Hi all,
In version 1.29, the resize operator supports nearest neighbor method which is used in MobileNetV1-FPN-SSD
The structure of nearest neighbor implementation is as follow (lib/python/snpe/converters/tensorflow/layers/resize.py:130):
But it seems like it's kind of different from the original implementation in tensorflow (https://github.com/tensorflow/models/blob/a85c40e36fad0ee3754c1046eb8968e50d22bbf8/research/object_detection/utils/ops.py#L936-L974)
Is there anyone know where this implementation come from?
Hi alex_li,
According to SNPE reference guide document, resize operator is from tf.image.resize_nearest_neighbor. You can refer to https://developer.qualcomm.com/docs/snpe/network_layers.html
Thanks,
Jihoonk
Thanks for your reply at first.
But I thought the operator tf.image.resize_nearest_neighbor have already implemented in previous version.
According to the object detection api (or Mobilenet V1 FPN SSD), there are two way to do upsampling. (https://github.com/tensorflow/models/blob/fe748d4a4a1576b57c279014ac0ceb47344399c4/research/object_detection/models/feature_map_generators.py#L569-L580)
So I thought the version 1.29 add another implementation about resize operator?
Thanks,
Alex