-
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
[Bug] Unable to save prediction results when running test.py #2962
Comments
Running the following command from command line also doesn't give the right answer:
Instead, I get the following error:
|
I am wondering what would happen if you just try without .pkl file with below command, does it saves results in some format? python tools/test.py projects/BEVFusion/configs/bevfusion_lidar-cam_voxel0075_second_secfpn_8xb4-cyclic-20e_nus-3d.py checkpoints/bevfusion_converted.pth --task 'multi-modality_det' |
@VeeranjaneyuluToka Yes, I've tried that, but it does not save individual prediction boxes --- it just creates a .json file with the standard metrics and a data/ folder with visualizations of the bounding boxes. I need the predicted boxes for my analysis. |
I have created my own inference runner based on their demo samples (https://github.com/open-mmlab/mmdetection3d/tree/main/demo), there is a way to visualize and dump the predictions, however i am working on LiDAR based 3D detection only. But it should work even in multi-modality case also i believe, so i would recommend to look into it. |
Hi @VeeranjaneyuluToka: we did the same for just Lidar 3D detector. But based on the demos, doing this for multi-modality did not work. If you look at the multi-modality demo, it requires each point cloud and all associated images for that sample to be in one folder. I'm not sure how to scale this up and run inference for the entire dataset, especially with BEVFusion. |
Prerequisite
Task
I have modified the scripts/configs, or I'm working on my own tasks/models/datasets.
Branch
main branch https://github.com/open-mmlab/mmdetection3d
Environment
sys.platform: linux
Python: 3.8.16 (default, Jan 17 2023, 23:13:24) [GCC 11.2.0]
CUDA available: True
numpy_random_seed: 2147483648
GPU 0,1: NVIDIA RTX A6000
CUDA_HOME: /home/apurvabadithela/miniconda3/envs/detection
NVCC: Cuda compilation tools, release 11.7, V11.7.99
GCC: gcc (Ubuntu 10.5.0-1ubuntu1~22.04) 10.5.0
PyTorch: 1.13.1
PyTorch compiling details: PyTorch built with:
TorchVision: 0.14.1
OpenCV: 4.7.0
MMEngine: 0.9.1
MMDetection: 3.2.0
MMDetection3D: 1.4.0+fe25f7a
spconv2.0: True
Reproduces the problem - code sample
I want to save prediction results from running the project mmdet3d/projects/BEVFusion. The documentation states to add the tag pklfile_prefix to the test_evaluator, which I do in the config file: config_file by adding the following line after:
test_evaluator.update({'pklfile_prefix':'/home/apurvabadithela/nuscenes_dataset/inference_results/bevfusion_model/results.pkl'})
Reproduces the problem - command or script
Then, I run the following from command line:
Reproduces the problem - error message
And I get the following error message.
Additional information
The text was updated successfully, but these errors were encountered: