search

NVIDIA-ISAAC-ROS / isaac_ros_pose_estimation

Deep learned, NVIDIA-accelerated 3D object pose estimation
https://developer.nvidia.com/isaac-ros-gems
Apache License 2.0
142 stars 21 forks source link

Can't convert the default centerpose weights in onnx from pytorch #27

Closed ArghyaChatterjee closed 10 months ago

ArghyaChatterjee commented 12 months ago

Hello, I was trying to convert the default model files for centerpose from pytorch to onnx. But I can see I can't convert them (most of them / all of them).

python3 ~/workspaces/isaac_ros-dev/src/isaac_ros_pose_estimation/isaac_ros_centerpose/scripts/centerpose_pytorch2onnx.py --input ~/Downloads/camera_v1_140.pth --output ~/Downloads/
Traceback (most recent call last):
  File "/home/arghya/workspaces/isaac_ros-dev/src/isaac_ros_pose_estimation/isaac_ros_centerpose/scripts/centerpose_pytorch2onnx.py", line 251, in <module>
    main(args)
  File "/home/arghya/workspaces/isaac_ros-dev/src/isaac_ros_pose_estimation/isaac_ros_centerpose/scripts/centerpose_pytorch2onnx.py", line 211, in main
    net.load_state_dict(torch.load(args.input)['state_dict'], strict=True)
  File "/home/arghya/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for CenterPoseNetwork:
    Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.conv3.weight", "layer1.0.bn3.weight", "layer1.0.bn3.bias", "layer1.0.bn3.running_mean", "layer1.0.bn3.running_var", "layer1.0.downsample.0.weight", "layer1.0.downsample.1.weight", "layer1.0.downsample.1.bias", "layer1.0.downsample.1.running_mean", "layer1.0.downsample.1.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.1.conv3.weight", "layer1.1.bn3.weight", "layer1.1.bn3.bias", "layer1.1.bn3.running_mean", "layer1.1.bn3.running_var", "layer1.2.conv1.weight", "layer1.2.bn1.weight", "layer1.2.bn1.bias", "layer1.2.bn1.running_mean", "layer1.2.bn1.running_var", "layer1.2.conv2.weight", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.2.conv3.weight", "layer1.2.bn3.weight", "layer1.2.bn3.bias", "layer1.2.bn3.running_mean", "layer1.2.bn3.running_var", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.conv3.weight", "layer2.0.bn3.weight", "layer2.0.bn3.bias", "layer2.0.bn3.running_mean", "layer2.0.bn3.running_var", "layer2.0.downsample.0.weight", "layer2.0.downsample.1.weight", "layer2.0.downsample.1.bias", "layer2.0.downsample.1.running_mean", "layer2.0.downsample.1.running_var", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.conv2.weight", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.1.conv3.weight", "layer2.1.bn3.weight", "layer2.1.bn3.bias", "layer2.1.bn3.running_mean", "layer2.1.bn3.running_var", "layer2.2.conv1.weight", "layer2.2.bn1.weight", "layer2.2.bn1.bias", "layer2.2.bn1.running_mean", "layer2.2.bn1.running_var", "layer2.2.conv2.weight", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.2.conv3.weight", "layer2.2.bn3.weight", "layer2.2.bn3.bias", "layer2.2.bn3.running_mean", "layer2.2.bn3.running_var", "layer2.3.conv1.weight", "layer2.3.bn1.weight", "layer2.3.bn1.bias", "layer2.3.bn1.running_mean", "layer2.3.bn1.running_var", "layer2.3.conv2.weight", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.3.conv3.weight", "layer2.3.bn3.weight", "layer2.3.bn3.bias", "layer2.3.bn3.running_mean", "layer2.3.bn3.running_var", "layer3.0.conv1.weight", "layer3.0.bn1.weight", "layer3.0.bn1.bias", "layer3.0.bn1.running_mean", "layer3.0.bn1.running_var", "layer3.0.conv2.weight", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.conv3.weight", "layer3.0.bn3.weight", "layer3.0.bn3.bias", "layer3.0.bn3.running_mean", "layer3.0.bn3.running_var", "layer3.0.downsample.0.weight", "layer3.0.downsample.1.weight", "layer3.0.downsample.1.bias", "layer3.0.downsample.1.running_mean", "layer3.0.downsample.1.running_var", "layer3.1.conv1.weight", "layer3.1.bn1.weight", "layer3.1.bn1.bias", "layer3.1.bn1.running_mean", "layer3.1.bn1.running_var", "layer