Closed zkluo closed 3 years ago
Hi, have you solved this problem? According to the author's script training on other data sets, I have modified the learning rate and epoch many times, but the accuracy cannot exceed the effect of the first stage.
@bobp26 @zkluo Hi, It is a little strange. I did not maintain this codebase anymore. However, recently, I found that do not using boundary relaxtion loss leads to better performance. Using mmseg(https://github.com/open-mmlab/mmsegmentation), the performance is better performance than the paper. I will make a pull request on mmseg.
refer to this issue. https://github.com/lxtGH/DecoupleSegNets/issues/22
@bobp26 @zkluo Hi, It is a little strange. I did not maintain this codebase anymore. However, recently, I found that do not using boundary relaxtion loss leads to better performance. Using mmseg(https://github.com/open-mmlab/mmsegmentation), the performance is better performance than the paper. I will make a pull request on mmseg.
so, what kind of loss function leads to better performance than boundary relaxtion loss? Or you mean network do not need body part loss to participate in training
Hi, I follow the two stage training instruction to reproduce the model, but I find the best miou (0.783) of the model in the second stage (deeplabv3-decouple) is lower than that (0.786) in the first stage (deeplabv3). I don't know why. Following is my logs:
First I run
sh ./scripts/train/train_cityscapes_ResNet50_deeplab.sh
to train the base model:Then I get a deeplabv3 model with reasonable performance (miou 0.786), log detail: log_2020_11_21_02_07_50_rank_0.log
Next, I run
sh ./scripts/train/train_ciytscapes_ResNet50_deeplab_decouple.sh
for the second stage training:The difference with your setting lies in:
However, I get a bad result (miou 0.783 < 0.786) despite the reduced lr and epoch num, log details: log_20201205_095232.txt
I feel confused. Could you help me?