def init_modules(self):
self.feature_extractor = ResNetFeatureExtractor(
self.feature_extractor_config)
self.rpn_model = RPNModel(self.rpn_config)
if self.pooling_mode == 'align':
self.rcnn_pooling = RoIAlignAvg(self.pooling_size,
self.pooling_size, 1.0 / 16.0)
elif self.pooling_mode == 'ps':
self.rcnn_pooling = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
elif self.pooling_mode == 'psalign':
raise NotImplementedError('have not implemented yet!')
elif self.pooling_mode == 'deformable_psalign':
raise NotImplementedError('have not implemented yet!')
self.rcnn_cls_pred = nn.Linear(2048, self.n_classes)
if self.reduce:
in_channels = 2048
else:
in_channels = 2048 * 4 * 4
if self.class_agnostic:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4)
else:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
def init_modules(self):
self.feature_extractor = ResNetFeatureExtractor(
self.feature_extractor_config)
self.rpn_model = RPNModel(self.rpn_config)
if self.pooling_mode == 'align':
self.rcnn_pooling = RoIAlignAvg(self.pooling_size,
self.pooling_size, 1.0 / 16.0)
elif self.pooling_mode == 'ps':
self.rcnn_pooling = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
elif self.pooling_mode == 'psalign':
raise NotImplementedError('have not implemented yet!')
elif self.pooling_mode == 'deformable_psalign':
raise NotImplementedError('have not implemented yet!')
self.rcnn_cls_pred = nn.Linear(2048, self.n_classes * 2048)
# self.rcnn_cls_pred = nn.Conv2d(2048, self.n_classes, 3, 1, 1)
if self.class_agnostic:
# self.bottle_neck = nn.Sequential(
# nn.Linear(2048, 512),
# nn.BatchNorm2d(512),
# nn.ReLU(inplace=True),
# nn.Linear(512, 2048))
# self.rcnn_bbox_pred_top = nn.Linear(2048, 4)
# self.relu_top = nn.ReLU(inplace=True)
self.rcnn_bbox_pred = nn.Conv2d(2048, 4, 3, 1, 1)
else:
self.rcnn_bbox_pred = nn.Linear(2048, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(
F.cross_entropy, reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
def init_modules(self):
# define the convrelu layers processing input feature map
self.rpn_conv = nn.Conv2d(self.in_channels, 512, 3, 1, 1, bias=True)
# define bg/fg classifcation score layer
self.rpn_cls_score = nn.Conv2d(512, self.nc_score_out, 1, 1, 0)
# define anchor box offset prediction layer
if self.use_score:
bbox_feat_channels = 512 + 2
self.nc_bbox_out /= self.num_anchors
else:
bbox_feat_channels = 512
self.rpn_bbox_pred = nn.Conv2d(bbox_feat_channels, self.nc_bbox_out, 1,
1, 0)
# bbox
self.rpn_bbox_loss = nn.modules.loss.SmoothL1Loss(reduce=False)
# cls
if self.use_focal_loss:
self.rpn_cls_loss = FocalLoss(2)
else:
self.rpn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
def init_modules(self):
self.feature_extractor = ResNetFeatureExtractor(
self.feature_extractor_config)
self.rpn_model = IoURPNModel(self.rpn_config)
self.rcnn_pooling = RoIAlignAvg(self.pooling_size, self.pooling_size,
1.0 / 16.0)
self.rcnn_cls_pred = nn.Conv2d(2048, self.n_classes, 3, 1, 1)
in_channels = 2048
self.rcnn_iou = nn.Linear(in_channels, self.n_classes)
self.rcnn_iog = nn.Linear(in_channels, self.n_classes)
self.rcnn_iod = nn.Linear(in_channels, self.n_classes)
if self.class_agnostic:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4)
else:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
self.rcnn_iou_loss = nn.MSELoss(reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
def init_modules(self):
self.feature_extractor = ResNetFeatureExtractor(
self.feature_extractor_config)
self.rpn_model = RPNModel(self.rpn_config)
if self.pooling_mode == 'align':
self.rcnn_pooling = RoIAlignAvg(self.pooling_size,
self.pooling_size, 1.0 / 16.0)
elif self.pooling_mode == 'ps':
self.rcnn_pooling = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
elif self.pooling_mode == 'psalign':
raise NotImplementedError('have not implemented yet!')
elif self.pooling_mode == 'deformable_psalign':
raise NotImplementedError('have not implemented yet!')