3.1.conv2.weight", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.1.conv3.weight", "layer3.1.bn3.weight", "layer3.1.bn3.bias", "layer3.1.bn3.running_mean", "layer3.1.bn3.running_var", "layer3.2.conv1.weight", "layer3.2.bn1.weight", "layer3.2.bn1.bias", "layer3.2.bn1.running_mean", "layer3.2.bn1.running_var", "layer3.2.conv2.weight", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.2.conv3.weight", "layer3.2.bn3.weight", "layer3.2.bn3.bias", "layer3.2.bn3.running_mean", "layer3.2.bn3.running_var", "layer3.3.conv1.weight", "layer3.3.bn1.weight", "layer3.3.bn1.bias", "layer3.3.bn1.running_mean", "layer3.3.bn1.running_var", "layer3.3.conv2.weight", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.3.conv3.weight", "layer3.3.bn3.weight", "layer3.3.bn3.bias", "layer3.3.bn3.running_mean", "layer3.3.bn3.running_var", "layer3.4.conv1.weight", "layer3.4.bn1.weight", "layer3.4.bn1.bias", "layer3.4.bn1.running_mean", "layer3.4.bn1.running_var", "layer3.4.conv2.weight", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "layer3.4.conv3.weight", "layer3.4.bn3.weight", "layer3.4.bn3.bias", "layer3.4.bn3.running_mean", "layer3.4.bn3.running_var", "layer3.5.conv1.weight", "layer3.5.bn1.weight", "layer3.5.bn1.bias", "layer3.5.bn1.running_mean", "layer3.5.bn1.running_var", "layer3.5.conv2.weight", "layer3.5.bn2.weight", "layer3.5.bn2.bias", "layer3.5.bn2.running_mean", "layer3.5.bn2.running_var", "layer3.5.conv3.weight", "layer3.5.bn3.weight", "layer3.5.bn3.bias", "layer3.5.bn3.running_mean", "layer3.5.bn3.running_var", "layer3.6.conv1.weight", "layer3.6.bn1.weight", "layer3.6.bn1.bias", "layer3.6.bn1.running_mean", "layer3.6.bn1.running_var", "layer3.6.conv2.weight", "layer3.6.bn2.weight", "layer3.6.bn2.bias", "layer3.6.bn2.running_mean", "layer3.6.bn2.running_var", "layer3.6.conv3.weight", "layer3.6.bn3.weight", "layer3.6.bn3.bias", "layer3.6.bn3.running_mean", "layer3.6.bn3.running_var", "layer3.7.conv1.weight", "layer3.7.bn1.weight", "layer3.7.bn1.bias", "layer3.7.bn1.running_mean", "layer3.7.bn1.running_var", "layer3.7.conv2.weight", "layer3.7.bn2.weight", "layer3.7.bn2.bias", "layer3.7.bn2.running_mean", "layer3.7.bn2.running_var", "layer3.7.conv3.weight", "layer3.7.bn3.weight", "layer3.7.bn3.bias", "layer3.7.bn3.running_mean", "layer3.7.bn3.running_var", "layer3.8.conv1.weight", "layer3.8.bn1.weight", "layer3.8.bn1.bias", "layer3.8.bn1.running_mean", "layer3.8.bn1.running_var", "layer3.8.conv2.weight", "layer3.8.bn2.weight", "layer3.8.bn2.bias", "layer3.8.bn2.running_mean", "layer3.8.bn2.running_var", "layer3.8.conv3.weight", "layer3.8.bn3.weight", "layer3.8.bn3.bias", "layer3.8.bn3.running_mean", "layer3.8.bn3.running_var", "layer3.9.conv1.weight", "layer3.9.bn1.weight", "layer3.9.bn1.bias", "layer3.9.bn1.running_mean", "layer3.9.bn1.running_var", "layer3.9.conv2.weight", "layer3.9.bn2.weight", "layer3.9.bn2.bias", "layer3.9.bn2.running_mean", "layer3.9.bn2.running_var", "layer3.9.conv3.weight", "layer3.9.bn3.weight", "layer3.9.bn3.bias", "layer3.9.bn3.running_mean", "layer3.9.bn3.running_var", "layer3.10.conv1.weight", "layer3.10.bn1.weight", "layer3.10.bn1.bias", "layer3.10.bn1.running_mean", "layer3.10.bn1.running_var", "layer3.10.conv2.weight", "layer3.10.bn2.weight", "layer3.10.bn2.bias", "layer3.10.bn2.running_mean", "layer3.10.bn2.running_var", "layer3.10.conv3.weight", "layer3.10.bn3.weight", "layer3.10.bn3.bias", "layer3.10.bn3.running_mean", "layer3.10.bn3.running_var", "layer3.11.conv1.weight", "layer3.11.bn1.weight", "layer3.11.bn1.bias", "layer3.11.bn1.running_mean", "layer3.11.bn1.running_var", "layer3.11.conv2.weight", "layer3.11.bn2.weight", "layer3.11.bn2.bias", "layer3.11.bn2.running_mean", "layer3.11.bn2.running_var", "layer3.11.conv3.weight", "layer3.11.bn3.weight", "layer3.11.bn3.bias", "layer3.11.bn3.running_mean", "layer3.11.bn3.running_var", "layer3.12.conv1.weight", "layer3.12.bn1.weight", "layer3.12.bn1.bias", "layer3.12.bn1.running_mean", "layer3.12.bn1.running_var", "layer3.12.conv2.weight", "layer3.12.bn2.weight", "layer3.12.bn2.bias", "layer3.12.bn2.running_mean", "layer3.12.bn2.running_var", "layer3.12.conv3.weight", "layer3.12.bn3.weight", "layer3.12.bn3.bias", "layer3.12.bn3.running_mean", "layer3.12.bn3.running_var", "layer3.13.conv1.weight", "layer3.13.bn1.weight", "layer3.13.bn1.bias", "layer3.13.bn1.running_mean", "layer3.13.bn1.running_var", "layer3.13.conv2.weight", "layer3.13.bn2.weight", "layer3.13.bn2.bias", "layer3.13.bn2.running_mean", "layer3.13.bn2.running_var", "layer3.13.conv3.weight", "layer3.13.bn3.weight", "layer3.13.bn3.bias", "layer3.13.bn3.running_mean", "layer3.13.bn3.running_var", "layer3.14.conv1.weight", "layer3.14.bn1.weight", "layer3.14.bn1.bias", "layer3.14.bn1.running_mean", "layer3.14.bn1.running_var", "layer3.14.conv2.weight", "layer3.14.bn2.weight", "layer3.14.bn2.bias", "layer3.14.bn2.running_mean", "layer3.14.bn2.running_var", "layer3.14.conv3.weight", "layer3.14.bn3.weight", "layer3.14.bn3.bias", "layer3.14.bn3.running_mean", "layer3.14.bn3.running_var", "layer3.15.conv1.weight", "layer3.15.bn1.weight", "layer3.15.bn1.bias", "layer3.15.bn1.running_mean", "layer3.15.bn1.running_var", "layer3.15.conv2.weight", "layer3.15.bn2.weight", "layer3.15.bn2.bias", "layer3.15.bn2.running_mean", "layer3.15.bn2.running_var", "layer3.15.conv3.weight", "layer3.15.bn3.weight", "layer3.15.bn3.bias", "layer3.15.bn3.running_mean", "layer3.15.bn3.running_var", "layer3.16.conv1.weight", "layer3.16.bn1.weight", "layer3.16.bn1.bias", "layer3.16.bn1.running_mean", "layer3.16.bn1.running_var", "layer3.16.conv2.weight", "layer3.16.bn2.weight", "layer3.16.bn2.bias", "layer3.16.bn2.running_mean", "layer3.16.bn2.running_var", "layer3.16.conv3.weight", "layer3.16.bn3.weight", "layer3.16.bn3.bias", "layer3.16.bn3.running_mean", "layer3.16.bn3.running_var", "layer3.17.conv1.weight", "layer3.17.bn1.weight", "layer3.17.bn1.bias", "layer3.17.bn1.running_mean", "layer3.17.bn1.running_var", "layer3.17.conv2.weight", "layer3.17.bn2.weight", "layer3.17.bn2.bias", "layer3.17.bn2.running_mean", "layer3.17.bn2.running_var", "layer3.17.conv3.weight", "layer3.17.bn3.weight", "layer3.17.bn3.bias", "layer3.17.bn3.running_mean", "layer3.17.bn3.running_var", "layer3.18.conv1.weight", "layer3.18.bn1.weight", "layer3.18.bn1.bias", "layer3.18.bn1.running_mean", "layer3.18.bn1.running_var", "layer3.18.conv2.weight", "layer3.18.bn2.weight", "layer3.18.bn2.bias", "layer3.18.bn2.running_mean", "layer3.18.bn2.running_var", "layer3.18.conv3.weight", "layer3.18.bn3.weight", "layer3.18.bn3.bias", "layer3.18.bn3.running_mean", "layer3.18.bn3.running_var", "layer3.19.conv1.weight", "layer3.19.bn1.weight", "layer3.19.bn1.bias", "layer3.19.bn1.running_mean", "layer3.19.bn1.running_var", "layer3.19.conv2.weight", "layer3.19.bn2.weight", "layer3.19.bn2.bias", "layer3.19.bn2.running_mean", "layer3.19.bn2.running_var", "layer3.19.conv3.weight", "layer3.19.bn3.weight", "layer3.19.bn3.bias", "layer3.19.bn3.running_mean", "layer3.19.bn3.running_var", "layer3.20.conv1.weight", "layer3.20.bn1.weight", "layer3.20.bn1.bias", "layer3.20.bn1.running_mean", "layer3.20.bn1.running_var", "layer3.20.conv2.weight", "layer3.20.bn2.weight", "layer3.20.bn2.bias", "layer3.20.bn2.running_mean", "layer3.20.bn2.running_var", "layer3.20.conv3.weight", "layer3.20.bn3.weight", "layer3.20.bn3.bias", "layer3.20.bn3.running_mean", "layer3.20.bn3.running_var", "layer3.21.conv1.weight", "layer3.21.bn1.weight", "layer3.21.bn1.bias", "layer3.21.bn1.running_mean", "layer3.21.bn1.running_var", "layer3.21.conv2.weight", "layer3.21.bn2.weight", "layer3.21.bn2.bias", "layer3.21.bn2.running_mean", "layer3.21.bn2.running_var", "layer3.21.conv3.weight", "layer3.21.bn3.weight", "layer3.21.bn3.bias", "layer3.21.bn3.running_mean", "layer3.21.bn3.running_var", "layer3.22.conv1.weight", "layer3