structure_knowledge_distillation

structure_knowledge_distillation copied to clipboard

Training from scratch reached the performance similar with that when initializing from ImageNet

1

Hi there, I was trying to reproduce the results reported here on PSPNet-Resnet18. I actually trained it from stratch( --is_student_load_imgnet = False, and empty in ./ckpt/save_path/Student), so student is not...

Shawn207

R.I.P.

8

感谢您在蒸馏领域做出的贡献，您这项工作给了我很大的启发。并且感谢您在百忙之中回复我咨询问题的邮件，您是那样的和蔼，有耐心。R.I.P.

yajieC

training log

1

can you sent your training log to me? I also got worse result

songyang86

How to run on my own dataset?

4

thanks for your great work. could i ask that what i should do to test this model on my own dataset?

eskeron-yxgg

Thank you for excellent work! I would like to apply two inputs (same scene but different sensors , low and high quality images) I pass high quality image to Teacher...

Tejuwi

__ext.so error: undefined symbol: __cudaRegisterFatBinaryEnd

1

Hi, I have encountered the same problems mentioned in [this issue](https://github.com/irfanICMLL/structure_knowledge_distillation/issues/36). Can you give me some detail on how to solve this? I have tried to create a new conda...

RonDen

training fails with "RuntimeError: cuda runtime error (11) : invalid argument at THCGeneral.cpp:405"

2

``` RTX 2080 Ti python 3.7.7 hcff3b4d_5 cuda100 1.0 0 pytorch pytorch 0.4.1 py37_py36_py35_py27__9.0.176_7.1.2_2 pytorch torchvision 0.2.1 py_2 pytorch CUDA Version 10.2.89 cudnn 7.6.4 ``` I have succesfully run :...

betogulliver

How are you? Thank you for your contribution to this project. When I run this code, I encounter some unsolvable problems. I want to ask you. If someone can know...

asiguan

Hi yifan, I am interest in your work. When I run your code , there are some questions about the error. could your please tell me how to deal with...

Liuhao-128

in paper,you concat images and segmentaion maps as input pf discriminstor, but in your codes ,i found not the images concat with seg maps. Where can i found it ?...

Lyan-ing