DDRNet icon indicating copy to clipboard operation
DDRNet copied to clipboard

The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"

Results 20 DDRNet issues
Sort by recently updated
recently updated
newest added

你好,想问一下为什么输入图片大小为512×512和768×1536时速度基本相当?

Dera Yuanduo Thanks very much for your perfect Network. I have a question about the structure of the DDRNet. In your program code, the layer of the bottleneck block in...

Hello Yuanduo, I think your achievement is really awesome. I am looking into your code and your model to develop more on it. I was wondering whether the "best.pth" model...

Hi, great project. Do you have any plans for adding DDRNet support to mmsegmentation?

This model is extremely fast & accurate. I've tried so many methods to make a model run fast enough with the same accuracy, like lite backbone, shrink the PPM or...

实际应用效果真的不错,又快又好,我们公司线上就用了这个

I am using your model to do segmentation, and its performance is really amazing. However, the inference speed is not ideal. I noticed that you merged conv2d and batchnorm during...

你好,我修改了DDRNet网络,因此想重新使用ImageNet进行预训练,但是怕ImageNet预训练这里出现问题导致模型效果受影响 您能否上传一下DDRNet的在ImageNet的预训练代码呢? 谢谢

Can you publish the visualization code?

Your work is excellent. Could you please publish the visualization code? I would like to see the segmentation results. If my input is 512x512, how should I modify the structure...