.22.bn1.weight", "layer3.22.bn1.bias", "layer3.22.bn1.running_mean", "layer3.22.bn1.running_var", "layer3.22.conv2.weight", "layer3.22.bn2.weight", "layer3.22.bn2.bias", "layer3.22.bn2.running_mean", "layer3.22.bn2.running_var", "layer3.22.conv3.weight", "layer3.22.bn3.weight", "layer3.22.bn3.bias", "layer3.22.bn3.running_mean", "layer3.22.bn3.running_var", "layer4.0.conv1.weight", "layer4.0.bn1.weight", "layer4.0.bn1.bias", "layer4.0.bn1.running_mean", "layer4.0.bn1.running_var", "layer4.0.conv2.weight", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.conv3.weight", "layer4.0.bn3.weight", "layer4.0.bn3.bias", "layer4.0.bn3.running_mean", "layer4.0.bn3.running_var", "layer4.0.downsample.0.weight", "layer4.0.downsample.1.weight", "layer4.0.downsample.1.bias", "layer4.0.downsample.1.running_mean", "layer4.0.downsample.1.running_var", "layer4.1.conv1.weight", "layer4.1.bn1.weight", "layer4.1.bn1.bias", "layer4.1.bn1.running_mean", "layer4.1.bn1.running_var", "layer4.1.conv2.weight", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "layer4.1.conv3.weight", "layer4.1.bn3.weight", "layer4.1.bn3.bias", "layer4.1.bn3.running_mean", "layer4.1.bn3.running_var", "layer4.2.conv1.weight", "layer4.2.bn1.weight", "layer4.2.bn1.bias", "layer4.2.bn1.running_mean", "layer4.2.bn1.running_var", "layer4.2.conv2.weight", "layer4.2.bn2.weight", "layer4.2.bn2.bias", "layer4.2.bn2.running_mean", "layer4.2.bn2.running_var", "layer4.2.conv3.weight", "layer4.2.bn3.weight", "layer4.2.bn3.bias", "layer4.2.bn3.running_mean", "layer4.2.bn3.running_var", "deconv_layers.0.weight", "deconv_layers.1.weight", "deconv_layers.1.bias", "deconv_layers.1.running_mean", "deconv_layers.1.running_var", "deconv_layers.3.weight", "deconv_layers.4.weight", "deconv_layers.4.bias", "deconv_layers.4.running_mean", "deconv_layers.4.running_var", "deconv_layers.6.weight", "deconv_layers.7.weight", "deconv_layers.7.bias", "deconv_layers.7.running_mean", "deconv_layers.7.running_var", "hm.2.weight", "hm.2.bias", "hm_hp.2.weight", "hm_hp.2.bias", "hp_offset.2.weight", "hp_offset.2.bias", "hps.2.weight", "hps.2.bias", "reg.2.weight", "reg.2.bias", "scale.2.weight", "scale.2.bias", "wh.2.weight", "wh.2.bias". 
    Unexpected key(s) in state_dict: "base.base_layer.0.weight", "base.base_layer.1.weight", "base.base_layer.1.bias", "base.base_layer.1.running_mean", "base.base_layer.1.running_var", "base.base_layer.1.num_batches_tracked", "base.level0.0.weight", "base.level0.1.weight", "base.level0.1.bias", "base.level0.1.running_mean", "base.level0.1.running_var", "base.level0.1.num_batches_tracked", "base.level1.0.weight", "base.level1.1.weight", "base.level1.1.bias", "base.level1.1.running_mean", "base.level1.1.running_var", "base.level1.1.num_batches_tracked", "base.level2.tree1.conv1.weight", "base.level2.tree1.bn1.weight", "base.level2.tree1.bn1.bias", "base.level2.tree1.bn1.running_mean", "base.level2.tree1.bn1.running_var", "base.level2.tree1.bn1.num_batches_tracked", "base.level2.tree1.conv2.weight", "base.level2.tree1.bn2.weight", "base.level2.tree1.bn2.bias", "base.level2.tree1.bn2.running_mean", "base.level2.tree1.bn2.running_var", "base.level2.tree1.bn2.num_batches_tracked", "base.level2.tree2.conv1.weight", "base.level2.tree2.bn1.weight", "base.level2.tree2.bn1.bias", "base.level2.tree2.bn1.running_mean", "base.level2.tree2.bn1.running_var", "base.level2.tree2.bn1.num_batches_tracked", "base.level2.tree2.conv2.weight", "base.level2.tree2.bn2.weight", "base.level2.tree2.bn2.bias", "base.level2.tree2.bn2.running_mean", "base.level2.tree2.bn2.running_var", "base.level2.tree2.bn2.num_batches_tracked", "base.level2.root.conv.weight", "base.level2.root.bn.weight", "base.level2.root.bn.bias", "base.level2.root.bn.running_mean", "base.level2.root.bn.running_var", "base.level2.root.bn.num_batches_tracked", "base.level2.project.0.weight", "base.level2.project.1.weight", "base.level2.project.1.bias", "base.level2.project.1.running_mean", "base.level2.project.1.running_var", "base.level2.project.1.num_batches_tracked", "base.level3.tree1.tree1.conv1.weight", "base.level3.tree1.tree1.bn1.weight", "base.level3.tree1.tree1.bn1.bias", "base.level3.tree1.tree1.bn1.running_mean", "base.level3.tree1.tree1.bn1.running_var", "base.level3.tree1.tree1.bn1.num_batches_tracked", "base.level3.tree1.tree1.conv2.weight", "base.level3.tree1.tree1.bn2.weight", "base.level3.tree1.tree1.bn2.bias", "base.level3.tree1.tree1.bn2.running_mean", "base.level3.tree1.tree1.bn2.running_var", "base.level3.tree1.tree1.bn2.num_batches_tracked", "base.level3.tree1.tree2.conv1.weight", "base.level3.tree1.tree2.bn1.weight", "base.level3.tree1.tree2.bn1.bias", "base.level3.tree1.tree2.bn1.running_mean", "base.level3.tree1.tree2.bn1.running_var", "base.level3.tree1.tree2.bn1.num_batches_tracked", "base.level3.tree1.tree2.conv2.weight", "base.level3.tree1.tree2.bn2.weight", "base.level3.tree1.tree2.bn2.bias", "base.level3.tree1.tree2.bn2.running_mean", "base.level3.tree1.tree2.bn2.running_var", "base.level3.tree1.tree2.bn2.num_batches_tracked", "base.level3.tree1.root.conv.weight", "base.level3.tree1.root.bn.weight", "base.level3.tree1.root.bn.bias", "base.level3.tree1.root.bn.running_mean", "base.level3.tree1.root.bn.running_var", "base.level3.tree1.root.bn.num_batches_tracked", "base.level3.tree1.project.0.weight", "base.level3.tree1.project.1.weight", "base.level3.tree1.project.1.bias", "base.level3.tree1.project.1.running_mean", "base.level3.tree1.project.1.running_var", "base.level3.tree1.project.1.num_batches_tracked", "base.level3.tree2.tree1.conv1.weight", "base.level3.tree2.tree1.bn1.weight", "base.level3.tree2.tree1.bn1.bias", "base.level3.tree2.tree1.bn1.running_mean", "base.level3.tree2.tree1.bn1.running_var", "base.level3.tree2.tree1.bn1.num_batches_tracked", "base.level3.tree2.tree1.conv2.weight", "base.level3.tree2.tree1.bn2.weight", "base.level3.tree2.tree1.bn2.bias", "base.level3.tree2.tree1.bn2.running_mean", "base.level3.tree2.tree1.bn2.running_var", "base.level3.tree2.tree1.bn2.num_batches_tracked", "base.level3.tree2.tree2.conv1.weight", "base.level3.tree2.tree2.bn1.weight", "base.level3.tree2.tree2.bn1.bias", "base.level3.tree2.tree2.bn1.running_mean", "base.level3.tree2.tree2.bn1.running_var", "base.level3.tree2.tree2.bn1.num_batches_tracked", "base.level3.tree2.tree2.conv2.weight", "base.level3.tree2.tree2.bn2.weight", "base.level3.tree2.tree2.bn2.bias", "base.level3.tree2.tree2.bn2.running_mean", "base.level3.tree2.tree2.bn2.running_var", "base.level3.tree2.tree2.bn2.num_batches_tracked", "base.level3.tree2.root.conv.weight", "base.level3.tree2.root.bn.weight", "base.level3.tree2.root.bn.bias", "base.level3.tree2.root.bn.running_mean", "base.level3.tree2.root.bn.running_var", "base.level3.tree2.root.bn.num_batches_tracked", "base.level3.project.0.weight", "base.level3.project.1.weight", "base.level3.project.1.bias", "base.level3.project.1.running_mean", "base.level3.project.1.running_var", "base.level3.project.1.num_batches_tracked", "base.level4.tree1.tree1.conv1.weight", "base.level4.tree1.tree1.bn1.weight", "base.level4.tree1.tree1.bn1.bias", "base.level4.tree1.tree1.bn1.running_mean", "base.level4.tree1.tree1.bn1.running_var", "base.level4.tree1.tree1.bn1.num_batches_tracked", "base.level4.tree1.tree1.conv2.weight", "base.level4.tree1.tree1.bn2.weight", "base.level4.tree1.tree1.bn2.bias", "base.level4.tree1.tree1.bn2.running_mean", "base.level4.tree1.tree1.bn2.running_var", "base.level4.tree1.tree1.bn2.num_batches_tracked", "base.level4.tree1.tree2.conv1.weight", "base.level4.tree1.tree2.bn1.weight", "base.level4.tree1.tree2.bn1.bias", "base.level4.tree1.tree2.bn1.running_mean", "base.level4.tree1.tree2.bn1.running_var", "base.level4.tree1.tree2.bn1.num_batches_tracked", "base.level4.tree1.tree2.conv2.weight", "base