# self.rcnn_cls_pred = nn.Linear(2048, self.n_classes)
self.rcnn_cls_pred = nn.Conv2d(2048, self.n_classes, 3, 1, 1)
if self.reduce:
in_channels = 2048
else:
in_channels = 2048 * 4 * 4
if self.class_agnostic:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4)
else:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
# some 3d statistic
# some 2d points projected from 3d
# self.rcnn_3d_preds_new = nn.Linear(in_channels, 3 + 4 * self.num_bins)
self.rcnn_3d_loss = MultiBinLoss(num_bins=self.num_bins)
# dims
self.rcnn_dims_pred = nn.Sequential(
*[nn.Linear(in_channels, 256),
nn.ReLU(),
nn.Linear(256, 3)])
# angle
self.rcnn_angle_pred = nn.Sequential(*[
nn.Linear(in_channels, 256),
nn.ReLU(),
nn.Linear(256, self.num_bins * 2)
])
# angle conf
self.rcnn_angle_conf_pred = nn.Sequential(*[
nn.Linear(in_channels, 256),
nn.ReLU(),
nn.Linear(256, self.num_bins * 2)
])
def init_modules(self):
self.feature_extractor = ResNetFeatureExtractor(
self.feature_extractor_config)
self.modify_feature_extractor()
self.rpn_model = RPNModel(self.rpn_config)
if self.pooling_mode == 'align':
self.rcnn_pooling = RoIAlignAvg(self.pooling_size,
self.pooling_size, 1.0 / 16.0)
elif self.pooling_mode == 'ps':
self.rcnn_pooling = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
elif self.pooling_mode == 'psalign':
raise NotImplementedError('have not implemented yet!')
elif self.pooling_mode == 'deformable_psalign':
raise NotImplementedError('have not implemented yet!')
self.mask_rcnn_pooling = RoIAlignAvg(14, 14, 1.0 / 16.0)
# self.rcnn_cls_pred = nn.Linear(2048, self.n_classes)
self.rcnn_cls_pred = nn.Conv2d(2048, self.n_classes, 3, 1, 1)
if self.reduce:
in_channels = 2048
else:
in_channels = 2048 * 4 * 4
if self.class_agnostic:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4)
else:
self.rcnn_bbox_pred = nn.Linear(in_channels, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
self.rcnn_kp_loss = functools.partial(F.cross_entropy,
reduce=False,
ignore_index=-1)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
# some 3d statistic
# some 2d points projected from 3d
self.rcnn_3d_pred = nn.Linear(in_channels, 3)
# self.rcnn_3d_loss = MultiBinLoss(num_bins=self.num_bins)
# self.rcnn_3d_loss = MultiBinRegLoss(num_bins=self.num_bins)
self.rcnn_3d_loss = OrientationLoss(split_loss=True)
self.keypoint_predictor = KeyPointPredictor2(1024)
def init_modules(self):
self.feature_extractor = feature_extractors_builder.build(
self.feature_extractor_config)
# self.feature_extractor = ResNetFeatureExtractor(
# self.feature_extractor_config)
# self.feature_extractor = MobileNetFeatureExtractor(
# self.feature_extractor_config)
self.rpn_model = RPNModel(self.rpn_config)
if self.pooling_mode == 'align':
self.rcnn_pooling = RoIAlignAvg(self.pooling_size,
self.pooling_size, 1.0 / 16.0)
elif self.pooling_mode == 'ps':
self.rcnn_pooling = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
elif self.pooling_mode == 'psalign':
raise NotImplementedError('have not implemented yet!')
elif self.pooling_mode == 'deformable_psalign':
raise NotImplementedError('have not implemented yet!')
self.rcnn_cls_pred = nn.Linear(self.ndin, self.n_classes)
if self.class_agnostic:
self.rcnn_bbox_pred = nn.Linear(self.ndin, 4)
# self.rcnn_bbox_pred = nn.Conv2d(2048,4,3,1,1)
else:
self.rcnn_bbox_pred = nn.Linear(self.ndin, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2,
gamma=2,
alpha=0.2,
auto_alpha=False)
else:
self.rcnn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
# attention
if self.use_self_attention:
self.spatial_attention = nn.Conv2d(self.ndin, 1, 3, 1, 1)
self.rcnn_pooling2 = RoIAlignAvg(self.pooling_size, self.pooling_size,
1.0 / 8.0)
self.reduce_pooling = nn.Sequential(nn.Conv2d(512, 1024, 1, 1, 0),
nn.ReLU())
def init_modules(self):
self.feature_extractor = ResNetFeatureExtractor(
self.feature_extractor_config)
self.rpn_model = RPNModel(self.rpn_config)
if self.pooling_mode == 'align':
self.rcnn_pooling = ROIAlign((self.pooling_size,
self.pooling_size), 1.0 / 16.0, 2)
elif self.pooling_mode == 'ps':
self.rcnn_pooling = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
elif self.pooling_mode == 'psalign':
raise NotImplementedError('have not implemented yet!')
elif self.pooling_mode == 'deformable_psalign':
raise NotImplementedError('have not implemented yet!')
