Skip to content

GitLab

Commit acdb300d authored by Jingwei Zhang's avatar Jingwei Zhang Committed by ZwwWayne
Browse files

Update docs && support loading old checkpoints in FCAF3D (#1974) 

* add loading converted keys and README, metafile

* update readme

* reorganize readme

* add version in FCAF3d detector
parent a894b8bf
Hide whitespace changes
Inline Side-by-side
Showing with 188 additions and 48 deletions
README.md
View file @ acdb300d
...@@ -165,6 +165,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md). ...@@ -165,6 +165,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
<li><a href="configs/votenet">VoteNet (ICCV'2019)</a></li> <li><a href="configs/votenet">VoteNet (ICCV'2019)</a></li>
<li><a href="configs/h3dnet">H3DNet (ECCV'2020)</a></li> <li><a href="configs/h3dnet">H3DNet (ECCV'2020)</a></li>
<li><a href="configs/groupfree3d">Group-Free-3D (ICCV'2021)</a></li> <li><a href="configs/groupfree3d">Group-Free-3D (ICCV'2021)</a></li>
<li><a href="configs/fcaf3d">FCAF3D (ECCV'2022)</a></li>
</ul> </ul>
</td> </td>
<td> <td>
...@@ -202,29 +203,30 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md). ...@@ -202,29 +203,30 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
</tbody> </tbody>
</table> </table>
| | ResNet | ResNeXt | SENet | PointNet++ | DGCNN | HRNet | RegNetX | Res2Net | DLA | | | ResNet | ResNeXt | SENet | PointNet++ | DGCNN | HRNet | RegNetX | Res2Net | DLA | MinkResNet |
| ------------- | :----: | :-----: | :---: | :--------: | :---: | :---: | :-----: | :-----: | :-: | | ------------- | :----: | :-----: | :---: | :--------: | :---: | :---: | :-----: | :-----: | :-: | :--------: |
| SECOND | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | SECOND | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| PointPillars | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | PointPillars | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| FreeAnchor | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | FreeAnchor | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| VoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | VoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| H3DNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | H3DNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 3DSSD | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | 3DSSD | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| SSN | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | SSN | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| ImVoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | ImVoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| FCOS3D | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | FCOS3D | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| PointNet++ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | PointNet++ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Group-Free-3D | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | Group-Free-3D | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| ImVoxelNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | | ImVoxelNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| PAConv | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | PAConv | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| DGCNN | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | | DGCNN | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
| SMOKE | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | | SMOKE | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ |
| PGD | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | PGD | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| MonoFlex | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | | MonoFlex | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ |
| SA-SSD | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | SA-SSD | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| FCAF3D | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ |
**Note:** All the about **300+ models, methods of 40+ papers** in 2D detection supported by [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/model_zoo.md) can be trained or used in this codebase. **Note:** All the about **300+ models, methods of 40+ papers** in 2D detection supported by [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/model_zoo.md) can be trained or used in this codebase.
......
README_zh-CN.md
View file @ acdb300d
...@@ -165,6 +165,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱，下一代 ...@@ -165,6 +165,7 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱，下一代
<li><a href="configs/votenet">VoteNet (ICCV'2019)</a></li> <li><a href="configs/votenet">VoteNet (ICCV'2019)</a></li>
<li><a href="configs/h3dnet">H3DNet (ECCV'2020)</a></li> <li><a href="configs/h3dnet">H3DNet (ECCV'2020)</a></li>
<li><a href="configs/groupfree3d">Group-Free-3D (ICCV'2021)</a></li> <li><a href="configs/groupfree3d">Group-Free-3D (ICCV'2021)</a></li>
<li><a href="configs/fcaf3d">FCAF3D (ECCV'2022)</a></li>
</ul> </ul>
</td> </td>
<td> <td>
...@@ -202,29 +203,30 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱，下一代 ...@@ -202,29 +203,30 @@ MMDetection3D 是一个基于 PyTorch 的目标检测开源工具箱，下一代
</tbody> </tbody>
</table> </table>
| | ResNet | ResNeXt | SENet | PointNet++ | DGCNN | HRNet | RegNetX | Res2Net | DLA | | | ResNet | ResNeXt | SENet | PointNet++ | DGCNN | HRNet | RegNetX | Res2Net | DLA | MinkResNet |
