Comments (6)
tyjiang1997
commented on August 12, 2024
when i use the config 'da-waymo-kitti_models/secondiou/secondiou_old_anchor_sn', I got the result as :
[2021-07-30 11:03:22,788 eval_utils.py 109 INFO] recall_roi_0.3: 0.977338
[2021-07-30 11:03:22,789 eval_utils.py 110 INFO] recall_rcnn_0.3: 0.977338
[2021-07-30 11:03:22,789 eval_utils.py 109 INFO] recall_roi_0.5: 0.949600
[2021-07-30 11:03:22,789 eval_utils.py 110 INFO] recall_rcnn_0.5: 0.949600
[2021-07-30 11:03:22,789 eval_utils.py 109 INFO] recall_roi_0.7: 0.746611
[2021-07-30 11:03:22,789 eval_utils.py 110 INFO] recall_rcnn_0.7: 0.746611
[2021-07-30 11:03:22,793 eval_utils.py 118 INFO] Average predicted number of objects(3769 samples): 9.362
[2021-07-30 11:03:43,656 eval_utils.py 129 INFO] Car [email protected], 0.70, 0.70:
bbox AP:81.0327, 77.9448, 79.4064
bev AP:77.7435, 71.9792, 70.3093
3d AP:70.1846, 61.3860, 59.4520
aos AP:80.87, 77.45, 78.74
Car [email protected], 0.70, 0.70:
bbox AP:84.6954, 78.0836, 79.7570
bev AP:79.4047, 72.5905, 72.6319
3d AP:70.1550, 61.2689, 60.8881
aos AP:84.50, 77.56, 79.06
Car [email protected], 0.50, 0.50:
bbox AP:81.0327, 77.9448, 79.4064
bev AP:86.2862, 79.7260, 80.9945
3d AP:82.0367, 79.1649, 80.4611
aos AP:80.87, 77.45, 78.74
Car [email protected], 0.50, 0.50:
bbox AP:84.6954, 78.0836, 79.7570
bev AP:87.2480, 82.6880, 84.4618
3d AP:85.8646, 80.6758, 82.2929
aos AP:84.50, 77.56, 79.06
from st3d.
jihanyang
commented on August 12, 2024
May I know which model you are used to eval?
from st3d.
tyjiang1997
commented on August 12, 2024
May I know which model you are used to eval?
I use the pretrained SECOND-IoU model provided by you
from st3d.
jihanyang
commented on August 12, 2024
I will come back to test it 2-3 days later due to some urgent works. However, since other researchers have already try to reproduce the result or verify the pretrained model (you can refer to issues), I guess this might be caused by the environment or data preparation.
from st3d.
tyjiang1997
commented on August 12, 2024
I will come back to test it 2-3 days later due to some urgent works. However, since other researchers have already try to reproduce the result or verify the pretrained model (you can refer to issues), I guess this might be caused by the environment or data preparation.
thank you for your reply,
from st3d.
jihanyang
commented on August 12, 2024
I haven't found any problem with my provided model. Have you used openpcdet before? If so, you need to re-install it in our repo since the version of spconv and pcdet might not well matched.
[2021-08-02 17:37:01,102 eval_utils.py 52 INFO] *************** EPOCH 7362 EVALUATION *****************
eval: 100%|██████████| 236/236 [01:04<00:00, 3.68it/s, recall_0.3=(3452, 3452) / 3532]
[2021-08-02 17:38:06,358 eval_utils.py 91 INFO] *************** Performance of EPOCH 7362 *****************
[2021-08-02 17:38:06,378 eval_utils.py 93 INFO] Generate label finished(sec_per_example: 0.0171 second).
[2021-08-02 17:38:06,378 eval_utils.py 109 INFO] recall_roi_0.3: 0.977344
[2021-08-02 17:38:06,378 eval_utils.py 110 INFO] recall_rcnn_0.3: 0.977344
[2021-08-02 17:38:06,378 eval_utils.py 109 INFO] recall_roi_0.5: 0.949614
[2021-08-02 17:38:06,378 eval_utils.py 110 INFO] recall_rcnn_0.5: 0.949614
[2021-08-02 17:38:06,378 eval_utils.py 109 INFO] recall_roi_0.7: 0.746612
[2021-08-02 17:38:06,378 eval_utils.py 110 INFO] recall_rcnn_0.7: 0.746612
[2021-08-02 17:38:06,380 eval_utils.py 118 INFO] Average predicted number of objects(3769 samples): 9.534
/mnt/lustre/yangjihan/.local/lib/python3.7/site-packages/numba/core/typed_passes.py:314: NumbaPerformanceWarning:
The keyword argument 'parallel=True' was specified but no transformation for parallel execution was possible.
