv_kxk = fuse_conv_bn(self.conv_kxk)
self.conv_kx1 = fuse_conv_bn(self.conv_kx1)
self.conv_1xk = fuse_conv_bn(self.conv_1xk)
# self.conv = nn.ModuleList([self.conv_kxk_fuse, self.conv_kx1_fuse, self.conv_1xk_fuse])
self.conv_kxk.conv.weight[:, :,
self.kernel_size // 2:self.kernel_size // 2 +
1, :] += self.conv_1xk.conv.weight
self.conv_kxk.conv.weight[:, :, :,
self.kernel_size // 2:self.kernel_size // 2 +
1] += self.conv_kx1.conv.weight
self.conv = nn.ModuleList([self.conv_kxk])
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
model = MMDataParallel(model, device_ids=[0])
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
# benchmark with 2000 image and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, rescale=True, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Done image [{i + 1:<3}/ 2000], fps: {fps:.1f} img / s')
if (i + 1) == 2000:
pure_inf_time += elapsed
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Overall fps: {fps:.1f} img / s')
break
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.backbone.pretrained = None
cfg.data.test.test_mode = True
# build the dataloader
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
data_loader = build_dataloader(
dataset,
videos_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
model = build_model(
cfg.model, train_cfg=None, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
model = MMDataParallel(model, device_ids=[0])
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
# benchmark with 2000 video and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(
f'Done video [{i + 1:<3}/ 2000], fps: {fps:.1f} video / s')
if (i + 1) == 200:
pure_inf_time += elapsed
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Overall fps: {fps:.1f} video / s')
break
def inference_pytorch(args, cfg, distributed, data_loader):
"""Get predictions by pytorch models."""
# remove redundant pretrain steps for testing
turn_off_pretrained(cfg.model)
# build the model and load checkpoint
model = build_model(cfg.model,
train_cfg=None,
test_cfg=cfg.get('test_cfg'))
if len(cfg.module_hooks) > 0:
register_module_hooks(model, cfg.module_hooks)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
return outputs
def __init__(self,
config,
ckpt_path=None,
cudnn_benchmark=False,
fp16=False,
enable_fuse_conv_bn=False):
self.config = config
self.fp16 = fp16
self.cudnn_benchmark = cudnn_benchmark
self.enable_fuse_conv_bn = enable_fuse_conv_bn
if isinstance(config, str):
cfg = Config.fromfile(config)
cfg.model.backbone.pretrained = None
self._model_name = _mmaction2_config_to_model_name(cfg.model)
self.model = mmaction2_build_model(cfg.model,
train_cfg=None,
test_cfg=cfg.get('test_cfg'))
elif isinstance(config, dict):
self.model = mmaction2_build_model(config, None, None)
# get model name
self._model_name = _mmaction2_config_to_model_name(config)
else:
raise ValueError({f"Unknown config {config}"})
if ckpt_path is not None:
load_checkpoint(self.model, ckpt_path, map_location='cpu')
if cudnn_benchmark:
torch.backends.cudnn.benchmark = True
if fp16:
wrap_fp16_model(self.model)
if enable_fuse_conv_bn:
self.model = fuse_conv_bn(self.model)
self.model.cuda().eval()
def test_fuse_conv_bn():
inputs = torch.rand((1, 3, 5, 5))
modules = nn.ModuleList()
modules.append(nn.BatchNorm2d(3))
modules.append(ConvModule(3, 5, 3, norm_cfg=dict(type='BN')))
modules.append(ConvModule(5, 5, 3, norm_cfg=dict(type='BN')))
modules = nn.Sequential(*modules)
fused_modules = fuse_conv_bn(modules)
assert torch.equal(modules(inputs), fused_modules(inputs))
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# build the dataloader
dataset = build_dataset(cfg.data.val)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
model = build_posenet(cfg.model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
model = MMDataParallel(model, device_ids=[0])
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
# benchmark with total batch and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
its = (i + 1 - num_warmup) / pure_inf_time
print(f'Done item [{i + 1:<3}], {its:.2f} items / s')
print(f'Overall average: {its:.2f} items / s')
print(f'Total time: {pure_inf_time:.2f} s')
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if cfg.get('USE_MMDET', False):
from mmdet.apis import multi_gpu_test, single_gpu_test
from mmdet.datasets import build_dataloader
from mmdet.models import build_detector as build_model
if 'detector' in cfg.model:
cfg.model = cfg.model.detector
elif cfg.get('TRAIN_REID', False):
from mmdet.apis import multi_gpu_test, single_gpu_test
from mmdet.datasets import build_dataloader
from mmtrack.models import build_reid as build_model
if 'reid' in cfg.model:
cfg.model = cfg.model.reid
else:
from mmtrack.apis import multi_gpu_test, single_gpu_test
from mmtrack.datasets import build_dataloader
from mmtrack.models import build_model
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# cfg.model.pretrains = None
if hasattr(cfg.model, 'detector'):
cfg.model.detector.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
if cfg.get('test_cfg', False):
model = build_model(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
else:
model = build_model(cfg.model)
