Skip to content

GitLab

"docs/en/getting_started.md" did not exist on "5d9682a27c4581d5724401873a62fa3019b53f4b"
Unverified Commit f885d28a authored by VVsssssk's avatar VVsssssk Committed by GitHub
Browse files

[Refactor] Update configs name (#1757) 

* fix cfg name

* update cfg name

* fix cfg

* fix comments

* fix comment

* fix comments
parent ea22f8ec
Hide whitespace changes
Inline Side-by-side
Showing with 56 additions and 50 deletions
configs/nuimages/mask_rcnn_r50_caffe_fpn_1x_nuim.py → configs/nuimages/mask-rcnn_r50_caffe_fpn_1x_nuim.py
View file @ f885d28a
_base_ = [
'../_base_/models/mask_rcnn_r50_fpn.py',
'../_base_/datasets/nuim_instance.py',
'../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
'../_base_/models/mask-rcnn_r50_fpn.py',
'../_base_/datasets/nuim-instance.py',
'../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py'
]
model = dict(
pretrained='open-mmlab://detectron2/resnet50_caffe',
......
configs/nuimages/mask_rcnn_r50_caffe_fpn_coco-3x_1x_nuim.py → configs/nuimages/mask-rcnn_r50_caffe_fpn_coco-3x_1x_nuim.py
View file @ f885d28a
_base_ = [
'../_base_/models/mask_rcnn_r50_fpn.py',
'../_base_/datasets/nuim_instance.py',
'../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
'../_base_/models/mask-rcnn_r50_fpn.py',
'../_base_/datasets/nuim-instance.py',
'../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py'
]
model = dict(
pretrained='open-mmlab://detectron2/resnet50_caffe',
......
configs/nuimages/mask_rcnn_r50_caffe_fpn_coco-3x_20e_nuim.py → configs/nuimages/mask-rcnn_r50_caffe_fpn_coco-3x_20e_nuim.py
View file @ f885d28a
_base_ = [
'../_base_/models/mask_rcnn_r50_fpn.py',
'../_base_/datasets/nuim_instance.py',
'../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
'../_base_/models/mask-rcnn_r50_fpn.py',
'../_base_/datasets/nuim-instance.py',
'../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py'
]
model = dict(
pretrained='open-mmlab://detectron2/resnet50_caffe',
......
configs/nuimages/mask_rcnn_r50_fpn_1x_nuim.py → configs/nuimages/mask-rcnn_r50_fpn_1x_nuim.py
View file @ f885d28a
_base_ = [
'../_base_/models/mask_rcnn_r50_fpn.py',
'../_base_/datasets/nuim_instance.py',
'../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
'../_base_/models/mask-rcnn_r50_fpn.py',
'../_base_/datasets/nuim-instance.py',
'../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py'
]
model = dict(
roi_head=dict(
......
configs/nuimages/mask_rcnn_r50_fpn_coco-2x_1x_nuim.py → configs/nuimages/mask-rcnn_r50_fpn_coco-2x_1x_nuim.py
View file @ f885d28a
_base_ = [
'../_base_/models/mask_rcnn_r50_fpn.py',
'../_base_/datasets/nuim_instance.py',
'../_base_/schedules/mmdet_schedule_1x.py', '../_base_/default_runtime.py'
'../_base_/models/mask-rcnn_r50_fpn.py',
'../_base_/datasets/nuim-instance.py',
'../_base_/schedules/mmdet-schedule-1x.py', '../_base_/default_runtime.py'
]
model = dict(
roi_head=dict(
......
configs/nuimages/metafile.yml
View file @ f885d28a
......@@ -86,7 +86,7 @@ Models:
- Name: mask_rcnn_r101_fpn_1x_nuim
In Collection: Mask R-CNN
Config: configs/nuimages/mask_rcnn_r101_fpn_1x_nuim.py
Config: configs/nuimages/mask-rcnn_r101_fpn_1x_nuim.py
Metadata:
Training Memory (GB): 10.9
Training Resources: 8x TITAN Xp
......@@ -103,7 +103,7 @@ Models:
- Name: mask_rcnn_x101_32x4d_fpn_1x_nuim
In Collection: Mask R-CNN
Config: configs/nuimages/mask_rcnn_x101_32x4d_fpn_1x_nuim.py
Config: configs/nuimages/mask-rcnn_x101_32x4d_fpn_1x_nuim.py
Metadata:
Training Memory (GB): 13.3
Training Resources: 8x TITAN Xp
......
configs/paconv/README.md
View file @ f885d28a
......@@ -23,10 +23,10 @@ We implement PAConv and provide the result and checkpoints on S3DIS dataset.
### S3DIS
| Method | Split | Lr schd | Mem (GB) | Inf time (fps) | mIoU (Val set) | Download |
| :-------------------------------------------------------------------------: | :----: | :---------: | :------: | :------------: | :------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [PAConv (SSG)](./paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class.py) | Area_5 | cosine 150e | 5.8 | | 66.65 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class_20210729_200615-2147b2d1.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class_20210729_200615.log.json) |
| [PAConv\* (SSG)](./paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class.py) | Area_5 | cosine 200e | 3.8 | | 65.33 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class_20210802_171802-e5ea9bb9.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class_20210802_171802.log.json) |
| Method | Split | Lr schd | Mem (GB) | Inf time (fps) | mIoU (Val set) | Download |
| :---------------------------------------------------------------: | :----: | :---------: | :------: | :------------: | :------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [PAConv (SSG)](./paconv_ssg_8xb8-cosine-150e_s3dis-seg.py) | Area_5 | cosine 150e | 5.8 | | 66.65 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class_20210729_200615-2147b2d1.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class_20210729_200615.log.json) |
| [PAConv\* (SSG)](./paconv_ssg-cuda_8xb8-cosine-200e_s3dis-seg.py) | Area_5 | cosine 200e | 3.8 | | 65.33 | [model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class_20210802_171802-e5ea9bb9.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/paconv/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class_20210802_171802.log.json) |