.level4.tree1.tree2.bn2.weight", "base.level4.tree1.tree2.bn2.bias", "base.level4.tree1.tree2.bn2.running_mean", "base.level4.tree1.tree2.bn2.running_var", "base.level4.tree1.tree2.bn2.num_batches_tracked", "base.level4.tree1.root.conv.weight", "base.level4.tree1.root.bn.weight", "base.level4.tree1.root.bn.bias", "base.level4.tree1.root.bn.running_mean", "base.level4.tree1.root.bn.running_var", "base.level4.tree1.root.bn.num_batches_tracked", "base.level4.tree1.project.0.weight", "base.level4.tree1.project.1.weight", "base.level4.tree1.project.1.bias", "base.level4.tree1.project.1.running_mean", "base.level4.tree1.project.1.running_var", "base.level4.tree1.project.1.num_batches_tracked", "base.level4.tree2.tree1.conv1.weight", "base.level4.tree2.tree1.bn1.weight", "base.level4.tree2.tree1.bn1.bias", "base.level4.tree2.tree1.bn1.running_mean", "base.level4.tree2.tree1.bn1.running_var", "base.level4.tree2.tree1.bn1.num_batches_tracked", "base.level4.tree2.tree1.conv2.weight", "base.level4.tree2.tree1.bn2.weight", "base.level4.tree2.tree1.bn2.bias", "base.level4.tree2.tree1.bn2.running_mean", "base.level4.tree2.tree1.bn2.running_var", "base.level4.tree2.tree1.bn2.num_batches_tracked", "base.level4.tree2.tree2.conv1.weight", "base.level4.tree2.tree2.bn1.weight", "base.level4.tree2.tree2.bn1.bias", "base.level4.tree2.tree2.bn1.running_mean", "base.level4.tree2.tree2.bn1.running_var", "base.level4.tree2.tree2.bn1.num_batches_tracked", "base.level4.tree2.tree2.conv2.weight", "base.level4.tree2.tree2.bn2.weight", "base.level4.tree2.tree2.bn2.bias", "base.level4.tree2.tree2.bn2.running_mean", "base.level4.tree2.tree2.bn2.running_var", "base.level4.tree2.tree2.bn2.num_batches_tracked", "base.level4.tree2.root.conv.weight", "base.level4.tree2.root.bn.weight", "base.level4.tree2.root.bn.bias", "base.level4.tree2.root.bn.running_mean", "base.level4.tree2.root.bn.running_var", "base.level4.tree2.root.bn.num_batches_tracked", "base.level4.project.0.weight", "base.level4.project.1.weight", "base.level4.project.1.bias", "base.level4.project.1.running_mean", "base.level4.project.1.running_var", "base.level4.project.1.num_batches_tracked", "base.level5.tree1.conv1.weight", "base.level5.tree1.bn1.weight", "base.level5.tree1.bn1.bias", "base.level5.tree1.bn1.running_mean", "base.level5.tree1.bn1.running_var", "base.level5.tree1.bn1.num_batches_tracked", "base.level5.tree1.conv2.weight", "base.level5.tree1.bn2.weight", "base.level5.tree1.bn2.bias", "base.level5.tree1.bn2.running_mean", "base.level5.tree1.bn2.running_var", "base.level5.tree1.bn2.num_batches_tracked", "base.level5.tree2.conv1.weight", "base.level5.tree2.bn1.weight", "base.level5.tree2.bn1.bias", "base.level5.tree2.bn1.running_mean", "base.level5.tree2.bn1.running_var", "base.level5.tree2.bn1.num_batches_tracked", "base.level5.tree2.conv2.weight", "base.level5.tree2.bn2.weight", "base.level5.tree2.bn2.bias", "base.level5.tree2.bn2.running_mean", "base.level5.tree2.bn2.running_var", "base.level5.tree2.bn2.num_batches_tracked", "base.level5.root.conv.weight", "base.level5.root.bn.weight", "base.level5.root.bn.bias", "base.level5.root.bn.running_mean", "base.level5.root.bn.running_var", "base.level5.root.bn.num_batches_tracked", "base.level5.project.0.weight", "base.level5.project.1.weight", "base.level5.project.1.bias", "base.level5.project.1.running_mean", "base.level5.project.1.running_var", "base.level5.project.1.num_batches_tracked", "base.fc.weight", "base.fc.bias", "dla_up.ida_0.proj_1.actf.0.weight", "dla_up.ida_0.proj_1.actf.0.bias", "dla_up.ida_0.proj_1.actf.0.running_mean", "dla_up.ida_0.proj_1.actf.0.running_var", "dla_up.ida_0.proj_1.actf.0.num_batches_tracked", "dla_up.ida_0.proj_1.conv.weight", "dla_up.ida_0.proj_1.conv.bias", "dla_up.ida_0.proj_1.conv.conv_offset_mask.weight", "dla_up.ida_0.proj_1.conv.conv_offset_mask.bias", "dla_up.ida_0.up_1.weight", "dla_up.ida_0.node_1.