# We need call `init_weights()` to load pretained weights in MOT task.
model.init_weights()
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.checkpoint is not None:
checkpoint = load_checkpoint(model,
args.checkpoint,
map_location='cpu')
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
if not hasattr(model, 'CLASSES'):
model.CLASSES = dataset.CLASSES
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model,
data_loader,
args.show,
args.show_dir,
show_score_thr=args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
eval_hook_args = [
'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
'rule', 'by_epoch'
]
for key in eval_hook_args:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
print(dataset.evaluate(outputs, **eval_kwargs))
def posenet(pretrained=False,
arch='litehrnet_30_coco_384x288',
model_dir=None,
force_reload=False,
unload_after=False,
**kwargs):
"""
Kwargs:
pretrained(bool, str): True for official checkpoint or path(str) to load a custom checkpoint
tag(str): git repo tag to explicitly specify a particular commit
url(str): direct url to download checkpoint
s3(dict): S3 source containing bucket and key to download a checkpoint from
threshold(float):
"""
ARCH = dict(litehrnet_18_coco_256x192='1ZewlvpncTvahbqcCFb-95C3NHet30mk5',
litehrnet_18_coco_384x288='1E3S18YbUfBm7YtxYOV7I9FmrntnlFKCp',
litehrnet_30_coco_256x192='1KLjNInzFfmZWSbEQwx-zbyaBiLB7SnEj',
litehrnet_30_coco_384x288='1BcHnLka4FWiXRmPnJgJKmsSuXXqN4dgn',
litehrnet_18_mpii_256x256='1bcnn5Ic2-FiSNqYOqLd1mOfQchAz_oCf',
litehrnet_30_mpii_256x256='1JB9LOwkuz5OUtry0IQqXammFuCrGvlEd')
tag = kwargs.get('tag', GITHUB['tag'])
modules = sys.modules.copy()
entry = 'posenet'
m = None
try:
logging.info(f"Creating '{entry}(arch={arch})'")
m = hub.load(github(tag=tag), entry, arch, force_reload=force_reload)
m.tag = tag
if pretrained:
if isinstance(pretrained, bool):
# official pretrained
state_dict = from_pretrained(f"{entry}.pt",
force_reload=force_reload,
gdrive=dict(id=ARCH[arch]))
else:
# custom checkpoint
path = Path(pretrained)
if not path.exists():
path = f"{hub.get_dir()}/{pretrained}"
state_dict = io.load(path, map_location='cpu')
state_dict = {
k: v
for k, v in state_dict.items()
if m.state_dict()[k].shape == v.shape
}
# load_checkpoint(model, path, map_location='cpu')
m.load_state_dict(state_dict, strict=True)
logging.info(f"kwargs={kwargs}")
if kwargs.get('fp16', False):
from mmpose.core import wrap_fp16_model
wrap_fp16_model(m)
logging.info(f"[posnet] wrapped in fp16")
if kwargs.get('fuse_conv_bn', True):
from mmcv.cnn import fuse_conv_bn
m = fuse_conv_bn(m)
logging.info(f"[posenet] fused conv and bn")
except Exception as e:
logging.error(f"Failed to load '{entry}': {e}")
raise e
finally:
# XXX Remove newly imported modules in case of conflict with next load
if unload_after:
for module in sys.modules.keys() - modules.keys():
del sys.modules[module]
m.to('cpu')
return m
def measure_inference_speed(cfg, checkpoint, max_iter, log_interval,
is_fuse_conv_bn):
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
# Because multiple processes will occupy additional CPU resources,
# FPS statistics will be more unstable when workers_per_gpu is not 0.
# It is reasonable to set workers_per_gpu to 0.
workers_per_gpu=0,
dist=True,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, checkpoint, map_location='cpu')
if is_fuse_conv_bn:
model = fuse_conv_bn(model)
model = MMDistributedDataParallel(model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
fps = 0
# benchmark with 2000 image and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, rescale=True, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(
f'Done image [{i + 1:<3}/ {max_iter}], '
f'fps: {fps:.1f} img / s, '
f'times per image: {1000 / fps:.1f} ms / img',
flush=True)
if (i + 1) == max_iter:
fps = (i + 1 - num_warmup) / pure_inf_time
print(
f'Overall fps: {fps:.1f} img / s, '
f'times per image: {1000 / fps:.1f} ms / img',
flush=True)
break
return fps
def main():
args = parse_args()
cfg = mmcv.Config.fromfile(args.config)
if args.update_config is not None:
cfg.merge_from_dict(args.update_config)
cfg = update_config(cfg, args)
cfg = propagate_root_dir(cfg, args.data_dir)
# Load output_config from cfg
output_config = cfg.get('output_config', {})
# Overwrite output_config from args.out
output_config = merge_configs(output_config, dict(out=args.out))
# Load eval_config from cfg
eval_config = cfg.get('eval_config', {})
# Overwrite eval_config from args.eval
eval_config = merge_configs(eval_config, dict(metrics=args.eval))
# Add options from args.option
eval_config = merge_configs(eval_config, args.options)
assert output_config or eval_config, \
('Please specify at least one operation (save or eval the '
'results) with the argument "--out" or "--eval"')
