PraNet

PraNet copied to clipboard

Res2Net weights

1

Hello Thanks for the great project Where should Res2Net weights be placed after downloading?

mahdiyehbakhshi822

Hello， Thanks for your great work! I noticed in the paper that PraNet's results are much better than UNet's. Therefore, I would like to know whether pre-training weights were used...

slll12

Hello! Author, I am very sorry for taking up your precious time. Recently, I am studying one of your papers-PraNet: Parallel Reverse Attention Network for Polyp Segmentation. In the process of learning PraNet network, there is a question that has puzzled me. The problem is as follows: In the Loss Function section of Section 2.3, ' the weighted IoU loss and binary cross entropy (BCE) loss for the global restriction and local (pixel-level) restriction.' What do "global restriction and local restriction" mean exactly? Thank you!

1

Progressiveyouth

image, gt, name = test_loader.load_data() gt = np.asarray(gt, np.float32) gt /= (gt.max() + 1e-8) image = image.cuda() res5, res4, res3, res2 = model(image) res = res2 res = F.upsample(res, size=gt.shape,...

xubigboy

前辈！您好！ 我想请问一下，您这里对图像进行数据增强所使用的均值和标准差是如何计算得到的？  我想了一下，您可能是对训练集的所有图像逐个进行了均值和标准差的计算然后累加这两个值，最后把两个累加和都除以1450，即图像数量，但是因为后续还需要对图像进行调整尺寸，即统一调整为352，所以计算的时候也把这个考虑进去了？ 不知道我想的对不对，期待您的回复

Alex-a233

data set

1

Hello, can you provide a link to the data set you use?

ss0219

Hi PraNet Team, do you use augmentations for your training? If I see it correctly in the dataloader I think there are no augmentations. My questions are: - Did you...

Testbild

Dear PraNet Team, I use your network to make segmentations on my images. Some images contain a ground truth, that can be segmented, some images are true negatives and the...

Testbild

The image and mask filenames in your test dataset don’t correspond to each other and are inconsistent with the original dataset.

dashen2004