**Notes:**
......
configs/paconv/metafile.yml
View file @ f885d28a
......@@ -15,9 +15,9 @@ Collections:
Version: v0.16.0
Models:
- Name: paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class.py
- Name: paconv_ssg_8xb8-cosine-150e_s3dis-seg.py
In Collection: PAConv
Config: configs/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class.py
Config: configs/paconv/paconv_ssg_8xb8-cosine-150e_s3dis-seg.py
Metadata:
Training Data: S3DIS
Training Memory (GB): 5.8
......
configs/paconv/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class.py → configs/paconv/paconv_ssg-cuda_8xb8-cosine-200e_s3dis-seg.py
View file @ f885d28a
_base_ = [
'../_base_/datasets/s3dis_seg-3d-13class.py',
'../_base_/models/paconv_cuda_ssg.py',
'../_base_/schedules/seg_cosine_150e.py', '../_base_/default_runtime.py'
'../_base_/datasets/s3dis-seg.py', '../_base_/models/paconv_ssg-cuda.py',
'../_base_/schedules/seg-cosine-150e.py', '../_base_/default_runtime.py'
]
# model settings
......
configs/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class.py → configs/paconv/paconv_ssg_8xb8-cosine-150e_s3dis-seg.py
View file @ f885d28a
_base_ = [
'../_base_/datasets/s3dis_seg-3d-13class.py',
'../_base_/models/paconv_ssg.py', '../_base_/schedules/seg_cosine_150e.py',
'../_base_/default_runtime.py'
'../_base_/datasets/s3dis-seg.py', '../_base_/models/paconv_ssg.py',
'../_base_/schedules/seg-cosine-150e.py', '../_base_/default_runtime.py'
]
# model settings
......
configs/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py → configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py
View file @ f885d28a
_base_ = [
'../_base_/schedules/cyclic_40e.py', '../_base_/default_runtime.py',
'../_base_/schedules/cyclic-40e.py', '../_base_/default_runtime.py',
'../_base_/models/parta2.py'
]
......
configs/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py → configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-car.py
View file @ f885d28a
_base_ = './hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py'
_base_ = './PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py'
point_cloud_range = [0, -40, -3, 70.4, 40, 1] # velodyne coordinates, x, y, z
......
configs/parta2/README.md
View file @ f885d28a
......@@ -20,10 +20,10 @@ We implement Part-A^2 and provide its results and checkpoints on KITTI dataset.
### KITTI
| Backbone | Class | Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
| :------------------------------------------------------------: | :-----: | :--------: | :------: | :------------: | :---: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py) | 3 Class | cyclic 80e | 4.1 | | 68.33 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class_20210831_022017-454a5344.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class_20210831_022017.log.json) |
| [SECFPN](./hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py) | Car | cyclic 80e | 4.0 | | 79.08 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car_20210831_022017-cb7ff621.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car_20210831_022017.log.json) |
| Backbone | Class | Lr schd | Mem (GB) | Inf time (fps) | mAP | Download |
| :-------------------------------------------------------------: | :-----: | :--------: | :------: | :------------: | :---: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [SECFPN](./PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py) | 3 Class | cyclic 80e | 4.1 | | 68.33 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class_20210831_022017-454a5344.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class_20210831_022017.log.json) |
| [SECFPN](./PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-car.py) | Car | cyclic 80e | 4.0 | | 79.08 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car_20210831_022017-cb7ff621.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car_20210831_022017.log.json) |
## Citation
......
configs/parta2/metafile.yml
View file @ f885d28a
......@@ -18,7 +18,7 @@ Collections:
Models:
- Name: hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class
In Collection: Part-A^2
Config: configs/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py
Config: configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py
Metadata:
Training Memory (GB): 4.1
Results:
......@@ -30,7 +30,7 @@ Models:
- Name: hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car
In Collection: Part-A^2
Config: configs/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-car.py
Config: configs/parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-car.py
Metadata:
Training Memory (GB): 4.0
Results:
......
configs/pgd/README.md
View file @ f885d28a
......@@ -26,9 +26,9 @@ A more extensive study based on FCOS3D and PGD is on-going. Please stay tuned.
### KITTI
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP_11 / mAP_40 | Download |
| :--------------------------------------------------------------: | :-----: | :------: | :------------: | :-------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [ResNet101](./pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d.py) | 4x | 9.07 | | 18.33 / 13.23 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d_20211022_102608-8a97533b.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d_20211022_102608.log.json) |
