zeal-up

I notice that you make a real-world demo that demonstrates estimating the pose of real ycb-v objects. I cannot find where to buy these this object. Can you give some...

Can you post some accuracy results of the pretrained models?

1

Thanks for your jobs! It's nice to release the pretrained models. I think it will be useful if you release some performances of the released models.

Resume cctexture download

1

Since when download cctexture always abort sometimes with internet issue， sometimes the request target is not a zip file and the script raises an exception. I add two features: 1....

why the Chebyshev polynomials is needed?

16

When approximate the initial filters kernel gθ(Λ) = diag(θ) with a polynomial  why we can‘t simply combine the eigenvector and eigenvalue matrix together like  because  * The...

Thanks for your jobs! This repo is well organized and help me a lot. I want to know how many GPUs did you use when training a Resnet101 on UCF101...

Thanks for sharing your work. I am interesting in whether can this pointsift module used in a classification task? Have you done some experiment about classification?

Question about SVM training.

4

Hi, thanks for your job. I have some question about the svm training and testing precedure. According to your paper, you randomly rotate the pointcloud and extract the features. Dose...

Cannot import index_max module

2

My environment: cuda10.0 pytroch1.2/1.4 python3.6 I have successfully compiled index_max and the module is installed in 'xx/xx/python3.6/site-packages/index_max-0.0.0-py3.6-linux-x86_64.egg/index_max.cpython-36m-x86_64-linux-gnu.so'. However, when I try to import index_max, it raised up an error: ```...

can't achieve the reported accuracy on VGG19

10

Have anyone train a VGG19 network used this code? I used the total exactly the same code in the repository except using a lr_schuduler to change the learning rate automatically....

#406 根据身高重建队列的另一种类似解法（也是贪心解法）

1

1. 按照身高从低到高排序，身高相同，k大的排在前面 2. 从后往前搜索，将每一个people往后移动k次 这样做能达到目的的原因是：当我们先将身高从低到高排序，任意元素往后移动，并不会影响后面元素的合理性。 并且，不需要额外空间存储，也就不需要是用链表。空间复杂度是O（1） ``` class Solution { static bool peopleCompare(vector& pre, vector& next) { if (pre[0] != next[0]) return pre[0] < next[0]; else { return pre[1] >...