My model is comprised of a few LSTM input layers (taking a 3d array), which is passed to some more Dense layers. For some reason, it keeps giving an error saying Invalid order tensor [0. 0. 0.] Conversion failed: ERROR_TF_PERMUTE_INVALID_ORDER_TENSOR. It works fine with just Dense layers, but adding CuDNNLSTM seems to break it. Anyone have any ideas?
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
