SoftTeacher
SoftTeacher copied to clipboard
Semi-Supervised Learning, Object Detection, ICCV2021
如果我想把预测网络换成单阶段网络,如yolo系列,在box jittering部分如何做的呢?请问有什么思路吗
dict(type="PseudoSamples", with_bbox=True) 请问这里为什么要使用PseudoSamples?如果不用伪标签替换原始数据中的gt标签,看起来后续也不会用到unsup支路的gt导致引入监督信息,这里是不是多此一举了
Hi, I want to apply yolo detector. I used single stage functions in softTeacher. I did modifications for sible stage detector in softTeacher file. After modication do i need to...
Hi. Is it possible to share the config files used for evaluating the weights available in through the Google Drive links? I was trying to reproduce the `44.05%` mAP of...
There are important files that Microsoft projects should all have that are not present in this repository. A pull request has been opened to add the missing file(s). When the...
Thank you very much for the amazing repository. I have 2 Questions. 1. Can you please tell me in the function https://github.com/microsoft/SoftTeacher/blob/bef9a256e5c920723280146fc66b82629b3ee9d4/ssod/models/soft_teacher.py#L182 where can I find the student generated foreground...
i got an error : assert len(indices) == len(self) AssertionError   i dont know what happened
How should I set lr_config parameters according to max_iter? Now I want to perform only 20k steps as max iteration what should lr_config will be? ` lr_config = dict(step=[120000 *...
hello , I try to train faster-RCNN model on my dataset using the following script (which is the same on your repository): ``` for FOLD in 1 2 3 4...
2022-07-07 14:05:26,893 - mmdet.ssod - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.135 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000...