| ------------- | :----: | :-----: | :---: | :--------: | :---: | :---: | :-----: | :-----: | :-: | | ------------- | :----: | :-----: | :---: | :--------: | :---: | :---: | :-----: | :-----: | :-: | :--------: |
| SECOND | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | SECOND | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| PointPillars | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | PointPillars | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| FreeAnchor | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | FreeAnchor | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| VoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | VoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| H3DNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | H3DNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 3DSSD | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | 3DSSD | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | Part-A2 | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | MVXNet | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | CenterPoint | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| SSN | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | | SSN | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ✓ | ☐ | ✗ | ✗ |
| ImVoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | ImVoteNet | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| FCOS3D | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | FCOS3D | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| PointNet++ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | PointNet++ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Group-Free-3D | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | Group-Free-3D | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| ImVoxelNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | | ImVoxelNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| PAConv | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | | PAConv | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| DGCNN | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | | DGCNN | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
| SMOKE | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | | SMOKE | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ |
| PGD | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | PGD | ✓ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| MonoFlex | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | | MonoFlex | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ |
| SA-SSD | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | | SA-SSD | ☐ | ☐ | ☐ | ✗ | ✗ | ☐ | ☐ | ☐ | ✗ | ✗ |
| FCAF3D | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ |
**注意：**[MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/zh_cn/model_zoo.md) 支持的基于 2D 检测的 **300+ 个模型，40+ 的论文算法**在 MMDetection3D 中都可以被训练或使用。 **注意：**[MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/zh_cn/model_zoo.md) 支持的基于 2D 检测的 **300+ 个模型，40+ 的论文算法**在 MMDetection3D 中都可以被训练或使用。
......
configs/fcaf3d/README.md 0 → 100644
View file @ acdb300d
# FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
> [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://arxiv.org/abs/2112.00322)
<!-- [ALGORITHM] -->
## Abstract
Recently, promising applications in robotics and augmented reality have attracted considerable attention to 3D object detection from point clouds. In this paper, we present FCAF3D --- a first-in-class fully convolutional anchor-free indoor 3D object detection method. It is a simple yet effective method that uses a voxel representation of a point cloud and processes voxels with sparse convolutions. FCAF3D can handle large-scale scenes with minimal runtime through a single fully convolutional feed-forward pass. Existing 3D object detection methods make prior assumptions on the geometry of objects, and we argue that it limits their generalization ability. To eliminate prior assumptions, we propose a novel parametrization of oriented bounding boxes that allows obtaining better results in a purely data-driven way. The proposed method achieves state-of-the-art 3D object detection results in terms of mAP@0.5 on ScanNet V2 (+4.5), SUN RGB-D (+3.5), and S3DIS (+20.5) datasets.
<div align="center">
<img src="https://user-images.githubusercontent.com/6030962/182842796-98c10576-d39c-4c2b-a15a-a04c9870919c.png" width="800"/>
</div>
## Introduction
We implement FCAF3D and provide the result and checkpoints on the ScanNet and SUN RGB-D dataset.
## Results and models
### ScanNet
| Backbone | Mem (GB) | Inf time (fps) | AP@0.25 | AP@0.5 | Download |
| :------------------------------------------------: | :------: | :------------: | :----------: | :----------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [MinkResNet34](./fcaf3d_8x2_scannet-3d-18class.py) | 10.5 | 8.0 | 69.7(70.7\*) | 55.2(56.0\*) | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/fcaf3d/fcaf3d_8x2_scannet-3d-18class/fcaf3d_8x2_scannet-3d-18class_20220805_084956.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/fcaf3d/fcaf3d_8x2_scannet-3d-18class/fcaf3d_8x2_scannet-3d-18class_20220805_084956.log.json) |
### SUN RGB-D
| Backbone | Mem (GB) | Inf time (fps) | AP@0.25 | AP@0.5 | Download |
| :------------------------------------------------: | :------: | :------------: | :----------: | :----------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [MinkResNet34](./fcaf3d_8x2_sunrgbd-3d-10class.py) | 6.3 | 15.6 | 63.8(63.8\*) | 47.3(48.2\*) | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/fcaf3d/fcaf3d_8x2_sunrgbd-3d-10class/fcaf3d_8x2_sunrgbd-3d-10class_20220805_165017.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/fcaf3d/fcaf3d_8x2_sunrgbd-3d-10class/fcaf3d_8x2_sunrgbd-3d-10class_20220805_165017.log.json) |
