Xavier Soria Poma

Hi, could you check now?

Hi, its a great question and the edge thinness depends on different things. For example if you compare Dexined trained in BIPED en evaluated on BSDS; and Dexined trained on...

> Hi, i have problem in training process of Pytorch version. When using hed_loss2/bdcn_loss/bdcn_loss2 in losses，training loss is large and does not converge，model can predict edge map but the result...

> is so thinner than hed. Hi, the 512x512 is the lenna image real size (also CID dataset). In the test stage, we try to test with the real image...

> @xavysp > Hed faster than DexiNed due to the number of parameters? Well, in terms of PC, in the test stage hed is faster > 1、Hed used the vgg...

Hi, maybe you can start training DexiNed with the BIPED settings. I think it will not change much. To see the difference you can get the mean of your dataset...

> Thank you for your reply, Why the parameters "mean_pixel_values" on BIPED i calculate is different from the code. > >  Can I see the results?

Hi, hope you are enjoying your holiday :), well the results of my rgb_mean are from the BIPED image but before post-processing them (white balance, gamma correction,...). In other words,...

Hi @matinmlk . I am afraid I cannot help you at this time sorry. I have not tested on such environment.

Hi sorry for my late response. As you can see in many DL models there is not accuracy in the training stage, it could be great use a metric for...