HanChen-HUST

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

4

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)...

I have the similar problem in evaluate.py,the error is：ensorflow.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

4

[[{{node split}} = Split[T=DT_FLOAT, num_split=3, _device="/device:CPU:0"](split/split_dim, ToFloat)]] [[{{node IteratorGetNext}} = IteratorGetNextoutput_shapes=[[?,?,?,3],[?,?,?,1]], output_types=[DT_FLOAT，DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](OneShotIterator)]] Hope to get your answer,that will be great apperciate _Originally posted by @chenhust1995 in https://github.com/rishizek/tensorflow-deeplab-v3-plus/issues/12#issuecomment-448083099_

I created the TFRecord data and then train the model with coco-stuff dataset，then error occured in evaluate.py

1

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],[?,?,?,1]],...