# init distributed env first, since logger depends on the dist info.
distributed = args.launcher != 'none'
if distributed:
init_dist(args.launcher, **cfg.dist_params)
# get rank
rank, _ = get_dist_info()
if cfg.get('seed'):
print(f'Set random seed to {cfg.seed}')
set_random_seed(cfg.seed)
# build the dataset
dataset = build_dataset(cfg.data, 'test', dict(test_mode=True))
if cfg.get('classes'):
dataset = dataset.filter(cfg.classes)
if rank == 0:
print(f'Test datasets:\n{str(dataset)}')
# build the dataloader
data_loader = build_dataloader(dataset,
videos_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_model(cfg.model,
train_cfg=None,
test_cfg=cfg.test_cfg,
class_sizes=dataset.class_sizes,
class_maps=dataset.class_maps)
# nncf model wrapper
if is_checkpoint_nncf(args.checkpoint) and not cfg.get('nncf_config'):
# reading NNCF config from checkpoint
nncf_part = get_nncf_config_from_meta(args.checkpoint)
for k, v in nncf_part.items():
cfg[k] = v
if cfg.get('nncf_config'):
check_nncf_is_enabled()
if not is_checkpoint_nncf(args.checkpoint):
raise RuntimeError(
'Trying to make testing with NNCF compression a model snapshot that was NOT trained with NNCF'
)
cfg.load_from = args.checkpoint
cfg.resume_from = None
if torch.cuda.is_available():
model = model.cuda()
_, model = wrap_nncf_model(model, cfg, None, get_fake_input)
else:
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
# load model weights
load_checkpoint(model,
args.checkpoint,
map_location='cpu',
force_matching=True)
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
if rank == 0:
if output_config:
out = output_config['out']
print(f'\nwriting results to {out}')
dataset.dump_results(outputs, **output_config)
if eval_config:
eval_res = dataset.evaluate(outputs, **eval_config)
print('\nFinal metrics:')
for name, val in eval_res.items():
if 'invalid_info' in name:
continue
if isinstance(val, float):
print(f'{name}: {val:.04f}')
elif isinstance(val, str):
print(f'{name}:\n{val}')
else:
print(f'{name}: {val}')
invalid_info = {
name: val
for name, val in eval_res.items() if 'invalid_info' in name
}
if len(invalid_info) > 0:
assert args.out_invalid is not None and args.out_invalid != ''
if os.path.exists(args.out_invalid):
shutil.rmtree(args.out_invalid)
if not os.path.exists(args.out_invalid):
os.makedirs(args.out_invalid)
for name, invalid_record in invalid_info.items():
out_invalid_dir = os.path.join(args.out_invalid, name)
item_gen = zip(invalid_record['ids'],
invalid_record['conf'],
invalid_record['pred'])
for invalid_idx, pred_conf, pred_label in item_gen:
record_info = dataset.get_info(invalid_idx)
gt_label = record_info['label']
if 'filename' in record_info:
src_data_path = record_info['filename']
in_record_name, record_extension = os.path.basename(
src_data_path).split('.')
out_record_name = f'{in_record_name}_gt{gt_label}_pred{pred_label}_conf{pred_conf:.3f}'
trg_data_path = os.path.join(
out_invalid_dir,
f'{out_record_name}.{record_extension}')
shutil.copyfile(src_data_path, trg_data_path)
else:
src_data_path = record_info['frame_dir']
in_record_name = os.path.basename(src_data_path)
out_record_name = f'{in_record_name}_gt{gt_label}_pred{pred_label}_conf{pred_conf:.3f}'
trg_data_path = os.path.join(
out_invalid_dir, out_record_name)
os.makedirs(trg_data_path)
start_frame_id = record_info[
'clip_start'] + dataset.start_index
end_frame_id = record_info[
'clip_end'] + dataset.start_index
for frame_id in range(start_frame_id,
end_frame_id):
img_name = f'{frame_id:05}.jpg'
shutil.copyfile(
os.path.join(src_data_path, img_name),
os.path.join(trg_data_path, img_name))
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
cfg.merge_from_dict(args.cfg_options)
# Load output_config from cfg
output_config = cfg.get('output_config', {})
# Overwrite output_config from args.out
output_config = merge_configs(output_config, dict(out=args.out))
# Load eval_config from cfg
eval_config = cfg.get('eval_config', {})
# Overwrite eval_config from args.eval
eval_config = merge_configs(eval_config, dict(metrics=args.eval))
# Add options from args.option
eval_config = merge_configs(eval_config, args.options)
assert output_config or eval_config, \
('Please specify at least one operation (save or eval the '
'results) with the argument "--out" or "--eval"')
# set cudnn benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.data.test.test_mode = True
if cfg.test_cfg is None:
cfg.test_cfg = dict(average_clips=args.average_clips)
else:
# You can set average_clips during testing, it will override the
# original settting
if args.average_clips is not None:
cfg.test_cfg.average_clips = args.average_clips
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# build the dataloader
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
dataloader_setting = dict(videos_per_gpu=cfg.data.get('videos_per_gpu', 2),
workers_per_gpu=cfg.data.get(
'workers_per_gpu', 0),
dist=distributed,
shuffle=False)
dataloader_setting = dict(dataloader_setting,
**cfg.data.get('test_dataloader', {}))
data_loader = build_dataloader(dataset, **dataloader_setting)
# build the model and load checkpoint
model = build_model(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if output_config:
out = output_config['out']
print(f'\nwriting results to {out}')
dataset.dump_results(outputs, **output_config)
if eval_config:
eval_res = dataset.evaluate(outputs, **eval_config)
for name, val in eval_res.items():
print(f'{name}: {val:.04f}')
def main():
args = parse_args()
assert (
args.out or args.eval or args.format_only or args.show
or args.show_dir), (
'Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir".')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified.')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if cfg.model.get('pretrained'):
cfg.model.pretrained = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# in case the test dataset is concatenated
samples_per_gpu = 1
if isinstance(cfg.data.test, dict):
samples_per_gpu = (cfg.data.get('test_dataloader', {})).get(
'samples_per_gpu', cfg.data.get('samples_per_gpu', 1))
if samples_per_gpu > 1:
# Support batch_size > 1 in test for text recognition
# by disable MultiRotateAugOCR since it is useless for most case
cfg = disable_text_recog_aug_test(cfg)
if cfg.data.test.get('pipeline', None) is not None:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(
cfg.data.test.pipeline)
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
samples_per_gpu = max(
[ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test])
if samples_per_gpu > 1:
for ds_cfg in cfg.data.test:
ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
# step 1: give default values and override (if exist) from cfg.data
loader_cfg = {
**dict(seed=cfg.get('seed'), drop_last=False, dist=distributed),
**({} if torch.__version__ != 'parrots' else dict(
prefetch_num=2,
