Closed Observerspy closed 6 years ago
I checked the API doc of Tensorflow 1.8 and it seems that the 'channels_first' data_format is still supported.
I just update my tf to 1.8.0 and data_format="channels_first" still got Error "UnimplementedError (see above for traceback): Generic conv implementation only supports NHWC tensor format for now."
Hi @dshnightmare,what is the version of TF you are using?Have you ever met the Error?This pull request is somehow reverting the last one #29
I just tried for some versions of tensorflow and got the same Error as you. Thank you for the pull request. I will merge it now.
@Observerspy @junxiaosong I'm using tensorflow 1.8 and unimplementedError is encountered when use cpu version of tensorflow, and I think a transpose operation is a better general approach for both of cpu and gpu version. It is my fault not making it clear.
conv2d in Tensorflow now only support data_format='channels_last', so just change "channels_first" to "channels_last" and add tf.transpose(self.input_states, [0, 2, 3, 1]) for input placeholder.