purse1996

lower result than using default config

1

When I run the code using default config file, the result is 80.99, which is lower than 81.6. Can you offer some suggestions? Seeding with 304 => creating output/cityscapes/seg_hrnet_ocr_w48_train_512x1024_sgd_lr1e-2_wd5e-4_bs_12_epoch484 =>...

代码中问题

1

您好 我们想在您的基础上训练一个分类网络，但细节的地方有两个位置不太理解，能不能麻烦解释一下，万分感谢。 第一个是results为什么后面还要torch.cat一个torch.ones_like results = torch.cat([torch.sigmoid(results), torch.ones_like(results[:, :1]).float().cuda() * 0.5], 1) 第二个是这里为什么要乘以16 out = self.fc(global_feat) * 16

SE Loss

1

论文中提到了SE Loss在解决一些小物体识别的准确性，但论文中没有给出loss的具体形式，也没有ablation study实验结果。想请教一下loss的具体形式

GPU-Util is zero

7

Thank you for your sharing code. I met a problem. When I train the model for my data in GPU,the memory-usage is high but the GPU-util is always zero. So...

moment pooling

1

The mean of moment pooling is whether to calculate the moment of single-channel or the moment of each region by the label mask? Can you offer the code for this...

excellent work

3

I think the idea is very novel and the result is very good. I want to follow your work and use Optimal Transport in another task. But a problem occurs...

rolo使用教程

8

前几天从头配置了一下ROLO 遇到的问题及解决办法 https://blog.csdn.net/dreamguard/article/details/83629579