pin_memory=False,
)),
**dict((k, cfg.data[k]) for k in [
'workers_per_gpu',
'seed',
'prefetch_num',
'pin_memory',
'persistent_workers',
] if k in cfg.data)
}
test_loader_cfg = {
**loader_cfg,
**dict(shuffle=False, drop_last=False),
**cfg.data.get('test_dataloader', {}),
**dict(samples_per_gpu=samples_per_gpu)
}
data_loader = build_dataloader(dataset, **test_loader_cfg)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
model = revert_sync_batchnorm(model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
is_kie = cfg.model.type in ['SDMGR']
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
is_kie, args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in [
'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
'rule'
]:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
print(dataset.evaluate(outputs, **eval_kwargs))
def main():
args = parse_args()
print('#'*100)
print(args)
print('#'*100)
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# in case the test dataset is concatenated
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
######################################################################
print(cfg.pretty_text)
#######################################################################
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
############################################################
if args.eval_options \
and 'load_results' in args.eval_options.keys() \
and args.eval_options['load_results']:
import pickle as pkl
with open(str(args.out), 'rb') as f:
outputs = pkl.load(f)
else:
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
############################################################
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in ['interval', 'tmpdir', 'start', 'gpu_collect']:
eval_kwargs.pop(key, None)
######################################
# from mmdet.utils import collect_env, get_root_logger
# import os.path as osp
# import time
# timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
# log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
# logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
# eval_kwargs['logger'] = True
################### 很多信息从kwargs，也就是eval_options中得到#################
work_dir = os.path.split(str(args.out))[0]
if args.eval_options and 'eval_results_path' in args.eval_options.keys():
eval_results_path = os.path.split(args.eval_options['eval_results_path'])[1]
eval_results_path = os.path.join(work_dir, eval_results_path)
else:
eval_results_path = os.path.join(work_dir, 'eval_results.txt')
print('#'*80, '\n', 'EVALUATE ReSULTS PATH: %s\n' % eval_results_path, '#'*80, '\n')
kwargs = {}
# eval_kwargs['classwise'] = True
# eval_kwargs['proposal_nums'] = (100, 300, 1000)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
s = str(dataset.evaluate(outputs, **eval_kwargs))
with open(eval_results_path, 'wt+') as f:
f.write(str(s))
print(s)
data_loader = build_dataloader(
dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set multi-process settings
setup_multi_processes(cfg)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# work_dir is determined in this priority: CLI > segment in file > filename
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
# step 1: give default values and override (if exist) from cfg.data
loader_cfg = {
**dict(seed=cfg.get('seed'), drop_last=False, dist=distributed),
**({} if torch.__version__ != 'parrots' else dict(
prefetch_num=2,
pin_memory=False,
)),
**dict((k, cfg.data[k]) for k in [
'seed',
'prefetch_num',
'pin_memory',
'persistent_workers',
] if k in cfg.data)
}
# step2: cfg.data.test_dataloader has higher priority
test_loader_cfg = {
**loader_cfg,
**dict(shuffle=False, drop_last=False),
**dict(workers_per_gpu=cfg.data.get('workers_per_gpu', 1)),
**dict(samples_per_gpu=cfg.data.get('samples_per_gpu', 1)),
**cfg.data.get('test_dataloader', {})
}
data_loader = build_dataloader(dataset, **test_loader_cfg)
# build the model and load checkpoint
model = build_posenet(cfg.model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[args.gpu_id])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
eval_config = cfg.get('evaluation', {})
eval_config = merge_configs(eval_config, dict(metric=args.eval))
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
results = dataset.evaluate(outputs, cfg.work_dir, **eval_config)
for k, v in sorted(results.items()):
print(f'{k}: {v}')
def main():
args = parse_args()
if 'cuda' in args.device.lower():
if torch.cuda.is_available():
with_cuda = True
else:
raise RuntimeError('No CUDA device found, please check it again.')
else:
with_cuda = False
if args.root_work_dir is None:
# get the current time stamp
now = datetime.now()
ts = now.strftime('%Y_%m_%d_%H_%M')
args.root_work_dir = f'work_dirs/inference_speed_test_{ts}'
mmcv.mkdir_or_exist(osp.abspath(args.root_work_dir))
cfg = mmcv.load(args.config)
dummy_datasets = mmcv.load(args.dummy_dataset_config)['dummy_datasets']
results = []
for i in range(args.priority + 1):
models = cfg['model_list'][f'P{i}']
for cur_model in models:
cfg_file = cur_model['config']
model_cfg = Config.fromfile(cfg_file)
test_dataset = model_cfg['data']['test']
dummy_dataset = dummy_datasets[test_dataset['type']]
test_dataset.update(dummy_dataset)
dataset = build_dataset(test_dataset)
data_loader = build_dataloader(
dataset,
samples_per_gpu=args.batch_size,
workers_per_gpu=model_cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
data_loader = IterLoader(data_loader)
if 'pretrained' in model_cfg.model.keys():
del model_cfg.model['pretrained']
model = init_pose_model(model_cfg, device=args.device.lower())
fp16_cfg = model_cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# benchmark with several iterations and take the average
pure_inf_time = 0
speed = []
for iteration in range(args.num_iters + args.num_warmup):
data = next(data_loader)
data['img'] = data['img'].to(args.device.lower())
data['img_metas'] = data['img_metas'].data[0]
if with_cuda:
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, **data)
if with_cuda:
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if iteration >= args.num_warmup:
pure_inf_time += elapsed
speed.append(1 / elapsed)
speed_mean = np.mean(speed)
speed_std = np.std(speed)
split_line = '=' * 30
result = f'{split_line}\nModel config:{cfg_file}\n' \
f'Device: {args.device}\n' \
f'Batch size: {args.batch_size}\n' \
f'Overall average speed: {speed_mean:.2f} \u00B1 ' \
f'{speed_std:.2f} items / s\n' \
f'Total iters: {args.num_iters}\n'\
f'Total time: {pure_inf_time:.2f} s \n{split_line}\n'\
print(result)
results.append(result)
print('!!!Please be cautious if you use the results in papers. '
'You may need to check if all ops are included and verify that the '
'speed computation is correct.')
