use custom dataset, new issue about efficientteacher HOT 3 CLOSED

@Jinping-Z 您好，看来是读训练数据的时候跑飞了，能检查一下您的train.txt里面的内容吗

from efficientteacher.

谢谢您，根据您的建议我检查了训练集的内容，是转换过程中归一化出现了问题，.txt文件不符合要求没有归一化。

from efficientteacher.

@Jinping-Z

were you able to replicate the results on custom data set.
I am truly confused for steps to follow for Custom Data set which is mentioned.
It am not clear which Pretrained weights of YoloL to be used, trained on partial custom data set whose unlabelled images to be labelled or Pretrained on Coco dataset that we should take
1)
--what kind of supervised training is below step referring to ?
Supervised Training(Optional)
modify the train: data/custom_train.txt in yolov5l_custom.yaml, and then enter the following script.
export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m torch.distributed.launch --nproc_per_node 8 --master_addr 127.0.0.2 --master_port 29502 train.py --cfg configs/sup/custom/yolov5l_custom.yaml

--What are the weights to be given as pretrained weights in this step ?
SSOD Training
export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m torch.distributed.launch --nproc_per_node 8 --master_addr 127.0.0.2 --master_port 29502 train.py --cfg configs/sup/custom/yolov5l_custom.yaml

Also What do they mean by direct start of SSOD training
"Start SSOD Training derectly"

How do we check if our unlabelled data is labelled properly or not ,using which weights ?

from efficientteacher.