def __init__(self,
alignsize=8,
reddim=32,
loadweight=True,
model=None,
downsample=4):
super(crop_model_multi_scale_shared, self).__init__()
if model == 'shufflenetv2':
self.Feat_ext = shufflenetv2_base(loadweight, downsample)
self.DimRed = nn.Conv2d(812, reddim, kernel_size=1, padding=0)
elif model == 'mobilenetv2':
self.Feat_ext = mobilenetv2_base(loadweight, downsample)
self.DimRed = nn.Conv2d(448, reddim, kernel_size=1, padding=0)
elif model == 'vgg16':
self.Feat_ext = vgg_base(loadweight, downsample)
self.DimRed = nn.Conv2d(1536, reddim, kernel_size=1, padding=0)
elif model == 'resnet50':
self.Feat_ext = resnet50_base(loadweight, downsample)
self.DimRed = nn.Conv2d(3584, reddim, kernel_size=1, padding=0)
self.downsample2 = nn.UpsamplingBilinear2d(scale_factor=1.0 / 2.0)
self.upsample2 = nn.UpsamplingBilinear2d(scale_factor=2.0)
self.RoIAlign = RoIAlignAvg(alignsize, alignsize, 1.0 / 2**downsample)
self.RoDAlign = RoDAlignAvg(alignsize, alignsize, 1.0 / 2**downsample)
self.FC_layers = fc_layers(reddim * 2, alignsize)
def __init__(self, alignsize = 8, reddim = 8, loadweight = True, model = None, downsample=4):
super(crop_model_single_scale, self).__init__()
if model == 'shufflenetv2':
self.Feat_ext = shufflenetv2_base(loadweight,downsample)
if downsample == 4:
self.DimRed = nn.Conv2d(232, reddim, kernel_size=1, padding=0)
else:
self.DimRed = nn.Conv2d(464, reddim, kernel_size=1, padding=0)
elif model == 'mobilenetv2':
self.Feat_ext = mobilenetv2_base(loadweight,downsample)
if downsample == 4:
self.DimRed = nn.Conv2d(96, reddim, kernel_size=1, padding=0)
else:
self.DimRed = nn.Conv2d(320, reddim, kernel_size=1, padding=0)
elif model == 'vgg16':
self.Feat_ext = vgg_base(loadweight,downsample)
self.DimRed = nn.Conv2d(512, reddim, kernel_size=1, padding=0)
elif model == 'resnet50':
self.Feat_ext = resnet50_base(loadweight,downsample)
self.DimRed = nn.Conv2d(1024, reddim, kernel_size=1, padding=0)
self.RoIAlign = RoIAlignAvg(alignsize, alignsize, 1.0/2**downsample)
self.RoDAlign = RoDAlignAvg(alignsize, alignsize, 1.0/2**downsample)
self.FC_layers = fc_layers(reddim*2, alignsize)
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model,
anchor_scales=cfg.RCNN_COMMON.ANCHOR_SCALES,
anchor_ratios=cfg.RCNN_COMMON.ANCHOR_RATIOS,
feat_stride=cfg.RCNN_COMMON.FEAT_STRIDE[0])
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.RCNN_COMMON.POOLING_SIZE,
cfg.RCNN_COMMON.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.RCNN_COMMON.POOLING_SIZE,
cfg.RCNN_COMMON.POOLING_SIZE,
1.0 / 16.0)
self.grid_size = cfg.RCNN_COMMON.POOLING_SIZE * 2 if cfg.RCNN_COMMON.CROP_RESIZE_WITH_MAX_POOL else cfg.RCNN_COMMON.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self,
alignsize=8,
reddim=32,
loadweight=True,
model=None,
downsample=4):
super(crop_model_multi_scale_individual, self).__init__()
if model == 'shufflenetv2':
self.Feat_ext1 = shufflenetv2_base(loadweight, downsample)
self.Feat_ext2 = shufflenetv2_base(loadweight, downsample)
self.Feat_ext3 = shufflenetv2_base(loadweight, downsample)
self.DimRed = nn.Conv2d(232, reddim, kernel_size=1, padding=0)
elif model == 'mobilenetv2':
self.Feat_ext1 = mobilenetv2_base(loadweight, downsample)