with open(osp.join(args.root_work_dir, 'inference_speed.txt'), 'w') as f:
for res in results:
f.write(res)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from plguin/xx, registry will be updated
if hasattr(cfg, 'plugin') & cfg.plugin:
import importlib
if hasattr(cfg, 'plugin_dir'):
plugin_dir = cfg.plugin_dir
_module_dir = os.path.dirname(plugin_dir)
_module_dir = _module_dir.split('/')
_module_path = _module_dir[0]
for m in _module_dir[1:]:
_module_path = _module_path + '.' + m
print(_module_path)
plg_lib = importlib.import_module(_module_path)
else:
# import dir is the dirpath for the config file
_module_dir = os.path.dirname(args.config)
_module_dir = _module_dir.split('/')
_module_path = _module_dir[0]
for m in _module_dir[1:]:
_module_path = _module_path + '.' + m
print(_module_path)
plg_lib = importlib.import_module(_module_path)
# import modules from string list.
# if cfg.get('custom_imports', None):
# from mmcv.utils import import_modules_from_strings
# import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# in case the test dataset is concatenated
samples_per_gpu = 1
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(
cfg.data.test.pipeline)
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
samples_per_gpu = max(
[ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test])
if samples_per_gpu > 1:
for ds_cfg in cfg.data.test:
ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# set random seeds
if args.seed is not None:
set_random_seed(args.seed, deterministic=args.deterministic)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
if not os.path.exists(args.out_dir):
os.mkdir(args.out_dir)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
#from IPython import embed
#embed()
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
#if args.checkpoint is not None:
# checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
model.eval()
meta_json = {}
print('len of data loader: ', len(data_loader))
for i, data in tqdm(enumerate(data_loader)):
with torch.no_grad():
data = scatter(data, [-1])[0]
for k, v in data.items():
if isinstance(v, torch.Tensor):
data[k] = v.cuda()
key_img_path = data['img_metas'][0]['filename']
key_img_name = os.path.join(*key_img_path.split('/')[2:])
key_img_filename = key_img_path.split('/')[-1]
save_path = os.path.join(args.out_dir, key_img_filename)
outputs = model.module.preprocess_forward(data)
outputs = outputs.detach().cpu().numpy()
np.save(save_path, outputs)
meta_json[key_img_name] = save_path + '.npy'
with open(
os.path.join(args.out_dir,
'sf_inp_val_meta_{}.json'.format(args.local_rank)),
'w') as f:
json.dump(meta_json, f)
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
# update data root according to MMDET_DATASETS
update_data_root(cfg)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set multi-process settings
setup_multi_processes(cfg)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if 'pretrained' in cfg.model:
cfg.model.pretrained = None
elif 'init_cfg' in cfg.model.backbone:
cfg.model.backbone.init_cfg = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# in case the test dataset is concatenated
samples_per_gpu = 1
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(
cfg.data.test.pipeline)
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
samples_per_gpu = max(
[ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test])
if samples_per_gpu > 1:
for ds_cfg in cfg.data.test:
ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids[0:1]
warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
'Because we only support single GPU mode in '
'non-distributed testing. Use the first GPU '
'in `gpu_ids` now.')
