Closed NaveenAri closed 7 years ago
yes, thank you NaveenAri. I've asked about this on tensorflow's github but I didn't received the answer yet. For the moment, I don't use top_k max pooling but a normal max pooling instead. It's hard to know if this operation can give better result or not (or redesigning the architecture will give higher effect). Anyway, thanks for the clarification !
The VDCNN paper's k-max pooling finds the top k values while preserving the order in which they appear in the original sequence. I don't think tensorflow's tf.nn.top_k does that.
This is what I get when I use tf.nn.top_k on a simple example: