Classes
class	Bottleneck

class	ResNest

Functions
	short_hash (name)

	build_resnest_backbone (cfg)

Variables
	logger = logging.getLogger(__name__)

str	_url_format = 'https://s3.us-west-1.wasabisys.com/resnest/torch/{}-{}.pth'

dict	_model_sha256

dict	model_urls

Detailed Description

ResNeSt models

Function Documentation

◆ build_resnest_backbone()

fastreid.modeling.backbones.resnest.build_resnest_backbone ( cfg )

Create a ResNest instance from config.
Returns:
    ResNet: a :class:`ResNet` instance.

Definition at line 359 of file resnest.py.

def build_resnest_backbone(cfg):
    """
    Create a ResNest instance from config.
    Returns:
        ResNet: a :class:`ResNet` instance.
    """
 
    # fmt: off
    pretrain      = cfg.MODEL.BACKBONE.PRETRAIN
    pretrain_path = cfg.MODEL.BACKBONE.PRETRAIN_PATH
    last_stride   = cfg.MODEL.BACKBONE.LAST_STRIDE
    bn_norm       = cfg.MODEL.BACKBONE.NORM
    with_ibn      = cfg.MODEL.BACKBONE.WITH_IBN
    with_se       = cfg.MODEL.BACKBONE.WITH_SE
    with_nl       = cfg.MODEL.BACKBONE.WITH_NL
    depth         = cfg.MODEL.BACKBONE.DEPTH
    # fmt: on
 
    num_blocks_per_stage = {
        "50x": [3, 4, 6, 3],
        "101x": [3, 4, 23, 3],
        "200x": [3, 24, 36, 3],
        "269x": [3, 30, 48, 8],
    }[depth]
 
    nl_layers_per_stage = {
        "50x": [0, 2, 3, 0],
        "101x": [0, 2, 3, 0],
        "200x": [0, 2, 3, 0],
        "269x": [0, 2, 3, 0],
    }[depth]
 
    stem_width = {
        "50x": 32,
        "101x": 64,
        "200x": 64,
        "269x": 64,
    }[depth]
 
    model = ResNest(last_stride, bn_norm, with_ibn, with_nl, Bottleneck, num_blocks_per_stage,
                    nl_layers_per_stage, radix=2, groups=1, bottleneck_width=64,
                    deep_stem=True, stem_width=stem_width, avg_down=True,
                    avd=True, avd_first=False)
    if pretrain:
        # Load pretrain path if specifically
        if pretrain_path:
            try:
                state_dict = torch.load(pretrain_path, map_location=torch.device('cpu'))
                logger.info(f"Loading pretrained model from {pretrain_path}")
            except FileNotFoundError as e:
                logger.info(f'{pretrain_path} is not found! Please check this path.')
                raise e
            except KeyError as e:
                logger.info("State dict keys error! Please check the state dict.")
                raise e
        else:
            state_dict = torch.hub.load_state_dict_from_url(
                model_urls['resnest' + depth[:-1]], progress=True, check_hash=True, map_location=torch.device('cpu'))
 
        incompatible = model.load_state_dict(state_dict, strict=False)
        if incompatible.missing_keys:
            logger.info(
                get_missing_parameters_message(incompatible.missing_keys)
            )
        if incompatible.unexpected_keys:
            logger.info(
                get_unexpected_parameters_message(incompatible.unexpected_keys)
            )
    return model

◆ short_hash()

fastreid.modeling.backbones.resnest.short_hash ( name )

Definition at line 32 of file resnest.py.

def short_hash(name):
    if name not in _model_sha256:
        raise ValueError('Pretrained model for {name} is not available.'.format(name=name))
    return _model_sha256[name][:8]
 
 

Variable Documentation

◆ _model_sha256

dict fastreid.modeling.backbones.resnest._model_sha256

protected

Initial value:

=  {name: checksum for checksum, name in [
    ('528c19ca', 'resnest50'),
    ('22405ba7', 'resnest101'),
    ('75117900', 'resnest200'),
    ('0cc87c48', 'resnest269'),
]}

Definition at line 24 of file resnest.py.

◆ _url_format

str fastreid.modeling.backbones.resnest._url_format = 'https://s3.us-west-1.wasabisys.com/resnest/torch/{}-{}.pth'

protected

Definition at line 22 of file resnest.py.

◆ logger

fastreid.modeling.backbones.resnest.logger = logging.getLogger(__name__)

Definition at line 21 of file resnest.py.

◆ model_urls

dict fastreid.modeling.backbones.resnest.model_urls