else:
cfg.gpu_ids = [args.gpu_id]
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
rank, _ = get_dist_info()
# allows not to create
if args.work_dir is not None and rank == 0:
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
json_file = osp.join(args.work_dir, f'eval_{timestamp}.json')
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint.get('meta', {}):
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=cfg.gpu_ids)
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in [
'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
'rule', 'dynamic_intervals'
]:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
metric = dataset.evaluate(outputs, **eval_kwargs)
print(metric)
metric_dict = dict(config=args.config, metric=metric)
if args.work_dir is not None and rank == 0:
mmcv.dump(metric_dict, json_file)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
args.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
dataloader_setting = dict(samples_per_gpu=1,
workers_per_gpu=cfg.data.get(
'workers_per_gpu', 1),
dist=distributed,
shuffle=False,
drop_last=False)
dataloader_setting = dict(dataloader_setting,
**cfg.data.get('test_dataloader', {}))
data_loader = build_dataloader(dataset, **dataloader_setting)
# build the model and load checkpoint
model = build_posenet(cfg.model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
eval_config = cfg.get('evaluation', {})
eval_config = merge_configs(eval_config, dict(metric=args.eval))
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
print(dataset.evaluate(outputs, args.work_dir, **eval_config))
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# in case the test dataset is concatenated
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
dataset = build_dataset(cfg.data.test)
#dataset.load_query()
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
############## evaluate fairmot results#################
#fairmot_file = '/raid/yy1/data/MOT/MOT17/images/results/MOT17_val_jde_half_dla34_det/det_results.pkl'
#with open(fairmot_file, 'rb') as fid:
# outputs = pickle.load(fid)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in ['interval', 'tmpdir', 'start', 'gpu_collect']:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
print(dataset.evaluate(outputs, **eval_kwargs))
for thresh in [0.1, 0.2, 0.3, 0.4, 0.5]:
num_dets = 0
tmp_outputs = list()
for to in outputs:
for j in range(to[0].shape[0]):
if to[0][j, 4] < thresh:
break
tmp_outputs.append([to[0][:j]])
num_dets += j
print('thresh {:f}, num of dets {:d}'.format(thresh, num_dets))
print(dataset.evaluate(tmp_outputs, **eval_kwargs))
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
model = MMDataParallel(model, device_ids=[0])
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
# benchmark with 2000 image and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, rescale=True, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Done image [{i + 1:<3}/ 2000], fps: {fps:.1f} img / s')
if (i + 1) == 2000:
pure_inf_time += elapsed
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Overall fps: {fps:.1f} img / s')
break
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
cfg.merge_from_dict(args.cfg_options)
# Load output_config from cfg
output_config = cfg.get('output_config', {})
if args.out:
# Overwrite output_config from args.out
output_config = Config._merge_a_into_b(dict(out=args.out),
output_config)
# Load eval_config from cfg
eval_config = cfg.get('eval_config', {})
if args.eval:
# Overwrite eval_config from args.eval
eval_config = Config._merge_a_into_b(dict(metrics=args.eval),
eval_config)
if args.eval_options:
# Add options from args.eval_options
eval_config = Config._merge_a_into_b(args.eval_options, eval_config)
assert output_config or eval_config, \
('Please specify at least one operation (save or eval the '
'results) with the argument "--out" or "--eval"')
dataset_type = cfg.data.test.type
if output_config.get('out', None):
if 'output_format' in output_config:
# ugly workround to make recognition and localization the same
warnings.warn(
'Skip checking `output_format` in localization task.')
else:
out = output_config['out']
# make sure the dirname of the output path exists
mmcv.mkdir_or_exist(osp.dirname(out))
_, suffix = osp.splitext(out)
if dataset_type == 'AVADataset':
assert suffix[1:] == 'csv', ('For AVADataset, the format of '
'the output file should be csv')
else:
assert suffix[1:] in file_handlers, (
'The format of the output '
'file should be json, pickle or yaml')
# set cudnn benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.data.test.test_mode = True
if args.average_clips is not None:
# You can set average_clips during testing, it will override the
# original setting
if cfg.model.get('test_cfg') is None and cfg.get('test_cfg') is None:
cfg.model.setdefault('test_cfg',
dict(average_clips=args.average_clips))
else:
if cfg.model.get('test_cfg') is not None:
cfg.model.test_cfg.average_clips = args.average_clips
else:
cfg.test_cfg.average_clips = args.average_clips
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# The flag is used to register module's hooks
cfg.setdefault('module_hooks', [])
# build the dataloader
dataset = build_dataset(cfg.data.test, dict(test_mode=True))
dataloader_setting = dict(videos_per_gpu=cfg.data.get('videos_per_gpu', 1),
workers_per_gpu=cfg.data.get(
'workers_per_gpu', 1),
dist=distributed,
shuffle=False)
dataloader_setting = dict(dataloader_setting,
**cfg.data.get('test_dataloader', {}))
data_loader = build_dataloader(dataset, **dataloader_setting)
# remove redundant pretrain steps for testing
turn_off_pretrained(cfg.model)
# build the model and load checkpoint
model = build_model(cfg.model,
train_cfg=None,
test_cfg=cfg.get('test_cfg'))
if len(cfg.module_hooks) > 0:
register_module_hooks(model, cfg.module_hooks)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if output_config.get('out', None):
out = output_config['out']
print(f'\nwriting results to {out}')
#import pdb
#pdb.set_trace()
print(out[-4:])
if out[-4:] == 'json':
result_dict = {}
for result in outputs:
video_name = result['video_name']
result_dict[video_name] = result['proposal_list']
output_dict = {
'version': 'VERSION 1.3',
'results': result_dict,
'external_data': {}
}
mmcv.dump(output_dict, out)
else:
dataset.dump_results(outputs, **output_config)
if eval_config:
eval_res = dataset.evaluate(outputs, **eval_config)
for name, val in eval_res.items():
print(f'{name}: {val:.04f}')
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# in case the test dataset is concatenated
samples_per_gpu = 1
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(
cfg.data.test.pipeline)
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
samples_per_gpu = max(
[ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test])
if samples_per_gpu > 1:
for ds_cfg in cfg.data.test:
ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# set random seeds
if args.seed is not None:
set_random_seed(args.seed, deterministic=args.deterministic)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint.get('meta', {}):
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in [
'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
'rule'
]:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
print(dataset.evaluate(outputs, **eval_kwargs))
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
if cfg.get('USE_MMDET', False):
from mmdet.apis import multi_gpu_test, single_gpu_test
from mmdet.models import build_detector as build_model
from mmdet.datasets import build_dataloader
else:
from mmtrack.apis import multi_gpu_test, single_gpu_test
from mmtrack.models import build_model
from mmtrack.datasets import build_dataloader
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# cfg.model.pretrains = None
if hasattr(cfg.model, 'detector'):
cfg.model.detector.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
logger = get_logger('ParamsSearcher', log_file=args.log)
# get all cases
search_params = get_search_params(cfg.model.tracker, logger=logger)
combinations = [p for p in product(*search_params.values())]
search_cfgs = []
for c in combinations:
search_cfg = dotty(cfg.model.tracker.copy())
for i, k in enumerate(search_params.keys()):
search_cfg[k] = c[i]
search_cfgs.append(dict(search_cfg))
print_log(f'Totally {len(search_cfgs)} cases.', logger)
# init with the first one
cfg.model.tracker = search_cfgs[0].copy()
# build the model and load checkpoint
if cfg.get('test_cfg', False):
model = build_model(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
else:
model = build_model(cfg.model)
