InvalidArgumentError (see above for traceback): Default AvgPoolingOp only supports NHWC.

[miaozhang0525]

I followed your Requirment and Dependency Tensorflow == 1.4.0, Pytorch == 0.3.1, But I got follow error:

InvalidArgumentError (see above for traceback): Default AvgPoolingOp only supports NHWC.
[[Node: child_1/layer_0/cell_4/x_conv/average_pooling2d/AvgPool = AvgPoolT=DT_FLOAT, data_format="NCHW", ksize=[1, 1, 3, 3], padding="SAME", strides=[1, 1, 1, 1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Am I wrong for the configuration?

I also tried on tensorflow-gpu, it either does not work.

[miaozhang0525]

Sometimes is IMaxPoolingOp only supports NHWC.

[mcbearone]

I followed your Requirment and Dependency Tensorflow == 1.4.0, Pytorch == 0.3.1, But I got follow error:

InvalidArgumentError (see above for traceback): Default AvgPoolingOp only supports NHWC. [[Node: child_1/layer_0/cell_4/x_conv/average_pooling2d/AvgPool = AvgPoolT=DT_FLOAT, data_format="NCHW", ksize=[1, 1, 3, 3], padding="SAME", strides=[1, 1, 1, 1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Am I wrong for the configuration?

I also tried on tensorflow-gpu, it either does not work.

Hello! Have you solved this problem? I meet the same problem when i run "bash train_search.sh"