[Fix]: add convert script for Votenet

[encore-zhou]

Fix issue #145 by converting the keys in the checkpoints of votenet models.

[codecov]

Codecov Report

Merging #163 into master will decrease coverage by 0.81%.
The diff coverage is 16.61%.

@@            Coverage Diff             @@
##           master     #163      +/-   ##
==========================================
- Coverage   50.31%   49.49%   -0.82%     
==========================================
  Files         164      165       +1     
  Lines       10749    11019     +270     
  Branches     1622     1669      +47     
==========================================
+ Hits         5408     5454      +46     
- Misses       5017     5241     +224     
  Partials      324      324              

Flag	Coverage Δ
#unittests	49.49% <16.61%> (-0.82%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmdet3d/core/anchor/__init__.py	100.00% <ø> (ø)
mmdet3d/models/dense_heads/anchor3d_head.py	61.85% <0.00%> (ø)
mmdet3d/models/dense_heads/train_mixins.py	6.47% <0.00%> (-2.02%)	⬇️
...et3d/models/roi_heads/mask_heads/primitive_head.py	18.91% <6.89%> (-2.49%)	⬇️
mmdet3d/models/dense_heads/shape_aware_head.py	13.55% <13.55%> (ø)
mmdet3d/core/anchor/anchor_3d_generator.py	94.24% <100.00%> (+0.96%)	⬆️
mmdet3d/models/dense_heads/__init__.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update f05828b...23458a7. Read the comment docs.

[EricWiener]

This is still an issue. When I run python tools/test.py configs/votenet/votenet_16x8_sunrgbd-3d-10class.py checkpoints/votenet_16x8_sunrgbd-3d-10class_20200620_230238-4483c0c0.pth --show --show-dir ./data/votenet/show_results, I get the message:

/home/eric/miniconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/cnn/bricks/conv_module.py:107: UserWarning: ConvModule has norm and bias at the same time
  warnings.warn('ConvModule has norm and bias at the same time')
The model and loaded state dict do not match exactly

unexpected key in source state_dict: bbox_head.conv_pred.0.conv.weight, bbox_head.conv_pred.0.conv.bias, bbox_head.conv_pred.0.bn.weight, bbox_head.conv_pred.0.bn.bias, bbox_head.conv_pred.0.bn.running_mean, bbox_head.conv_pred.0.bn.running_var, bbox_head.conv_pred.0.bn.num_batches_tracked, bbox_head.conv_pred.1.conv.weight, bbox_head.conv_pred.1.conv.bias, bbox_head.conv_pred.1.bn.weight, bbox_head.conv_pred.1.bn.bias, bbox_head.conv_pred.1.bn.running_mean, bbox_head.conv_pred.1.bn.running_var, bbox_head.conv_pred.1.bn.num_batches_tracked, bbox_head.conv_pred.conv_out.weight, bbox_head.conv_pred.conv_out.bias

missing keys in source state_dict: bbox_head.conv_pred.shared_convs.layer0.conv.weight, bbox_head.conv_pred.shared_convs.layer0.conv.bias, bbox_head.conv_pred.shared_convs.layer0.bn.weight, bbox_head.conv_pred.shared_convs.layer0.bn.bias, bbox_head.conv_pred.shared_convs.layer0.bn.running_mean, bbox_head.conv_pred.shared_convs.layer0.bn.running_var, bbox_head.conv_pred.shared_convs.layer1.conv.weight, bbox_head.conv_pred.shared_convs.layer1.conv.bias, bbox_head.conv_pred.shared_convs.layer1.bn.weight, bbox_head.conv_pred.shared_convs.layer1.bn.bias, bbox_head.conv_pred.shared_convs.layer1.bn.running_mean, bbox_head.conv_pred.shared_convs.layer1.bn.running_var, bbox_head.conv_pred.conv_cls.weight, bbox_head.conv_pred.conv_cls.bias, bbox_head.conv_pred.conv_reg.weight, bbox_head.conv_pred.conv_reg.bias