InvalidArgumentError: flat indices[117, :] = [2, 7] does not index into param (shape: [7,7,512]).

[happyday521]

When I run "python demo.py --image utils/examples/plane.png" , I meet the problem:

InvalidArgumentError (see above for traceback): flat indices[117, :] = [2, 7] does not index into param (shape: [7,7,512]).
[[Node: graphprojection_1/GatherNd_13 = GatherNd[Tindices=DT_INT32, Tparams=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](gcn/Squeeze_3, graphprojection_1/stack_13)]]

However, I didn't change anything.
My TF is 1.9 and Cuda is 9.0 , I compile my own cd_dist.so. I didn't know what is wrong. Can anyone help me ? Thanks very much!

[jspih]

I also have this issue, but on tensorflow 1.3 and cuda 10.0.

[jspih]

I even installed cuda version 8.0, is there a specific numpy version that was used? Or any other versions?

[jspih]

Fixed it!

From a different issue

I ran into the same error. It looks like changing the following two lines in layers.py:

x2 = tf.ceil(x)

and

y2 = tf.ceil(y)

into

x2 = tf.minimum(tf.ceil(x), tf.cast(tf.shape(img_feat)[0], tf.float32) - 1)

and

y2 = tf.minimum(tf.ceil(y), tf.cast(tf.shape(img_feat)[1], tf.float32) - 1)

will bypass the error. Not sure if this is the correct solution.

Then make sure to run python setup.py install again

[happyday521]

@jspih Thanks very much！ I will try!

[happyday521]

GPU version doesn‘t have any problem. However, CPU should modify x2 and y2.

[zshyang]

Hi,
Do you know how to download the dataset and unzip it from the link below?
https://drive.google.com/open?id=131dH36qXCabym1JjSmEpSQZg4dmZVQid