xiongzhu666

vkEnumeratePhysicalDevices failed

4

My dear nihui dalao, compile has passed, but I faced the problem as below when I run the realsr-ncnn-vulkan: command : ./realsr-ncnn-vulkan -i ../images/timg.jpg -o output.png -s 4 vkEnumeratePhysicalDevices failed...

关于特征点分散和GMS兼容的问题

1

大神你好，我本来打算将你的算法应用在ORB-SLAM里面，但是ORB-SLAM的特征提取方法基于四叉树做了均匀处理，分散得比较开，这样的话GMS匹配貌似没有优势了。反而用opencv自带的ORB算法，由于opencv的特征点扎堆，GMS更能够筛选出正确的配对。 在SLAM中，我们更希望特征点分散来精准估计位姿，这种期望貌似和GMS的栅格统计原理是不兼容的，请问大神有解决思路吗？？？

person segmentation soft label

1

Hi, Xuebin, I am coming again for the person segmentation, I prepare the training datasets of high-precision soft label. do you have any suggestion about modify the loss function??? because...

mask post-processing

7

Hi Xuebin, I implement a mask post-processing by c++ to retain the segmentation detail, but perhaps it only has good performance on sky-segmentation。thanks for your kind help in my model...

background segmentation

5

Hi~I retrain a sky segmentation based on your project,I have some doubt： 1. my dataset is sky mask，the mask is alpha mask and then I binary the mask(0/255). so that...

doubt about training datasets resize method

3

Hello Mr Xuebin: about the datasets resize method, my training image size is very big（4000*3000）, so I need to resize the image to 320*320 offline. but I compare the results...

about training

1

Hi~Mr Qin，I am coming again.... I retrain u2net on my datasets（9000 pics），the loss value oscillate around 0.2，do you think should I keep training？？（I just train for 1.5 day），I am a...

I am confused that why there is no confidence in network output.....

thanks for your great working, but I can't find the pre traning model....

in boards_from_cornersr.cc if(!params.overlay) { // start from random index std::default_random_engine e; auto time = std::chrono::system_clock::now().time_since_epoch(); e.seed(static_cast(time.count())); if (corners.p.size() == 0) { return; } start = e() % corners.p.size(); } when...