ConsistentTeacher
ConsistentTeacher copied to clipboard
Adamdad
[CVPR2023 Highlight] Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
Is this issue because the CUDA version is incorrect? If so, what should be the correct CUDA version？ I am using cuda11.1+torch 1.9.0.
For the configuration file, I only changed the data path and the number of categories.Run the following code: python tools/train.py configs/consistent-teacher/consistent_teacher_r50_fpn_coco_180k_10p.py --work-dir ./work-dir --gpus 1 Then, /root/anaconda3/envs/cont2/lib/python3.6/site-packages/mmdet/models/builder.py:53: UserWarning: train_cfg and...
I have 1 GPU,and i run the code for 4000iters. Before testing, I copyed DynamicSoftLabelAssigner to ConsistentTeacher-main\thirdparty\mmdetection\mmdet\core\bbox\assigners and change __init__.py ``` from .dynamic_assigner import DynamicSoftLabelAssigner __all__ = [ 'BaseAssigner', 'MaxIoUAssigner',...
hi, I have met the problem when I want to run "bash dist_test.sh". This issue does not appear to be related to the config file. Could you tell me how...
I can train normally on 2*v100, but the following error occurred on 8*v100. Have you encountered it? Thanks! 
Hello, the result of running the code directly differs significantly from the result displayed in your paper. I guess it's due to a problem with the training method, so I...
Thank you for your contribution. I have successfully installed and run the RetinaNet version. It's truly excellent. So I would now like to utilize your session with FCOS for my...
您好，类似于问题26，我有相似的疑问。我阅读了代码，不知道我的理解是否准确。 在每轮训练中有两次过滤，第一次使用每个类的阈值筛选边界框（未使用GMM，是一个粗略的检测框过滤），第二次使用GMM计算全类别的平均gmm_thr，再次过滤。  
As show in readme file. I use mmcv == 1.7.2， however， when I use mmdet>2.25.3, it will give me: ```powershell ModuleNotFoundError: No module named 'mmcv._ext' ext_module = ext_loader.load_ext( File "/opt/conda/lib/python3.10/site-packages/mmcv/utils/ext_loader.py",...
