[Feature]: Support MoCa #327
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## 1.0 #327 +/- ##
==========================================
- Coverage 49.71% 48.97% -0.75%
==========================================
Files 181 184 +3
Lines 12451 12689 +238
Branches 1951 2005 +54
==========================================
+ Hits 6190 6214 +24
- Misses 5871 6091 +220
+ Partials 390 384 -6
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
|
|
||
| @OBJECTSAMPLERS.register_module() | ||
| class MMDataBaseSampler(DataBaseSampler): | ||
|
|
| results['img_shape'] = img.shape | ||
| results['ori_shape'] = img.shape | ||
| # Set initial values for default meta_keys | ||
| results['pad_shape'] = img.shape |
There was a problem hiding this comment.
Other keys like scale_factor and img_norm_cfg are not used any longer?
| @@ -77,11 +78,11 @@ def __call__(self, results): | |||
| # modified from `flip_aug = [False, True] if self.flip else [False]` | |||
| # to reduce unnecessary scenes when using double flip augmentation | |||
| # during test time | |||
| flip_aug = [True] if self.flip else [False] | |||
| flip_aug = [False, True] if self.flip else [False] | |||
There was a problem hiding this comment.
This seems to be a conflict. Please make sure this modification will not affect current models.
…a-kitti Conflicts: mmdet3d/models/fusion_layers/point_fusion.py
| (w_scale, h_scale). | ||
| img_crop_offset (torch.Tensor): Crop offset used to crop \ |
There was a problem hiding this comment.
Should keep the '' because it is needed when converting the API documentation?
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = None | ||
| # You may need to download the model first is the network is unstable |
There was a problem hiding this comment.
typo 'is the network is unstable'?
|
Looks like |
It seems that moca needs instance_train.json which is the instance segmentation results of KITTI train split to produce this file. I also want to know whether moca would provide this file later. |
* start up * zh-cn v0.1 * [Docs] Add a from-scratch example for "Get Started" (open-mmlab#326) * Add a from-scratch example * Fix typo * resolve comment * bachslash * Resolve comments * Refine commands * add cn docs * Correct commands * fixing... * update zn-cn docs * update en link * add sdk's get-started (open-mmlab#331) * add sdk's get-started * add SDK build command * fix chinglish * add sdk get start zh_cn * update zh_cn cite * fix command * add selfsup/razor readme * Fix command Co-authored-by: Yifan Zhou <singlezombie@163.com> Co-authored-by: lvhan028 <lvhan_028@163.com>
This is the official code release of paper: Multi-Modality Cut and Paste for 3D Object Detection. This PR includes the implementation of Hybrid Optimizer and multi-modality cut and paste on the KITTI dataset.