def init_modules(self):
"""
some modules
"""
self.feature_extractor = OFTNetFeatureExtractor(
self.feature_extractor_config)
feats_reduce_1 = nn.Conv2d(128, self.feat_size, 1, 1, 0)
feats_reduce_2 = nn.Conv2d(256, self.feat_size, 1, 1, 0)
feats_reduce_3 = nn.Conv2d(512, self.feat_size, 1, 1, 0)
self.feats_reduces = nn.ModuleList(
[feats_reduce_1, feats_reduce_2, feats_reduce_3])
self.feat_collapse = nn.Conv2d(8, 1, 1, 1, 0)
self.output_head = nn.Conv2d(256 * 4, self.output_channels, 1, 1, 0)
# loss
self.reg_loss = nn.L1Loss(reduce=False)
# self.reg_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)
self.conf_loss = nn.L1Loss(reduce=False)
self.angle_loss = MultiBinLoss(num_bins=self.num_bins)
def init_modules(self):
self.det_model = PRNet(ModelCFG)
# dims loss
self.dims_loss = nn.SmoothL1Loss(reduce=False)
# multibin loss
self.multibin_loss = MultiBinLoss(self.num_bins)
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):
"""
some modules
"""
self.feature_extractor = OFTNetFeatureExtractor(
self.feature_extractor_config)
feats_reduce_1 = nn.Conv2d(128, self.feat_size, 1, 1, 0)
feats_reduce_2 = nn.Conv2d(256, self.feat_size, 1, 1, 0)
feats_reduce_3 = nn.Conv2d(512, self.feat_size, 1, 1, 0)
self.feats_reduces = nn.ModuleList(
[feats_reduce_1, feats_reduce_2, feats_reduce_3])
self.feat_collapse = nn.Conv2d(8, 1, 1, 1, 0)
self.rcnn_output_head = nn.Conv2d(1152, self.rcnn_output_channels, 1,
1, 0)
self.rpn_output_head = nn.Conv2d(256 * 4, self.rpn_output_channels, 1,
1, 0)
# loss
self.reg_loss = nn.L1Loss(reduce=False)
# self.reg_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)
self.conf_loss = nn.L1Loss(reduce=False)
self.angle_loss = MultiBinLoss(num_bins=self.num_bins)
# fusion layer
# self.upconv1 = nn.ConvTranspose2d(self.feat_size, self.feat_size, 2, 2,
# 0)
self.fusion1 = nn.Conv2d(2 * self.feat_size, self.feat_size, 3, 1, 1)
self.fusion1_bn = nn.BatchNorm2d(self.feat_size)
self.relu1 = nn.ReLU()
self.upconv2 = nn.ConvTranspose2d(self.feat_size, self.feat_size, 2, 2,
0)
self.upconv2_bn = nn.BatchNorm2d(self.feat_size)
self.upconv2_relu = nn.ReLU()
self.relu2 = nn.ReLU()
self.fusion2 = nn.Conv2d(2 * self.feat_size, self.feat_size, 3, 1, 1)
self.fusion2_bn = nn.BatchNorm2d(self.feat_size)
self.upconv3 = nn.ConvTranspose2d(self.feat_size, self.feat_size, 2, 2,
0)
self.upconv3_bn = nn.BatchNorm2d(self.feat_size)
self.upconv3_relu = nn.ReLU()
# self.fusion3 = nn.Conv2d(self.feat_size, self.feat_size, 3, 1, 1)
# self.relu3 = nn.ReLU()
self.rcnn_pooling = RoIAlignAvg(self.pooling_size, self.pooling_size,
1.0 / 8.0)
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)