actf.0.weight", "dla_up.ida_0.node_1.actf.0.bias", "dla_up.ida_0.node_1.actf.0.running_mean", "dla_up.ida_0.node_1.actf.0.running_var", "dla_up.ida_0.node_1.actf.0.num_batches_tracked", "dla_up.ida_0.node_1.conv.weight", "dla_up.ida_0.node_1.conv.bias", "dla_up.ida_0.node_1.conv.conv_offset_mask.weight", "dla_up.ida_0.node_1.conv.conv_offset_mask.bias", "dla_up.ida_1.proj_1.actf.0.weight", "dla_up.ida_1.proj_1.actf.0.bias", "dla_up.ida_1.proj_1.actf.0.running_mean", "dla_up.ida_1.proj_1.actf.0.running_var", "dla_up.ida_1.proj_1.actf.0.num_batches_tracked", "dla_up.ida_1.proj_1.conv.weight", "dla_up.ida_1.proj_1.conv.bias", "dla_up.ida_1.proj_1.conv.conv_offset_mask.weight", "dla_up.ida_1.proj_1.conv.conv_offset_mask.bias", "dla_up.ida_1.up_1.weight", "dla_up.ida_1.node_1.actf.0.weight", "dla_up.ida_1.node_1.actf.0.bias", "dla_up.ida_1.node_1.actf.0.running_mean", "dla_up.ida_1.node_1.actf.0.running_var", "dla_up.ida_1.node_1.actf.0.num_batches_tracked", "dla_up.ida_1.node_1.conv.weight", "dla_up.ida_1.node_1.conv.bias", "dla_up.ida_1.node_1.conv.conv_offset_mask.weight", "dla_up.ida_1.node_1.conv.conv_offset_mask.bias", "dla_up.ida_1.proj_2.actf.0.weight", "dla_up.ida_1.proj_2.actf.0.bias", "dla_up.ida_1.proj_2.actf.0.running_mean", "dla_up.ida_1.proj_2.actf.0.running_var", "dla_up.ida_1.proj_2.actf.0.num_batches_tracked", "dla_up.ida_1.proj_2.conv.weight", "dla_up.ida_1.proj_2.conv.bias", "dla_up.ida_1.proj_2.conv.conv_offset_mask.weight", "dla_up.ida_1.proj_2.conv.conv_offset_mask.bias", "dla_up.ida_1.up_2.weight", "dla_up.ida_1.node_2.actf.0.weight", "dla_up.ida_1.node_2.actf.0.bias", "dla_up.ida_1.node_2.actf.0.running_mean", "dla_up.ida_1.node_2.actf.0.running_var", "dla_up.ida_1.node_2.actf.0.num_batches_tracked", "dla_up.ida_1.node_2.conv.weight", "dla_up.ida_1.node_2.conv.bias", "dla_up.ida_1.node_2.conv.conv_offset_mask.weight", "dla_up.ida_1.node_2.conv.conv_offset_mask.bias", "dla_up.ida_2.proj_1.actf.0.weight", "dla_up.ida_2.proj_1.actf.0.bias", "dla_up.ida_2.proj_1.actf.0.running_mean", "dla_up.ida_2.proj_1.actf.0.running_var", "dla_up.ida_2.proj_1.actf.0.num_batches_tracked", "dla_up.ida_2.proj_1.conv.weight", "dla_up.ida_2.proj_1.conv.bias", "dla_up.ida_2.proj_1.conv.conv_offset_mask.weight", "dla_up.ida_2.proj_1.conv.conv_offset_mask.bias", "dla_up.ida_2.up_1.weight", "dla_up.ida_2.node_1.actf.0.weight", "dla_up.ida_2.node_1.actf.0.bias", "dla_up.ida_2.node_1.actf.0.running_mean", "dla_up.ida_2.node_1.actf.0.running_var", "dla_up.ida_2.node_1.actf.0.num_batches_tracked", "dla_up.ida_2.node_1.conv.weight", "dla_up.ida_2.node_1.conv.bias", "dla_up.ida_2.node_1.conv.conv_offset_mask.weight", "dla_up.ida_2.node_1.conv.conv_offset_mask.bias", "dla_up.ida_2.proj_2.actf.0.weight", "dla_up.ida_2.proj_2.actf.0.bias", "dla_up.ida_2.proj_2.actf.0.running_mean", "dla_up.ida_2.proj_2.actf.0.running_var", "dla_up.ida_2.proj_2.actf.0.num_batches_tracked", "dla_up.ida_2.proj_2.conv.weight", "dla_up.ida_2.proj_2.conv.bias", "dla_up.ida_2.proj_2.conv.conv_offset_mask.weight", "dla_up.ida_2.proj_2.conv.conv_offset_mask.bias", "dla_up.ida_2.up_2.weight", "dla_up.ida_2.node_2.actf.0.weight", "dla_up.ida_2.node_2.actf.0.bias", "dla_up.ida_2.node_2.actf.0.running_mean", "dla_up.ida_2.node_2.actf.0.running_var", "dla_up.ida_2.node_2.actf.0.num_batches_tracked", "dla_up.ida_2.node_2.conv.weight", "dla_up.ida_2.node_2.conv.bias", "dla_up.ida_2.node_2.conv.conv_offset_mask.weight", "dla_up.ida_2.node_2.conv.conv_offset_mask.bias", "dla_up.ida_2.proj_3.actf.0.weight", "dla_up.ida_2.proj_3.actf.0.bias", "dla_up.ida_2.proj_3.actf.0.running_mean", "dla_up.ida_2.proj_3.actf.0.running_var", "dla_up.ida_2.proj_3.actf.0.num_batches_tracked", "dla_up.ida_2.proj_3.conv.weight", "dla_up.ida_2.proj_3.conv.bias", "dla_up.ida_2.proj_3.conv.conv_offset_mask.weight", "dla_up.ida_2.proj_3.conv.conv_offset_mask.bias", "dla_up.ida_2.up_3.weight", "dla_up.ida_