-
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
Add PAD operator to relay tflite frontend #3310
Conversation
python/tvm/relay/frontend/tflite.py
Outdated
in_expr = self.get_expr(input_tensor.tensor_idx) | ||
|
||
# paddings | ||
padlist = self.get_tensor_value(input_tensors[1]) |
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.
pad_list
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.
fixed
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.
lgtm
c4ad7a8
to
573729e
Compare
@apivovarov Can you fix ci failure? |
The test which I added to
Failed test is |
There is "Missing workspace - workspace deleted during concurrent build" issue workspace path which tvm ci uses to test topi is not unique - |
PAD operator is used in TFLite SSD Resnet 50 model (ssd_resnet_50_fpn_coco).
Model graph: ssd_resnet_50_fpn_coco.tflite.pdf
This PR adds PAD operator support to relay tflite frontend.