# We need call `init_weights()` to load pretained weights in MOT task.
model.init_weights()
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.checkpoint is not None:
checkpoint = load_checkpoint(model,
args.checkpoint,
map_location='cpu')
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
if not hasattr(model, 'CLASSES'):
model.CLASSES = dataset.CLASSES
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
print_log(f'Record {cfg.search_metrics}.', logger)
for i, search_cfg in enumerate(search_cfgs):
if not distributed:
model.module.tracker = build_tracker(search_cfg)
outputs = single_gpu_test(model, data_loader, args.show,
args.show_dir)
else:
model.module.tracker = build_tracker(search_cfg)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in ['interval', 'tmpdir', 'start', 'gpu_collect']:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
results = dataset.evaluate(outputs, **eval_kwargs)
_records = []
for k in cfg.search_metrics:
if isinstance(results[k], float):
_records.append(f'{(results[k]):.3f}')
else:
_records.append(f'{(results[k])}')
print_log(f'{combinations[i]}: {_records}', logger)
def main():
args = parse_args()
assert args.out
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# for rfp backbone
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# in case the test dataset is concatenated
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_caption(cfg.model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(dataset.evaluate(outputs), args.out)
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show \
or args.show_dir, \
('Please specify at least one operation (save/eval/format/show the '
'results / save the results) with the argument "--out", "--eval"'
', "--format-only", "--show" or "--show-dir"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
# config 파일 읽기
cfg = Config.fromfile(args.config)
# 코드 돌릴 때 --cfg-options 설정하면 기존 config 파일에 내용 합치는 코드
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
if cfg.model.get('neck'):
if isinstance(cfg.model.neck, list):
for neck_cfg in cfg.model.neck:
if neck_cfg.get('rfp_backbone'):
if neck_cfg.rfp_backbone.get('pretrained'):
neck_cfg.rfp_backbone.pretrained = None
elif cfg.model.neck.get('rfp_backbone'):
if cfg.model.neck.rfp_backbone.get('pretrained'):
cfg.model.neck.rfp_backbone.pretrained = None
# in case the test dataset is concatenated
if isinstance(cfg.data.test, dict): # cfg.data.test가 dict 타입이면 실행
cfg.data.test.test_mode = True # coco_detection.py 랑 비슷한 form에 test_mode를 설정해줄 수 있나봄
elif isinstance(cfg.data.test, list): # cfg.data.test가 list 타입이면 실행
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
########################################################################################
""" 여기에서 cctv 영상을 이미지로 변환해서 폴더에 넣고 cfg.data.test 부분에 폴더 경로를 추가"""
video = mmcv.VideoReader("/home/minjae/mjseong/mmdetection/data/test.avi")
print(len(video)) # get the total frame number
print(video.width, video.height, video.resolution, video.fps)
video.cvt2frames(
"/home/minjae/mjseong/mmdetection/data/KRRI_Video_cvt2frames",
start=0,
max_num=10000)
cfg.data.test.img_prefix = "data_root" + "/home/minjae/mjseong/mmdetection/data/KRRI_Video_cvt2frames/"
# cfg.data.test.ann_file =
########################################################################################
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
args.show_score_thr)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
if args.out:
print(f'\nwriting results to {args.out}')
mmcv.dump(outputs, args.out)
kwargs = {} if args.eval_options is None else args.eval_options
if args.format_only:
dataset.format_results(outputs, **kwargs)
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
for key in ['interval', 'tmpdir', 'start', 'gpu_collect']:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
print(dataset.evaluate(outputs, **eval_kwargs))
########################################################################################
"""여기에서 box쳐진 test 결과의 이미지를 다시 video로 변환 시켜주기"""
mmcv.frames2video(
"/home/minjae/mjseong/mmdetection/data/KRRI_Video_cvt2frames",
"/home/minjae/mjseong/mmdetection/data/test.avi")
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from plguin/xx, registry will be updated
if hasattr(cfg, 'plugin') & cfg.plugin:
import importlib
if hasattr(cfg, 'plugin_dir'):
plugin_dir = cfg.plugin_dir
_module_dir = os.path.dirname(plugin_dir)
_module_dir = _module_dir.split('/')
_module_path = _module_dir[0]
for m in _module_dir[1:]:
_module_path = _module_path + '.' + m
print(_module_path)
plg_lib = importlib.import_module(_module_path)
else:
# import dir is the dirpath for the config file
_module_dir = os.path.dirname(args.config)
_module_dir = _module_dir.split('/')
_module_path = _module_dir[0]
for m in _module_dir[1:]:
_module_path = _module_path + '.' + m
print(_module_path)
plg_lib = importlib.import_module(_module_path)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
# in case the test dataset is concatenated
samples_per_gpu = 1
if isinstance(cfg.data.test, dict):
cfg.data.test.test_mode = True
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
if samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.test.pipeline = replace_ImageToTensor(
cfg.data.test.pipeline)
elif isinstance(cfg.data.test, list):
for ds_cfg in cfg.data.test:
