HRNet
performance gap with pytorch 0.4.1: mIoU 79.99
Sorry to bother you! I tried to implement the training process using the seg_hrnet_w48_train_512x1024_sgd_lr1e-2_wd5e-4_bs_12_epoch484.yaml. But it came out that the validation mIoU for single-scale and no-flip is 79.99, almost 1% lower than your result shown(80.9). I wonder if this is normal variation or I did something wrong ? Here is the training log: https://pan.baidu.com/s/1utKUVuBEjDBtfgOk7A-5sQ 【passward: jckv】 Thank you!
Hi, @Wangzhuoying0716 would you mind sharing your training settings,
I have been trying to train it, but it always gets stuck at this point
I don't know where I'm doing something wrong.
my training settings: Pytorch 0.4.1 python 3.7 OpenCV 3.4.2.17 rest is according to requirements.txt
@Hussainflr If there is no error message but just gets stuck, I guess it's because the memory is too full to keep on? You can check the memory usage when it is stuck to see whether it's almost full. As for me, I just used 4xTitan Xp GPU cards and the setting in seg_hrnet_w48_train_512x1024_sgd_lr1e-2_wd5e-4_bs_12_epoch484.yaml.
@Wangzhuoying0716 Sorry for late reply. I checked your log. When training on cityscapes, we use the "class balance" in the loss function. You can change the config and set the class balance as True.
Hi @sunke123, LOSS.CLASS_BALANCE defined in lib/config/default.py, but is there any place to use it? and i found, the loss: criterion = CrossEntropy(ignore_label=config.TRAIN.IGNORE_LABEL, weight=train_dataset.class_weights), use class weighs, which doesn't matter with CLASS_BALANCE param
@whiteinblue Class weights are used to train the model on Cityscapes. If you don't want to use it, you can change it in the yaml.
@sunke123 thank you for your reply， and i confuse, it's where that the param LOSS.CLASS_BALANCE used ?
Hi, @Wangzhuoying0716 would you mind sharing your training settings, I have been trying to train it, but it always gets stuck at this point
I don't know where I'm doing something wrong.
my training settings: Pytorch 0.4.1 python 3.7 OpenCV 3.4.2.17 rest is according to requirements.txt
Hello, i met same problem, have you solved it?
So where that the param LOSS.CLASS_BALANCE used? I read the code, it seems that no matter what is CLASS_BALANCE param, the balance loss is used in the cityscape dataset.
