search

hirotomusiker / CLRerNet

The official implementation of "CLRerNet: Improving Confidence of Lane Detection with LaneIoU"
Apache License 2.0
181 stars 19 forks source link

TypeError: LoadImageFromWebcam: __init__() got an unexpected keyword argument 'pipelines' #33

Closed mihirkalakamb029 closed 4 months ago

mihirkalakamb029 commented 6 months ago

Hello, I'm new to mmdet and I was trying to test the results giving video input, but I encountered a TypeError as mentioned in the title. The command I used is python demo/video_demo.py demo/demo.mp4 configs/clrernet/culane/clrernet_culane_dla34_ema.py clrernet_culane_dla34_ema.pth --out result.mp4. It would be helpful if you could help me to debug this error.

Note: I used the video_demo.py from the official mmdetection repo.

Traceback (most recent call last): File "/home/sandlogic/anaconda3/envs/clrernet/lib/python3.8/site-packages/mmcv/utils/registry.py", line 69, in build_from_cfg return obj_cls(**args) TypeError: init() got an unexpected keyword argument 'pipelines'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "demo/video_demo.py", line 63, in main() File "demo/video_demo.py", line 49, in main result = inference_detector(model, frame) File "/home/sandlogic/anaconda3/envs/clrernet/lib/python3.8/site-packages/mmdet/apis/inference.py", line 127, in inference_detector test_pipeline = Compose(cfg.data.test.pipeline) File "/home/sandlogic/anaconda3/envs/clrernet/lib/python3.8/site-packages/mmdet/datasets/pipelines/compose.py", line 23, in init transform = build_from_cfg(transform, PIPELINES) File "/home/sandlogic/anaconda3/envs/clrernet/lib/python3.8/site-packages/mmcv/utils/registry.py", line 72, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') TypeError: LoadImageFromWebcam: init() got an unexpected keyword argument 'pipelines'

mihirkalakamb029 commented 6 months ago

Link to the video_demo.py: https://github.com/open-mmlab/mmdetection/blob/v2.28.0/demo/video_demo.py

hirotomusiker commented 6 months ago

Thank you.

  1. Add the following lines at the beginning of video_demo.py:

    from libs.api.inference import inference_one_image
from libs.utils.visualizer import visualize_lanes

  2. Change the following lines: https://github.com/open-mmlab/mmdetection/blob/v2.28.0/demo/video_demo.py#L47-L48 to 

    frame, preds = inference_one_image(model, frame)
frame = visualize_lanes(frame, preds)