To find out why, try turning on parallel diagnostics, see http://numba.pydata.org/numba-doc/latest/user/parallel.html#diagnostics for help.
File "../pcdet/datasets/kitti/kitti_object_eval_python/eval.py", line 121:
@numba.jit(nopython=True, parallel=True)
def d3_box_overlap_kernel(boxes, qboxes, rinc, criterion=-1):
^
state.func_ir.loc))
/mnt/lustre/yangjihan/.local/lib/python3.7/site-packages/numba/core/typed_passes.py:314: NumbaPerformanceWarning:
The keyword argument 'parallel=True' was specified but no transformation for parallel execution was possible.
To find out why, try turning on parallel diagnostics, see http://numba.pydata.org/numba-doc/latest/user/parallel.html#diagnostics for help.
File "../pcdet/datasets/kitti/kitti_object_eval_python/eval.py", line 121:
@numba.jit(nopython=True, parallel=True)
def d3_box_overlap_kernel(boxes, qboxes, rinc, criterion=-1):
^
state.func_ir.loc))
[2021-08-02 17:39:07,021 eval_utils.py 129 INFO] Car [email protected], 0.70, 0.70:
bbox AP:90.2642, 87.2909, 86.5538
bev AP:89.3554, 83.9180, 82.0950
3d AP:84.1257, 74.0156, 70.7837
aos AP:90.21, 86.98, 86.14
Car [email protected], 0.70, 0.70:
bbox AP:95.2374, 89.2881, 88.5335
bev AP:91.9372, 85.7694, 83.7419
3d AP:85.9557, 74.0871, 71.2213
aos AP:95.17, 88.96, 88.07
Car [email protected], 0.50, 0.50:
bbox AP:90.2642, 87.2909, 86.5538
bev AP:90.4402, 88.3341, 87.7081
3d AP:90.4336, 88.2360, 87.5608
aos AP:90.21, 86.98, 86.14
Car [email protected], 0.50, 0.50:
bbox AP:95.2374, 89.2881, 88.5335
bev AP:95.4826, 92.3827, 91.9459
3d AP:95.4700, 91.9819, 91.5355
aos AP:95.17, 88.96, 88.07
[2021-08-02 17:39:07,026 eval_utils.py 135 INFO] Result is save to /mnt/lustre/yangjihan/ST3D/output/da-waymo-kitti_models/secondiou/secondiou_old_anchor_sn/default/eval/epoch_7362/val/default
[2021-08-02 17:39:07,026 eval_utils.py 136 INFO] ****************Evaluation done.*****************
from st3d.
Related Issues (20)
- Pretrain on waymo data HOT 2
- About pretrained weights for ST3D++ - PVRCNN HOT 1
- Evaluation on Lyft for paper result HOT 2
- Question about pretrained model HOT 1
- Unstable performance HOT 4
- Source Only and SN training HOT 13
- Have you ever tried ST3D on PointPillars? HOT 2
- Can this project be implement in openpdet-v0.6 HOT 10
- AttributeError: 'DataAugmentor' object has no attribute 'random_object_scaling' HOT 9
- AttributeError: 'EasyDict' object has no attribute 'FOV_DEGREE' HOT 4
- The Car [email protected], 0.70, 0.70 IS 0
- The code hangs on during multi GPU training HOT 8
- The cost definition for SASD HOT 1
- Performance of Nuscenes2KITTI HOT 3
- RecursionError: maximum recursion depth exceeded while calling a Python object
- RecursionError: maximum recursion depth exceeded while calling a Python object HOT 2
- what is the purpose of data augmentation in the target domain? HOT 4
- How to set source batch and target batch to fetch data as the data order in ImageSets.
- The config file for multi classes training
- attempt to write config kitti -> nuscenes(mini)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from st3d.