Qudagang

training problem:IndexError: Cannot choose from an empty sequence

2

when I train using small content dataset, the system puts forward" IndexError: Cannot choose from an empty sequence". Process Process-1: ValueError: number of bits must be greater than zero: IndexError:...

After start: Limit: 3210821632 InUse: 3142544896 MaxInUse: 3166815232 NumAllocs: 1714 MaxAllocSize: 688914432 Then the system show that : Hint: If you want to see a list of allocated tensors when...

Problems about the first step

4

When I do as you shown in the webpage, However, when I run "python generate_dataset.py", the system shows like below: 'binvox' is not recognized as an internal or external command,...

ValueError: Cannot feed value of shape (64L, 256L, 256L, 256L, 1L) for Tensor u'x0:0', which has shape '(64, 32, 32, 32, 1)'

1

ValueError: Cannot feed value of shape (64L, 256L, 256L, 256L, 1L) for Tensor u'x0:0', which has shape '(64, 32, 32, 32, 1)'， When I built python2.7 architecture and run the...

Problems about Dataset making

1

when I write like you shown in the "How to run the code", like below: " import glob import os import subprocess import sys voxsize = 32 paths = glob.glob("C:/Users/20185290/Desktop/New...

ValueError problem

1

When I input the folder which is full of binvox format files as input paths, The when run the code train.py The system show that: ValueError: Tried to convert 'reduction_indices'...