ds_cfg.test_mode = True
samples_per_gpu = max(
[ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test])
if samples_per_gpu > 1:
for ds_cfg in cfg.data.test:
ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
distributed = False
# set random seeds
if args.seed is not None:
set_random_seed(args.seed, deterministic=args.deterministic)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
if not os.path.exists(args.out_dir):
os.mkdir(args.out_dir)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
#from IPython import embed
#embed()
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
model = MMDataParallel(model, device_ids=[0])
model.eval()
output_list = []
for i, data in enumerate(data_loader):
with torch.no_grad():
data = scatter(data, [-1])[0]
for k, v in data.items():
if isinstance(v, torch.Tensor):
data[k] = v.cuda()
outputs = model.module.eval_forward(data)
output_list.append(outputs)
if i >= 100:
break
merged_output_list = []
for i, output in enumerate(output_list):
save_dir = os.path.join(args.out_dir, 'sample-{}'.format(i))
if not os.path.isdir(save_dir):
os.mkdir(save_dir)
outputs = parse_output(output, save_dir)
merged_output_list.append(outputs)
save_dir = os.path.join(args.out_dir, 'gifs')
if not os.path.isdir(save_dir):
os.mkdir(save_dir)
merge_output(merged_output_list, save_dir)
def main():
args = parse_args()
assert args.eval or args.show \
or args.show_dir, \
('Please specify at least one operation (eval/show the '
'results) with the argument "--eval"'
', "--show" or "--show-dir"')
cfg = Config.fromfile(args.config)
if cfg.get('USE_MMDET', False):
from mmdet.apis import multi_gpu_test, single_gpu_test
from mmdet.datasets import build_dataloader
from mmdet.models import build_detector as build_model
if 'detector' in cfg.model:
cfg.model = cfg.model.detector
elif cfg.get('USE_MMCLS', False):
from mmtrack.apis import multi_gpu_test, single_gpu_test
from mmtrack.datasets import build_dataloader
from mmtrack.models import build_reid as build_model
if 'reid' in cfg.model:
cfg.model = cfg.model.reid
else:
from mmtrack.apis import multi_gpu_test, single_gpu_test
from mmtrack.datasets import build_dataloader
from mmtrack.models import build_model
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# build the dataloader
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
logger = get_logger('SOTParamsSearcher', log_file=args.log)
# build the model and load checkpoint
if cfg.get('test_cfg', False):
model = build_model(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
else:
model = build_model(cfg.model)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.checkpoint is not None:
checkpoint = load_checkpoint(model,
args.checkpoint,
map_location='cpu')
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
if not hasattr(model, 'CLASSES'):
model.CLASSES = dataset.CLASSES
if args.fuse_conv_bn:
model = fuse_conv_bn(model)
if not distributed:
model = MMDataParallel(model, device_ids=[0])
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
if 'meta' in checkpoint and 'hook_msgs' in checkpoint[
'meta'] and 'best_score' in checkpoint['meta']['hook_msgs']:
best_score = checkpoint['meta']['hook_msgs']['best_score']
else:
best_score = 0
best_result = dict(success=best_score, norm_precision=0., precision=0.)
best_params = dict(penalty_k=cfg.model.test_cfg.rpn.penalty_k,
lr=cfg.model.test_cfg.rpn.lr,
win_influ=cfg.model.test_cfg.rpn.window_influence)
print_log(f'init best score as: {best_score}', logger)
print_log(f'init best params as: {best_params}', logger)
num_cases = len(args.penalty_k_range) * len(args.lr_range) * len(
args.win_influ_range)
case_count = 0
for penalty_k in args.penalty_k_range:
for lr in args.lr_range:
for win_influ in args.win_influ_range:
case_count += 1
cfg.model.test_cfg.rpn.penalty_k = penalty_k
cfg.model.test_cfg.rpn.lr = lr
cfg.model.test_cfg.rpn.window_influence = win_influ
print_log(f'-----------[{case_count}/{num_cases}]-----------',
logger)
print_log(
f'penalty_k={penalty_k} lr={lr} win_influence={win_influ}',
logger)
if not distributed:
outputs = single_gpu_test(
model,
data_loader,
args.show,
args.show_dir,
show_score_thr=args.show_score_thr)
else:
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
rank, _ = get_dist_info()
if rank == 0:
kwargs = args.eval_options if args.eval_options else {}
if args.eval:
eval_kwargs = cfg.get('evaluation', {}).copy()
# hard-code way to remove EvalHook args
eval_hook_args = [
'interval', 'tmpdir', 'start', 'gpu_collect',
'save_best', 'rule', 'by_epoch'
]
for key in eval_hook_args:
eval_kwargs.pop(key, None)
eval_kwargs.update(dict(metric=args.eval, **kwargs))
eval_results = dataset.evaluate(outputs, **eval_kwargs)
# print(eval_results)
print_log(f'evaluation results: {eval_results}',
logger)
print_log('------------------------------------------',
logger)
if eval_results['success'] > best_result['success']:
best_result = eval_results
best_params['penalty_k'] = penalty_k,
best_params['lr'] = lr,
best_params['win_influ'] = win_influ
print_log(
f'The current best evaluation results: \
{best_result}', logger)
print_log(f'The current best params: {best_params}',
logger)
print_log(
f'After parameter searching, the best evaluation results: \
{best_result}', logger)
print_log(f'After parameter searching, the best params: {best_params}',
logger)
