yukitsuji / 3D_CNN_tensorflow

KITTI data processing and 3D CNN for Vehicle Detection

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

What is the difference between the model_01_deconv and model_025_deconv. Is one used for training over the other. The model_01_deconv training does not seem to work

spbayley opened this issue · comments

I tried implementing the training function of the model_01_deconv.py function but I get errors starting with the first being the following:
File "model_01_deconv.py", line 382, in lidar_generator
yield np.array(batch_voxel, dtype=np.float32)[:, :, :, :, np.newaxis], np.array(batch_g_map, dtype=np.float32), np.array(batch_g_cord, dtype=np.float32)
IndexError: too many indices for array

Hi @spbayley
I think generator give error when there is no Car in scene. you may reffer to this issue for solutionhttps://github.com/yukitsuji/3D_CNN_tensorflow/issues/4 I hope this will help you

@ansabsheikh9 Hi, i get an error when there is no car in scene, and the link you provided doesnt is blank. any help? thank you

@spbayley did you figure out how to fix the error when there is no car in scene?

@OneManArmy93 One easiest solution would be to filterout all the files (pointcloud) which do not contain any vehicle in them by using information from ground truth.

@ansabsheikh9 thank you for your reply. But can you explain how to do that? and how can i get the information from the ground truth? Thank you.