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP_11 / mAP_40 | Download |
| :---------------------------------------------------------------: | :-----: | :------: | :------------: | :-------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [ResNet101](./pgd_r101-caffe_fpn_head-gn_4xb3-4x_kitti-mono3d.py) | 4x | 9.07 | | 18.33 / 13.23 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d_20211022_102608-8a97533b.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d_20211022_102608.log.json) |
Detailed performance on KITTI 3D detection (3D/BEV) is as follows, evaluated by AP11 and AP40 metric:
......@@ -41,14 +41,14 @@ Note: mAP represents Car moderate 3D strict AP11 / AP40 results. Because of the
### NuScenes
| Backbone | Lr schd | Mem (GB) | mAP | NDS | Download |
| :------------------------------------------------------------------------------: | :-----: | :------: | :--: | :--: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [ResNet101 w/ DCN](./pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d.py) | 1x | 9.20 | 31.7 | 39.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_20211116_195350-f4b5eec2.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_20211116_195350.log.json) |
| [above w/ finetune](./pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune.py) | 1x | 9.20 | 34.6 | 41.1 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune_20211118_093245-fd419681.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune_20211118_093245.log.json) |
| above w/ tta | 1x | 9.20 | 35.5 | 41.8 | |
| [ResNet101 w/ DCN](./pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d.py) | 2x | 9.20 | 33.6 | 40.9 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_20211112_125314-cb677266.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_20211112_125314.log.json) |
| [above w/ finetune](./pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune.py) | 2x | 9.20 | 35.8 | 42.5 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune_20211114_162135-5ec7c1cd.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune_20211114_162135.log.json) |
| above w/ tta | 2x | 9.20 | 36.8 | 43.1 | |
| Backbone | Lr schd | Mem (GB) | mAP | NDS | Download |
| :-------------------------------------------------------------------------------: | :-----: | :------: | :--: | :--: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [ResNet101 w/ DCN](./pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d.py) | 1x | 9.20 | 31.7 | 39.3 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_20211116_195350-f4b5eec2.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_20211116_195350.log.json) |
| [above w/ finetune](./pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d_finetune.py) | 1x | 9.20 | 34.6 | 41.1 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune_20211118_093245-fd419681.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune_20211118_093245.log.json) |
| above w/ tta | 1x | 9.20 | 35.5 | 41.8 | |
| [ResNet101 w/ DCN](./pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d.py) | 2x | 9.20 | 33.6 | 40.9 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_20211112_125314-cb677266.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_20211112_125314.log.json) |
| [above w/ finetune](./pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d_finetune.py) | 2x | 9.20 | 35.8 | 42.5 | [model](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune_20211114_162135-5ec7c1cd.pth) \| [log](https://download.openmmlab.com/mmdetection3d/v1.0.0_models/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune_20211114_162135.log.json) |
| above w/ tta | 2x | 9.20 | 36.8 | 43.1 | |
## Citation
......
configs/pgd/metafile.yml
View file @ f885d28a
......@@ -18,7 +18,7 @@ Collections:
Models:
- Name: pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d
In Collection: PGD
Config: configs/pgd/pgd_r101_caffe_fpn_gn-head_3x4_4x_kitti-mono3d.py
Config: configs/pgd/pgd_r101-caffe_fpn_head-gn_4xb3-4x_kitti-mono3d.py
Metadata:
Training Memory (GB): 9.1
Results:
......@@ -30,7 +30,7 @@ Models:
- Name: pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d
In Collection: PGD
Config: configs/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d.py
Config: configs/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d.py
Metadata:
Training Memory (GB): 9.2
Results:
......@@ -43,7 +43,7 @@ Models:
- Name: pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune
In Collection: PGD
Config: configs/pgd/pgd_r101_caffe_fpn_gn-head_2x16_1x_nus-mono3d_finetune.py
Config: configs/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-1x_nus-mono3d_finetune.py
Metadata:
Training Memory (GB): 9.2
Results:
......@@ -56,7 +56,7 @@ Models:
- Name: pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d
In Collection: PGD
Config: configs/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d.py
Config: configs/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d.py
Metadata:
Training Memory (GB): 9.2
Results:
......@@ -69,7 +69,7 @@ Models:
- Name: pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune
In Collection: PGD
Config: configs/pgd/pgd_r101_caffe_fpn_gn-head_2x16_2x_nus-mono3d_finetune.py
Config: configs/pgd/pgd_r101-caffe_fpn_head-gn_16xb2-2x_nus-mono3d_finetune.py
Metadata:
Training Memory (GB): 9.2
Results:
......
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