InvalidArgumentError (see above for traceback): input must have at least k columns

[DL-ljw]

When I use SAR images, I got the following error. Can you help me to solve it? InvalidArgumentError (see above for traceback): input must have at least k columns [[Node: rpn_losses/TopKV2 = TopKV2[T=DT_FLOAT, sorted=true, _device="/job:localhost/replica:0/task:0/cpu:0"](rpn_losses/strided_slice_2/_4989, rpn_losses/TopKV2/k)]] [[Node: fast_rcnn_predict/fast_rcnn_proposals/cond/Slice/_4787 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_7827_fast_rcnn_predict/fast_rcnn_proposals/cond/Slice", tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/gpu:0"]]

Process finished with exit code 1

[yangxue0827]

Comment the topk's summary related code.

[tsing-cv]

@DL-ljw I encountered the same problem. Have you solved it?

[kealennieh]

The same problem. When I train the network at step 301, the problem occurs.

W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: input must have at least k columns

@DL-ljw @tsing-cv @yangxue0827 have you guys solved this problem? Thanks.

[GuoleiSun]

@DL-ljw @tsing-cv @yangxue0827 have you guys solved this problem? Thanks.