search

rishizek / tensorflow-deeplab-v3-plus

DeepLabv3+ built in TensorFlow
MIT License
834 stars 307 forks source link

I have similar issue with Python 3.5, Tensorflow 1.12, CUDA 8 #45

Open HanChen-HUST opened 5 years ago

HanChen-HUST commented 5 years ago

I have similar issue with Python 3.5, Tensorflow 1.12, CUDA 8

tensorflow.python.framework.errors_impl.InvalidArgumentError: Number of ways to split should evenly divide the split dimension, but got split_dim 2 (size = 1) and num_split 3 [[{{node split}} = Split[T=DT_FLOAT, num_split=3, _device="/device:CPU:0"](split/split_dim, ToFloat)]] [[{{node IteratorGetNext}} = IteratorGetNextoutput_shapes=[[?,?,?,3]], output_types=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Originally posted by @lthngan in https://github.com/rishizek/tensorflow-deeplab-v3-plus/issues/12#issuecomment-444011415

HanChen-HUST commented 5 years ago

@rishizek

HanChen-HUST commented 5 years ago

@lthngan

HanChen-HUST commented 5 years ago

@lthngan have u solve this problem？hope to get ur answer,thanks

ningxiangyun commented 5 years ago

did u resolved the bug?