Conversation
cc @PariksheetPinjari909 can you help review this? |
cc @zhreshold |
an example and testcase is needed |
I will review this and get back to you. |
I'll keep working on this PR and pushing new commits. |
@@ -195,6 +195,22 @@ def _upsampling(inputs, attrs): | |||
new_attrs = {'scale':int(scale)} | |||
return _get_nnvm_op('upsampling')(inputs[0], **new_attrs) | |||
|
|||
def _contrib_MultiBoxDetection(inputs, attrs): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
use snake case for method name _contrib_multibox_detection
@@ -0,0 +1,130 @@ | |||
/*! | |||
* Copyright (c) 2017 by Contributors | |||
* \file object_dectection.cc |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can move to src/top/vision folder
@@ -0,0 +1,51 @@ | |||
"""Definition of object detection ops""" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
merge to already existing python/nnvm/top/vision.py
return true; | ||
} | ||
|
||
NNVM_REGISTER_OP(multibox_prior) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Shall we also add MultiBoxTarget op in nnvm even it won't be used in tvm? |
@zxwitsme Since MultiBoxTarget is only useful at training stage, it is recommended to export an inference model, instead of using the same model for model training. It can be a lot faster without MultiBoxTarget at inference stage. |
@liangfu Thanks for the reply. I got the model from here and it includes the MultiBoxTarget op: |
In this script, there are two models, one for training, the other for inference. Use |
@liangfu I will try it. Thanks. |
c.f. #518 we will redirect further changes to tvm repo, please open a new PR there |
Support SSD in NNVM. Add a quick solution so that major part of network can run on various devices and final NMS part will run on CPU.