qiqihaer/votenet-kitti

votenet-kitti's Issues

你好！关于数据预处理部分

感谢你的开源hh
我在看代码的时候，发现在预处理的时候，点云数据只保留了与摄像头视野重叠的部分

 pts_img, pts_rect_depth = calib.rect_to_img(pts_rect)
 pts_valid_flag = self.get_valid_flag(pts_rect, pts_img, pts_rect_depth, img_shape)
 pts_rect = pts_rect[pts_valid_flag][:, 0:3]
 pts_intensity = pts_intensity[pts_valid_flag]

我如果想要使用所有的点云进行训练的话，是不是只需要去掉这几行代码就可以了呢？然后改变保留的点个数？
希望收到你的回复，谢谢!

RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

我在python train.py的时候，发生这个报错

File "train.py", line 375, in
train(start_epoch)
File "train.py", line 352, in train
train_one_epoch()
File "train.py", line 247, in train_one_epoch
loss.backward()
File "/home/hova/anaconda3/lib/python3.7/site-packages/torch/tensor.py", line 166, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/hova/anaconda3/lib/python3.7/site-packages/torch/autograd/init.py", line 99, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

哥哥救我Orz

question about the loss

when training on kitti dataset, two kinds of printed losses akways increased(mean loss and mean box loss), while other types decreased. Have you ever encountered such problem?

Thanks~

about 3 classes detection

Hi! Thank you for your great code.
I have a question of how to learning in 3 classes.
It can only learn about 'Car' class or not. I want to input point cloud data and output which is ['Car', 'Pedestrian', 'Cyclist'].

Ask for the code of visualization

Thanks for you contribution! I am really new to the field and don't have much comprehension of point clouds. I find there are many *.ply and *.obj files in the document data_viz_dump. I wonder how to make the visualization like this project? which software do you use? Thanks again for your very kind reply.

how to make own datasets

你好，基于votenet 的数据集格式，有参考的制作demo吗？这边想训练自己的数据集，但是不知道怎么制作。

Test results?

Thanks for your code! Have you evaluated the test results or evaluation results?