Skip to content

[Fix Bug]fix the bug of tensorflow frontend when parsing Range layer #9999

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
masahi merged 5 commits into from
Jan 26, 2022
Merged

[Fix Bug]fix the bug of tensorflow frontend when parsing Range layer #9999

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e0ad1bb
[Fix Bug]fix the bug of tensorflow frontend when parsing Range layer
Jan 20, 2022
f032b20
Merge pull request #1 from apache/main
ninesheep Jan 21, 2022
3a357a7
Merge pull request #2 from apache/main
ninesheep Jan 24, 2022
c263c02
Merge pull request #3 from apache/main
ninesheep Jan 25, 2022
feadfc9
Merge pull request #4 from apache/main
ninesheep Jan 26, 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
4 changes: 2 additions & 2 deletions python/tvm/relay/frontend/tensorflow_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2454,16 +2454,16 @@ def _impl(inputs, attr, params, mod):
delta = inputs[2]

# if all attributes are constant, evalute the range function and return relay.const
dtype = attr["Tidx"].name if "Tidx" in attr else str(start.dtype)
if all(
[
isinstance(start, (np.int32, np.int64, int, np.float32, np.float64, float)),
isinstance(limit, (np.int32, np.int64, int, np.float32, np.float64, float)),
isinstance(delta, (np.int32, np.int64, int, np.float32, np.float64, float)),
]
):
return tvm.relay.const(list(range(int(start), int(limit), int(delta))))
return tvm.relay.const(list(range(int(start), int(limit), int(delta))), dtype=dtype)

dtype = attr["Tidx"].name if "Tidx" in attr else str(start.dtype)
if isinstance(start, (np.int32, np.int64, int, np.float32, np.float64, float)):
start = _expr.const(start, dtype=dtype)
if isinstance(limit, (np.int32, np.int64, int, np.float32, np.float64, float)):
Expand Down