self.Feat_ext2 = mobilenetv2_base(loadweight, downsample)
self.Feat_ext3 = mobilenetv2_base(loadweight, downsample)
self.DimRed = nn.Conv2d(96, reddim, kernel_size=1, padding=0)
elif model == 'vgg16':
self.Feat_ext1 = vgg_base(loadweight, downsample)
self.Feat_ext2 = vgg_base(loadweight, downsample)
self.Feat_ext3 = vgg_base(loadweight, downsample)
self.DimRed = nn.Conv2d(512, reddim, kernel_size=1, padding=0)
self.downsample2 = nn.UpsamplingBilinear2d(scale_factor=1.0 / 2.0)
self.upsample2 = nn.UpsamplingBilinear2d(scale_factor=2.0)
self.RoIAlign = RoIAlignAvg(alignsize, alignsize, 1.0 / 2**downsample)
self.RoDAlign = RoDAlignAvg(alignsize, alignsize, 1.0 / 2**downsample)
self.FC_layers = fc_layers(reddim * 2, alignsize)
def __init__(self, classes, class_agnostic, feat_name, feat_list=('conv4',), pretrained = True):
super(fasterRCNN, self).__init__(classes, class_agnostic, feat_name, feat_list, pretrained)
##### Important to set model to eval mode before evaluation ####
self.FeatExt.eval()
rand_img = torch.Tensor(1, 3, 224, 224)
rand_feat = self.FeatExt(rand_img)
self.FeatExt.train()
self.dout_base_model = rand_feat.size(1)
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model,
anchor_scales=cfg.RCNN_COMMON.ANCHOR_SCALES,
anchor_ratios=cfg.RCNN_COMMON.ANCHOR_RATIOS,
feat_stride=cfg.RCNN_COMMON.FEAT_STRIDE[0])
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.RCNN_COMMON.POOLING_SIZE, cfg.RCNN_COMMON.POOLING_SIZE, 1.0/16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.RCNN_COMMON.POOLING_SIZE, cfg.RCNN_COMMON.POOLING_SIZE, 1.0/16.0)
self.grid_size = cfg.RCNN_COMMON.POOLING_SIZE * 2 if cfg.RCNN_COMMON.CROP_RESIZE_WITH_MAX_POOL else cfg.RCNN_COMMON.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
self.iter_counter = 0
def __init__(self, classes, class_agnostic):
super(_All_in_One, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self._fs = cfg.FCGN.FEAT_STRIDE[0]
# for resnet
if self.dout_base_model is None:
if self._fs == 16:
self.dout_base_model = 256 * self.expansions
elif self._fs == 32:
self.dout_base_model = 512 * self.expansions
# loss
self.VMRN_obj_loss_cls = 0
self.VMRN_obj_loss_bbox = 0
# define rpn
self.VMRN_obj_rpn = _RPN(self.dout_base_model,
anchor_scales=cfg.RCNN_COMMON.ANCHOR_SCALES,
anchor_ratios=cfg.RCNN_COMMON.ANCHOR_RATIOS,
feat_stride=self._fs)
self.VMRN_obj_proposal_target = _ProposalTargetLayer(self.n_classes)
self.VMRN_obj_roi_pool = _RoIPooling(cfg.RCNN_COMMON.POOLING_SIZE, cfg.RCNN_COMMON.POOLING_SIZE, 1.0 / 16.0)
self.VMRN_obj_roi_align = RoIAlignAvg(cfg.RCNN_COMMON.POOLING_SIZE, cfg.RCNN_COMMON.POOLING_SIZE, 1.0 / 16.0)
self.grid_size = cfg.RCNN_COMMON.POOLING_SIZE * 2 if cfg.RCNN_COMMON.CROP_RESIZE_WITH_MAX_POOL else cfg.RCNN_COMMON.POOLING_SIZE
self.VMRN_obj_roi_crop = _RoICrop()
self._isex = cfg.TRAIN.VMRN.ISEX
self.VMRN_rel_op2l = _OP2L(cfg.VMRN.OP2L_POOLING_SIZE, cfg.VMRN.OP2L_POOLING_SIZE, 1.0 / 16.0, self._isex)
self._train_iter_conter = 0
self._MGN_as = cfg.FCGN.ANCHOR_SCALES
self._MGN_ar = cfg.FCGN.ANCHOR_RATIOS
self._MGN_aa = cfg.FCGN.ANCHOR_ANGLES
# grasp detection components
self.MGN_classifier = _Classifier(self.dout_base_model, 5, self._MGN_as,
self._MGN_ar, self._MGN_aa)
