mirror of
https://github.com/JDAI-CV/fast-reid.git
synced 2025-06-03 14:50:47 +08:00
78 lines
3.1 KiB
Python
78 lines
3.1 KiB
Python
# encoding: utf-8
|
|
"""
|
|
@author: liaoxingyu
|
|
@contact: sherlockliao01@gmail.com
|
|
"""
|
|
|
|
import torch
|
|
from torch import nn
|
|
|
|
from fastreid.layers import *
|
|
from fastreid.utils.weight_init import weights_init_kaiming, weights_init_classifier
|
|
from .build import REID_HEADS_REGISTRY
|
|
|
|
|
|
@REID_HEADS_REGISTRY.register()
|
|
class AttrHead(nn.Module):
|
|
def __init__(self, cfg):
|
|
super().__init__()
|
|
# fmt: off
|
|
feat_dim = cfg.MODEL.BACKBONE.FEAT_DIM
|
|
num_classes = cfg.MODEL.HEADS.NUM_CLASSES
|
|
pool_type = cfg.MODEL.HEADS.POOL_LAYER
|
|
cls_type = cfg.MODEL.HEADS.CLS_LAYER
|
|
with_bnneck = cfg.MODEL.HEADS.WITH_BNNECK
|
|
norm_type = cfg.MODEL.HEADS.NORM
|
|
|
|
if pool_type == 'fastavgpool': self.pool_layer = FastGlobalAvgPool2d()
|
|
elif pool_type == 'avgpool': self.pool_layer = nn.AdaptiveAvgPool2d(1)
|
|
elif pool_type == 'maxpool': self.pool_layer = nn.AdaptiveMaxPool2d(1)
|
|
elif pool_type == 'gempoolP': self.pool_layer = GeneralizedMeanPoolingP()
|
|
elif pool_type == 'gempool': self.pool_layer = GeneralizedMeanPooling()
|
|
elif pool_type == "avgmaxpool": self.pool_layer = AdaptiveAvgMaxPool2d()
|
|
elif pool_type == 'clipavgpool': self.pool_layer = ClipGlobalAvgPool2d()
|
|
elif pool_type == "identity": self.pool_layer = nn.Identity()
|
|
elif pool_type == "flatten": self.pool_layer = Flatten()
|
|
else: raise KeyError(f"{pool_type} is not supported!")
|
|
|
|
# Classification layer
|
|
if cls_type == 'linear': self.classifier = nn.Linear(feat_dim, num_classes, bias=False)
|
|
elif cls_type == 'arcSoftmax': self.classifier = ArcSoftmax(cfg, feat_dim, num_classes)
|
|
elif cls_type == 'circleSoftmax': self.classifier = CircleSoftmax(cfg, feat_dim, num_classes)
|
|
elif cls_type == 'amSoftmax': self.classifier = AMSoftmax(cfg, feat_dim, num_classes)
|
|
else: raise KeyError(f"{cls_type} is not supported!")
|
|
# fmt: on
|
|
|
|
# bottleneck = []
|
|
# if with_bnneck:
|
|
# bottleneck.append(get_norm(norm_type, feat_dim, bias_freeze=True))
|
|
bottleneck = [nn.BatchNorm1d(num_classes)]
|
|
|
|
self.bottleneck = nn.Sequential(*bottleneck)
|
|
|
|
self.bottleneck.apply(weights_init_kaiming)
|
|
self.classifier.apply(weights_init_classifier)
|
|
|
|
def forward(self, features, targets=None):
|
|
"""
|
|
See :class:`ReIDHeads.forward`.
|
|
"""
|
|
global_feat = self.pool_layer(features)
|
|
global_feat = global_feat[..., 0, 0]
|
|
|
|
classifier_name = self.classifier.__class__.__name__
|
|
# fmt: off
|
|
if classifier_name == 'Linear': cls_outputs = self.classifier(global_feat)
|
|
else: cls_outputs = self.classifier(global_feat, targets)
|
|
# fmt: on
|
|
|
|
cls_outputs = self.bottleneck(cls_outputs)
|
|
|
|
if self.training:
|
|
return {
|
|
"cls_outputs": cls_outputs,
|
|
}
|
|
else:
|
|
cls_outputs = torch.sigmoid(cls_outputs)
|
|
return cls_outputs
|