-
I used my own data set for training. According to the training steps given by the author, I first pre-trained the supernet and parameters, and then obtained the search file to train the teacher ne…
-
Thanks for your code. I have studied your code. The training process contains two stages. Firstly, the teacher and student networks are separately trained based on the same dataset. Then, the distilla…
-
after resolving all problems about training my custom dataset with One teacher when I launch the training, I got this error:
Epoch gpu_mem box obj cls mls semi_obj …
-
### Checklist
- I have searched related issues but cannot get the expected help.
- I have read related documents and don't know what to do.
### Describe the question you meet
In distillation…
-
1. I have two trained models using the mmpretrain: Res2net, ShufflenetV1
2. I employed the model and training weight of Res2net as the teacher and the model of shufflenetv1 as the student model in th…
-
Thanks for your work! I have some questions about model distillation.
"we leverage the same training loop with a few exceptions: we use a larger
model as a frozen teacher, keep a spare EMA of the st…
-
Hello,
I would like to integrate VoCo into my pretraining framework and have a few questions.
Currently the repo seems to diverge from the method described in the paper as it does a teacher-studen…
-
i'm implementing soft-teacher without mmedetection tools and have some questions
i don't clearly understand the structure.
In training teacher model get soft_auged img and student get hard_auged …
-
I have finished training the teachers .
python train_teachers.py --nb_teachers=100 --teacher_id=10 --dataset=mnist
teacher_id values range from 0 to 99.
When I wanted to train the student,it faile…
-
Hi, thank you for your work!
I am attempting to train the BIDNet and would greatly appreciate your assistance with the following questions:
1. The SN6 SAR imagery consists of 4-channel, 32-bit dat…