Hsuan
Hsuan
I have tried to train on different dataset, and the code can work. There are several things you should notice: 1. Update the mean & var first using the flag...
Hey @Danzip, you got that error because I haven't update the code yet. Recently, I am trying to train on another dataset. Please wait my new version codes, I will...
Hey, it will initialize the model at first iteration, so the time you calculated contain the time of initialization. You can try to run more images and calculate like following:...
Hey @Anubhav7 , I will fix this bottleneck tomorrow, just wait for me, thanks.
@Anubhav7, I have change the decode_label function. Can you test on it again?
Hey @StOnEGiggity. My way to calculate inference time is to subtract the time of processing input data, so it contains interp layer. Does this confuse you, or something else? Btw,...
@StOnEGiggity , Ohhh!!!!! I got it, this is my fault. I forgot to calculate this time at `evaluate.py`, now i understand what you mean. Thanks for your reply, I have...
Hey @StOnEGiggity , the new inference time test on GTX 1080ti shown below: Inference time excluding loading data ( Calculated as described in paper ): ~0.03s Inference time including loading...
Het, @wangbofei11 there's three possibility: 1. The half kernel model cannot learn well, so I'm trying to re-produce the training procedure described in original paper. ( That is train with...
Hello @wangbofei11 , I started my training weights from the pre-trained model of cityscapes, and then trained on the ADE20k dataset ( I use 27 classes instead 150 classes ).