pyni

The strange mirror for the rendered result

1

Hi, i find a strange mirror for the final rendered result: a rendered result is shown like this:  But actually, the mesh is shown as follows...

The algorithm

5

Nice work. I wonder what algorithm do you use. Is there a paper to support your code?

Hi, if i want to compile all the modules with **cpu**,including NMS, ROI_Temporal_Pooing, how can i change the order? Thanks.

YCB_Video_Dataset.reindexed.v2 does not exist.

3

Hi, i have followed all of your steps,but when i run : cd examples/ycb_video/singleview_3d ./download_dataset.py it shows: OSError: /home/yuan/data/ycb_video/YCB_Video_Dataset.reindexed.v2 does not exist. So what is the 'YCB_Video_Dataset.reindexed.v2'? is there anything...

Hi, in the original paper, the parameters for FC-DenseNet56 is about 1.5 M But your code requires about 4000MB gpu to do a forward computation. I wonder why there is...

Hi, i wonder how to set radius value. Since the data is normalized, why the radius is larger than 1 in semantic dataset: "l1_radius": 0.5, "l2_radius": 1.0, "l3_radius": 2.0, "l4_radius":...

您好，请教一下一个问题

8

您好，我想请问下，我看数据集好像不是pascalvoc之类的，能不能给出数据集，尤其是 它的label的定义方式？ 谢谢

hi , i wonder what's the meaning of flip_rot_matrix in your code: pcds = [] pcd = copy.deepcopy(camera_pcd) pcd.transform(flip_rot_matrix) # why flip_rot_matrix is required? pcds.append(pcd)

A good work. But your work need to train the network. I wonder why not directly use CNN to do this work, which means the G(z) is treated as the...

Hi, Thanks for your amazing loss function. After reading your papers, I have the following question:   So how to get this equation? I find it looks like softmax...