-
Notifications
You must be signed in to change notification settings - Fork 1.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature]: Support MoCa #327
base: 1.0
Are you sure you want to change the base?
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): | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Docstring
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also for the functions below.
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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This seems to be a conflict. Please make sure this modification will not affect current models.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Unit test may be added in next version.
…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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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.