self.MGN_proposal_target = _GraspTargetLayer(self._fs, self._MGN_ar,
self._MGN_as, self._MGN_aa)
self._MGN_anchors = torch.from_numpy(generate_oriented_anchors(base_size=self._fs,
scales=np.array(self._MGN_as),
ratios=np.array(self._MGN_ar),
angles=np.array(self._MGN_aa))).float()
self._MGN_num_anchors = self._MGN_anchors.size(0)
# [x1, y1, x2, y2] -> [xc, yc, w, h]
self._MGN_anchors = torch.cat([
0 * self._MGN_anchors[:, 0:1],
0 * self._MGN_anchors[:, 1:2],
self._MGN_anchors[:, 2:3] - self._MGN_anchors[:, 0:1] + 1,
self._MGN_anchors[:, 3:4] - self._MGN_anchors[:, 1:2] + 1,
self._MGN_anchors[:, 4:5]
], dim=1)
self._MGN_USE_POOLED_FEATS = cfg.MGN.USE_POOLED_FEATS
def __init__(self, classes, class_agnostic):
super(_FPN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpns
self._share_rpn = cfg.FPN.SHARE_RPN
self._share_header = cfg.FPN.SHARE_HEADER
self._num_pyramid_layers = len(cfg.RCNN_COMMON.FEAT_STRIDE)
if self._share_rpn:
self.RCNN_rpn = _RPN(self.dout_base_model,
anchor_scales=cfg.RCNN_COMMON.ANCHOR_SCALES,
anchor_ratios=cfg.RCNN_COMMON.ANCHOR_RATIOS,
feat_stride=cfg.RCNN_COMMON.FEAT_STRIDE)
else:
self.RCNN_rpns = nn.ModuleList()
for i in range(len(cfg.RCNN_COMMON.FEAT_STRIDE)):
self.RCNN_rpns.append(
_RPN(self.dout_base_model,
anchor_scales=cfg.RCNN_COMMON.ANCHOR_SCALES,
anchor_ratios=cfg.RCNN_COMMON.ANCHOR_RATIOS,
feat_stride=cfg.RCNN_COMMON.FEAT_STRIDE[i])
)
self.RCNN_roi_aligns = nn.ModuleList()
self.RCNN_roi_pools = nn.ModuleList()
for i in range(len(cfg.RCNN_COMMON.FEAT_STRIDE)):
self.RCNN_roi_aligns.append(
RoIAlignAvg(cfg.RCNN_COMMON.POOLING_SIZE,
cfg.RCNN_COMMON.POOLING_SIZE,
1.0 / float(cfg.RCNN_COMMON.FEAT_STRIDE[i]))
)
self.RCNN_roi_pools.append(
_RoIPooling(cfg.RCNN_COMMON.POOLING_SIZE,
cfg.RCNN_COMMON.POOLING_SIZE,
1.0 / float(cfg.RCNN_COMMON.FEAT_STRIDE[i]))
)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
def __init__(self, classes, class_agnostic):
super(_fastRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self,
classes,
class_agnostic,
feat_name,
feat_list=('conv2', 'conv3', 'conv4', 'conv5'),
pretrained=True):
super(FPN, self).__init__(classes, class_agnostic, feat_name,
feat_list, pretrained)
##### Important to set model to eval mode before evaluation ####
self.FeatExt.eval()
rand_img = torch.Tensor(1, 3, 224, 224)
rand_feat = self.FeatExt(rand_img)
self.FeatExt.train()
self.n_channels = [f.size(1) for f in rand_feat]
self.dout_base_model = 256
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self._num_pyramid_layers = len(cfg.RCNN_COMMON.FEAT_STRIDE)
self.RCNN_rpn = _RPN(self.dout_base_model,
anchor_scales=cfg.RCNN_COMMON.ANCHOR_SCALES,
anchor_ratios=cfg.RCNN_COMMON.ANCHOR_RATIOS,
feat_stride=cfg.RCNN_COMMON.FEAT_STRIDE)
self.RCNN_roi_aligns = nn.ModuleList()
self.RCNN_roi_pools = nn.ModuleList()
for i in range(len(cfg.RCNN_COMMON.FEAT_STRIDE)):
self.RCNN_roi_aligns.append(
RoIAlignAvg(cfg.RCNN_COMMON.POOLING_SIZE,
cfg.RCNN_COMMON.POOLING_SIZE,
1.0 / float(cfg.RCNN_COMMON.FEAT_STRIDE[i])))
self.RCNN_roi_pools.append(
_RoIPooling(cfg.RCNN_COMMON.POOLING_SIZE,
cfg.RCNN_COMMON.POOLING_SIZE,
1.0 / float(cfg.RCNN_COMMON.FEAT_STRIDE[i])))
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.iter_counter = 0