why do u use pretrained best network weight to retrain the network?
Closed this issue · 7 comments
As the title mentions, the code (https://github.com/proteus1991/GridDehazeNet/blob/master/train.py#L98) use the best weight (indoor_haze_best_3_6) to retrain the network with indoor training dataset. It seems that it is not reasonable.
Hi, this is just an example to show how to retrain/finetune the GridDehazeNet. You can modify the code accordingly to match your use case.
If I want to reproduce the experiment results, I should comment the line mentioned above, is that right? @proteus1991
After reading your paper, I have some questions.
- Do u just use the ITS dataset to train the network and test on SOTS?
- Do u just use the OTS dataset to train the network and test on SOTS?
- If I use pretrained network (using OTS to train) to finetune on ITS, will I get better test results on SOTS?
If I want to reproduce the experiment results, I should comment the line mentioned above, is that right? @proteus1991
Yes. You should not load my well-trained weights.
After reading your paper, I have some questions.
- Do u just use the ITS dataset to train the network and test on SOTS?
- Do u just use the OTS dataset to train the network and test on SOTS?
- If I use pretrained network (using OTS to train) to finetune on ITS, will I get better test results on SOTS?
For question 1 and 2, yes. I used ITS dataset to train the network and test on SOTS indoor and used OTS dataset for outdoor.
For question 3, I didn't train it in that way. You can read the paper which introduces RESIDE dataset for more details.
After reading your paper, I have some questions.
- Do u just use the ITS dataset to train the network and test on SOTS?
- Do u just use the OTS dataset to train the network and test on SOTS?
- If I use pretrained network (using OTS to train) to finetune on ITS, will I get better test results on SOTS?
For question 1 and 2, yes. I used ITS dataset to train the network and test on SOTS indoor and used OTS dataset for outdoor.
For question 3, I didn't train it in that way. You can read the paper which introduces RESIDE dataset for more details.
Thanks for ur reply!!! Great work!
After reading your paper, I have some questions.
- Do u just use the ITS dataset to train the network and test on SOTS?
- Do u just use the OTS dataset to train the network and test on SOTS?
- If I use pretrained network (using OTS to train) to finetune on ITS, will I get better test results on SOTS?
For question 1 and 2, yes. I used ITS dataset to train the network and test on SOTS indoor and used OTS dataset for outdoor.
For question 3, I didn't train it in that way. You can read the paper which introduces RESIDE dataset for more details.Thanks for ur reply!!! Great work!
Thanks. This issue is closed.