Skip to content

ADD: support of fp16 python inference backend #773

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

ADD: support of fp16 python inference backend #773

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 5 additions & 1 deletion onnx_tensorrt/backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ def count_trailing_ones(vals):

class TensorRTBackendRep(BackendRep):
def __init__(self, model, device,
max_workspace_size=None, serialize_engine=False, verbose=False, **kwargs):
max_workspace_size=None, serialize_engine=False, verbose=False, fp16=False, **kwargs):
if not isinstance(device, Device):
device = Device(device)
self._set_device(device)
Expand All @@ -44,8 +44,12 @@ def __init__(self, model, device,
self.shape_tensor_inputs = []
self.serialize_engine = serialize_engine
self.verbose = verbose
self.fp16 = fp16
self.dynamic = False

if self.fp16:
self.config.set_flag(trt.BuilderFlag.FP16)

if self.verbose:
print(f'\nRunning {model.graph.name}...')
TRT_LOGGER.min_severity = trt.Logger.VERBOSE
Expand Down