Hi,
Is there a way to export a model that uses tf.nn.conv2d_transpose in a fully convolutional network (the input size can change depending on the input image using the network resizing tool)?
Unfortunately, tf.nn.conv2d_transpose requires feeding the output tensor shape as an argument and the way how it's done in tensorflow is to use tf.shape to infer the output shape. However, tf.shape is not supported in SNPE...
Thank you very much in advance,
Kind regards
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.