2.node_3.actf.0.weight", "dla_up.ida_2.node_3.actf.0.bias", "dla_up.ida_2.node_3.actf.0.running_mean", "dla_up.ida_2.node_3.actf.0.running_var", "dla_up.ida_2.node_3.actf.0.num_batches_tracked", "dla_up.ida_2.node_3.conv.weight", "dla_up.ida_2.node_3.conv.bias", "dla_up.ida_2.node_3.conv.conv_offset_mask.weight", "dla_up.ida_2.node_3.conv.conv_offset_mask.bias", "convGRU.cell0.Wir.weight", "convGRU.cell0.Wir.bias", "convGRU.cell0.Whr.weight", "convGRU.cell0.Wiz.weight", "convGRU.cell0.Wiz.bias", "convGRU.cell0.Whz.weight", "convGRU.cell0.Win.weight", "convGRU.cell0.Win.bias", "convGRU.cell0.Whn.weight", "ida_up.proj_1.actf.0.weight", "ida_up.proj_1.actf.0.bias", "ida_up.proj_1.actf.0.running_mean", "ida_up.proj_1.actf.0.running_var", "ida_up.proj_1.actf.0.num_batches_tracked", "ida_up.proj_1.conv.weight", "ida_up.proj_1.conv.bias", "ida_up.proj_1.conv.conv_offset_mask.weight", "ida_up.proj_1.conv.conv_offset_mask.bias", "ida_up.up_1.weight", "ida_up.node_1.actf.0.weight", "ida_up.node_1.actf.0.bias", "ida_up.node_1.actf.0.running_mean", "ida_up.node_1.actf.0.running_var", "ida_up.node_1.actf.0.num_batches_tracked", "ida_up.node_1.conv.weight", "ida_up.node_1.conv.bias", "ida_up.node_1.conv.conv_offset_mask.weight", "ida_up.node_1.conv.conv_offset_mask.bias", "ida_up.proj_2.actf.0.weight", "ida_up.proj_2.actf.0.bias", "ida_up.proj_2.actf.0.running_mean", "ida_up.proj_2.actf.0.running_var", "ida_up.proj_2.actf.0.num_batches_tracked", "ida_up.proj_2.conv.weight", "ida_up.proj_2.conv.bias", "ida_up.proj_2.conv.conv_offset_mask.weight", "ida_up.proj_2.conv.conv_offset_mask.bias", "ida_up.up_2.weight", "ida_up.node_2.actf.0.weight", "ida_up.node_2.actf.0.bias", "ida_up.node_2.actf.0.running_mean", "ida_up.node_2.actf.0.running_var", "ida_up.node_2.actf.0.num_batches_tracked", "ida_up.node_2.conv.weight", "ida_up.node_2.conv.bias", "ida_up.node_2.conv.conv_offset_mask.weight", "ida_up.node_2.conv.conv_offset_mask.bias", "hm.3.weight", "hm.3.bias", "hm.1.weight", "hm.1.bias", "hm_hp.3.weight", "hm_hp.3.bias", "hm_hp.1.weight", "hm_hp.1.bias", "hp_offset.3.weight", "hp_offset.3.bias", "hp_offset.1.weight", "hp_offset.1.bias", "hps.3.weight", "hps.3.bias", "hps.1.weight", "hps.1.bias", "reg.3.weight", "reg.3.bias", "reg.1.weight", "reg.1.bias", "scale.3.weight", "scale.3.bias", "scale.1.weight", "scale.1.bias", "wh.3.weight", "wh.3.bias", "wh.1.weight", "wh.1.bias". 
    size mismatch for hm.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for hm.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for hm_hp.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for hm_hp.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for hp_offset.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for hp_offset.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for hps.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for hps.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for reg.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for reg.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for scale.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for scale.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).
    size mismatch for wh.0.weight: copying a param with shape torch.Size([256, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 3, 3]).
    size mismatch for wh.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]).

This happens for all the models that exist in the centerpose repo.

Also, I think there should be a separate demo for the centerpose repo. The demo that you provide here is for DOPE only. A separate demo for centerpose will be good.

Thanks in advance.

swapnesh-wani-nvidia commented 12 months ago

Hello, could you please look at the demo for centerpose listed here. Also, I was able to convert the models pointed out in the demo listed above. It looks like your custom model has mismatched binding names.