**Note**
- We report the results across 5 train runs followed by 5 test runs. * means the results reported in the paper.
- Inference time is given for a single NVidia GeForce GTX 1080 Ti GPU. All models are trained on 2 GPUs.
## Citation
```latex
@inproceedings{rukhovich2022fcaf3d,
title={FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection},
author={Danila Rukhovich, Anna Vorontsova, Anton Konushin},
booktitle={European conference on computer vision},
year={2022}
}
```
configs/fcaf3d/metafile.yml 0 → 100644
View file @ acdb300d
Collections:
- Name: FCAF3D
Metadata:
Training Techniques:
- AdamW
Training Resources: 2x V100 GPUs
Architecture:
- MinkResNet
Paper:
URL: https://arxiv.org/abs/2112.00322
Title: 'FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection'
README: configs/fcaf3d/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/models/detectors/mink_single_stage.py#L15
Version: v1.0.0rc4
Models:
- Name: fcaf3d_2xb8_scannet-3d-18class
In Collection: FCAF3D
Config: configs/fcaf3d/fcaf3d_2xb8_scannet-3d-18class.py
Metadata:
Training Data: ScanNet
Training Memory (GB): 10.7
Results:
- Task: 3D Object Detection
Dataset: ScanNet
Metrics:
AP@0.25: 69.7
AP@0.5: 55.2
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/fcaf3d/fcaf3d_8x2_scannet-3d-18class/fcaf3d_8x2_scannet-3d-18class_20220805_084956.pth
- Name: fcaf3d_2xb8_sunrgbd-3d-10class
In Collection: FCAF3D
Config: configs/fcaf3d/fcaf3d_2xb8_sunrgbd-3d-10class.py
Metadata:
Training Data: SUNRGBD
Training Memory (GB): 6.5
Results:
- Task: 3D Object Detection
Dataset: SUNRGBD
Metrics:
AP@0.25: 63.76
AP@0.5: 47.31
Weights: https://download.openmmlab.com/mmdetection3d/v1.0.0_models/fcaf3d/fcaf3d_8x2_sunrgbd-3d-10class/fcaf3d_8x2_sunrgbd-3d-10class_20220805_165017.pth
mmdet3d/models/detectors/mink_single_stage.py
View file @ acdb300d
# Copyright (c) OpenMMLab. All rights reserved. # Copyright (c) OpenMMLab. All rights reserved.
# Adapted from https://github.com/SamsungLabs/fcaf3d/blob/master/mmdet3d/models/detectors/single_stage_sparse.py # noqa # Adapted from https://github.com/SamsungLabs/fcaf3d/blob/master/mmdet3d/models/detectors/single_stage_sparse.py # noqa
from typing import Dict, Tuple, Union from typing import Dict, List, OrderedDict, Tuple, Union
import torch import torch
from torch import Tensor from torch import Tensor
...@@ -38,6 +38,7 @@ class MinkSingleStage3DDetector(SingleStage3DDetector): ...@@ -38,6 +38,7 @@ class MinkSingleStage3DDetector(SingleStage3DDetector):
init_cfg (dict or ConfigDict, optional): the config to control the init_cfg (dict or ConfigDict, optional): the config to control the
initialization. Defaults to None. initialization. Defaults to None.
""" """
_version = 2
def __init__(self, def __init__(self,
backbone: ConfigType, backbone: ConfigType,
...@@ -87,3 +88,47 @@ class MinkSingleStage3DDetector(SingleStage3DDetector): ...@@ -87,3 +88,47 @@ class MinkSingleStage3DDetector(SingleStage3DDetector):
if self.with_neck: if self.with_neck:
x = self.neck(x) x = self.neck(x)
return x return x
def _load_from_state_dict(self, state_dict: OrderedDict, prefix: str,
local_metadata: Dict, strict: bool,
missing_keys: List[str],
unexpected_keys: List[str],
error_msgs: List[str]) -> None:
"""Load checkpoint.
Args:
state_dict (dict): a dict containing parameters and
persistent buffers.
prefix (str): the prefix for parameters and buffers used in this
module
local_metadata (dict): a dict containing the metadata for this
module.
strict (bool): whether to strictly enforce that the keys in
:attr:`state_dict` with :attr:`prefix` match the names of
parameters and buffers in this module
missing_keys (list of str): if ``strict=True``, add missing keys to
this list
unexpected_keys (list of str): if ``strict=True``, add unexpected
keys to this list
error_msgs (list of str): error messages should be added to this
list, and will be reported together in
:meth:`~torch.nn.Module.load_state_dict`
"""
# The names of some parameters in FCAF3D has been changed
# since 2022.10.
version = local_metadata.get('version', None)
if (version is None or
version < 2) and self.__class__ is MinkSingleStage3DDetector:
convert_dict = {'head.': 'bbox_head.'}
state_dict_keys = list(state_dict.keys())
for k in state_dict_keys:
for ori_key, convert_key in convert_dict.items():
if ori_key in k:
convert_key = k.replace(ori_key, convert_key)
state_dict[convert_key] = state_dict[k]
del state_dict[k]
super(MinkSingleStage3DDetector,
self)._load_from_state_dict(state_dict, prefix, local_metadata,
strict, missing_keys,
unexpected_keys, error_msgs)
tests/test_models/test_detectors/test_fcaf3d.py
View file @ acdb300d
...@@ -21,7 +21,7 @@ class TestFCAF3d(unittest.TestCase): ...@@ -21,7 +21,7 @@ class TestFCAF3d(unittest.TestCase):
DefaultScope.get_instance('test_fcaf3d', scope_name='mmdet3d') DefaultScope.get_instance('test_fcaf3d', scope_name='mmdet3d')
_setup_seed(0) _setup_seed(0)
fcaf3d_net_cfg = _get_detector_cfg( fcaf3d_net_cfg = _get_detector_cfg(
'fcaf3d/fcaf3d_8xb2_scannet-3d-18class.py') 'fcaf3d/fcaf3d_2xb8_scannet-3d-18class.py')
model = MODELS.build(fcaf3d_net_cfg) model = MODELS.build(fcaf3d_net_cfg)
num_gt_instance = 3 num_gt_instance = 3
packed_inputs = _create_detector_inputs( packed_inputs = _create_detector_inputs(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment