Skip to content

[QNNParam] Refactor the implmentation of QNNParam #11011

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.

Sign up for GitHub

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

Merged
AndrewZhaoLuo merged 3 commits into from
Apr 15, 2022
Merged

[QNNParam] Refactor the implmentation of QNNParam #11011

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b4dc91b
The patch is to simplify the implmentation of QNNParam and make it mo…
billishyahao Apr 14, 2022
88c4311
Empty-Commit
billishyahao Apr 15, 2022
072a557
fix error about boolean value of Tensor with more than one value is a…
billishyahao Apr 15, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 2 additions & 7 deletions python/tvm/relay/frontend/qnn_torch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,17 +28,12 @@
from .pytorch_utils import is_version_greater_than, getattr_attr_name


class QNNParam:
class QNNParam(object):
"""A placeholder for weight quantization parameters"""

def __init__(self, weight, bias, scale, zero_point):
self.weight = weight

if bias is not None:
self.bias = bias.detach().numpy()
else:
self.bias = None

self.bias = None if bias is None else bias.detach().numpy()
self.scale = _expr.const(scale)
self.zero_point = _expr.const(zero_point, dtype="int32")

Expand Down