def __init__(self):
super(Aggregator, self).__init__()
self.img_resnet_dim = cfg.resnet_feat_dim[cfg.img_resnet_type]
self.pose_resnet_dim = cfg.resnet_feat_dim[cfg.pose_resnet_type]
## temporal strided conv to fuse with RGB
self.pose_frame_num = (cfg.frame_per_seg -
1) * cfg.pose_frame_factor + 1
self.pose_temporal_conv = make_conv3d_layers(
[self.pose_resnet_dim, self.pose_resnet_dim],
kernel=(5, 1, 1),
stride=(cfg.pose_frame_factor, 1, 1),
padding=(2, 0, 0))
## pose gate layer
self.pose_gate_fc = make_linear_layers(
[self.pose_resnet_dim, cfg.agg_feat_dim], relu_final=False)
## aggregation layer
self.img_conv = make_conv_layers(
[self.img_resnet_dim, cfg.agg_feat_dim], kernel=1, padding=0)
self.img_norm = nn.LayerNorm([cfg.agg_feat_dim, 1, 1])
self.pose_conv = make_conv_layers(
[self.pose_resnet_dim, cfg.agg_feat_dim], kernel=1, padding=0)
self.pose_norm = nn.LayerNorm([cfg.agg_feat_dim, 1, 1])
def __init__(self, joint_num):
super(PoseNet, self).__init__()
self.joint_num = joint_num # single hand
self.joint_deconv_1 = make_deconv_layers([2048,256,256,256])
self.joint_conv_1 = make_conv_layers([256,self.joint_num*cfg.output_hm_shape[0]],kernel=1,stride=1,padding=0,bnrelu_final=False)
self.joint_deconv_2 = make_deconv_layers([2048,256,256,256])
self.joint_conv_2 = make_conv_layers([256,self.joint_num*cfg.output_hm_shape[0]],kernel=1,stride=1,padding=0,bnrelu_final=False)
self.root_fc = make_linear_layers([2048,512,cfg.output_root_hm_shape],relu_final=False)
self.hand_fc = make_linear_layers([2048,512,2],relu_final=False)
def __init__(self, joint_num):
super(Pose2Feat, self).__init__()
self.joint_num = joint_num
self.conv = make_conv_layers(
[64 + joint_num * cfg.output_hm_shape[0], 64])
def __init__(self, joint_num, skeleton):
super(Pose2Feat, self).__init__()
self.joint_num = joint_num
self.skeleton_num = len(skeleton)
self.conv = make_conv_layers(
[self.joint_num + 2 * self.skeleton_num, 64])