-
Notifications
You must be signed in to change notification settings - Fork 3.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[RELAY]Vision ops for yolo #1941
Conversation
89d965d
to
63fa16a
Compare
python/tvm/relay/op/vision/yolo.py
Outdated
return _make.yolo_region(data) | ||
|
||
|
||
def yolov3_yolo(data): |
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.
This is quite confusing as it is unclear what specifically the operation this, please write out more details about what is the operation about
python/tvm/relay/op/vision/yolo.py
Outdated
|
||
def yolo_region(data): | ||
"""Yolo region operation used for detection. | ||
|
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.
document the behavior of the operation as it is non-conventional
python/tvm/relay/op/vision/yolo.py
Outdated
|
||
def yolo_reorg(data, stride=1): | ||
"""Yolo reorg operation. This layer reorganize the output based on the stride value. | ||
Its function is mostly shape transform. |
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.
document the behavior of the operation
given #1974 maybe we want to consider close this pr |
region and yolo op can be defenitely removed. But we may need to keep yolo_reorg as realizing this from frontend is difficult. |
68d3e10
to
ee7803e
Compare
68a637f
to
4ed21d3
Compare
What is the status of this PR? |
4ed21d3
to
f82dea1
Compare
f82dea1
to
8a20a5f
Compare
#1799
The following yolo ops are added in relay
Thanks for contributing to TVM! Please refer to guideline https://docs.tvm.ai/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from others in the community.