# self.rcnn_cls_pred = nn.Conv2d(2048, self.n_classes, 3, 1, 1)
self.rcnn_cls_preds = nn.Linear(2048, self.n_classes)
if self.reduce:
in_channels = 2048
else:
in_channels = 2048 * 4 * 4
if self.class_agnostic:
self.rcnn_bbox_preds = nn.Linear(in_channels, 4)
else:
self.rcnn_bbox_preds = nn.Linear(in_channels, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(self.n_classes)
else:
self.rcnn_cls_loss = functools.partial(
F.cross_entropy, reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
# self.rcnn_3d_pred = nn.Linear(c, 3 + 4 + 11 + 2 + 1)
if self.class_agnostic_3d:
self.rcnn_3d_pred = nn.Linear(in_channels, 3 + 4 * self.num_bins)
else:
self.rcnn_3d_pred = nn.Linear(
in_channels, 3 * self.n_classes + 4 * self.num_bins)
# self.rcnn_3d_loss = OrientationLoss(split_loss=True)
self.rcnn_3d_loss = MultiBinLoss(num_bins=self.num_bins)
def init_modules(self):
self.feature_extractor = FeatureExtractor(
self.feature_extractor_config)
self.rpn_model = GateRPNModel(self.rpn_config)
self.rcnn_pooling = RoIAlignAvg(self.pooling_size, self.pooling_size,
1.0 / 16.0)
self.rcnn_cls_pred = nn.Linear(2048, self.n_classes)
if self.class_agnostic:
self.rcnn_bbox_pred = nn.Linear(2048, 4)
else:
self.rcnn_bbox_pred = nn.Linear(2048, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(F.cross_entropy,
reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
def init_modules(self):
self.feature_extractor = PyramidVggnetExtractor(
self.feature_extractor_config)
# loc layers and conf layers
base_feat = self.feature_extractor.base_feat
extra_layers = self.feature_extractor.extras_layers
loc_layers, conf_layers = self.make_multibox(base_feat, extra_layers)
self.loc_layers = loc_layers
self.conf_layers = conf_layers
# self.rcnn_3d_preds = nn.Linear()
# loss layers
self.loc_loss = nn.SmoothL1Loss(reduce=False)
if self.use_focal_loss:
self.conf_loss = FocalLoss(
self.n_classes, alpha=0.2, gamma=2, auto_alpha=False)
else:
self.conf_loss = nn.CrossEntropyLoss(reduce=False)
def init_modules(self):
self.feature_extractor = FeatureExtractor(
self.feature_extractor_config)
self.rpn_model = RPNModel(self.rpn_config)
self.rcnn_pooling_cls = PSRoIPool(7, 7, 1.0 / 16, 7, self.n_classes)
self.rcnn_pooling_loc = PSRoIPool(7, 7, 1.0 / 16, 7, 4)
self.rcnn_cls_base = nn.Conv2d(
in_channels=1024,
out_channels=self.n_classes * self.pooling_size *
self.pooling_size,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.rcnn_bbox_base = nn.Conv2d(
in_channels=1024,
out_channels=4 * self.pooling_size * self.pooling_size,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.rcnn_top = nn.Conv2d(2048, 1024, 1, 1, 0, bias=False)
# self.rcnn_cls_pred = nn.Linear(2048, self.n_classes)
# if self.class_agnostic:
# self.rcnn_bbox_pred = nn.Linear(2048, 4)
# else:
# self.rcnn_bbox_pred = nn.Linear(2048, 4 * self.n_classes)
# loss module
if self.use_focal_loss:
self.rcnn_cls_loss = FocalLoss(2)
else:
self.rcnn_cls_loss = functools.partial(
F.cross_entropy, reduce=False)
self.rcnn_bbox_loss = nn.modules.SmoothL1Loss(reduce=False)
