Skip to content
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

Dynamic ONNX engine generation #2208

Merged
merged 6 commits into from
Feb 22, 2021
Merged

Dynamic ONNX engine generation #2208

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c265dcf
add: dynamic onnx export
aditya-dl Feb 12, 2021
b8b5a86
delete: test onnx inference
aditya-dl Feb 13, 2021
c453bb8
fix dynamic output axis
shivamswarnkar Feb 14, 2021
5ec68db
Code reduction
glenn-jocher Feb 16, 2021
e7e4a59
fix: dynamic output axes, dynamic input naming
aditya-dl Feb 21, 2021
d6676f3
Remove fixed axes
glenn-jocher Feb 22, 2021
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
11 changes: 9 additions & 2 deletions models/export.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path') # from yolov5/models/
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width
parser.add_argument('--dynamic', action='store_true', help='dynamic onnx export')
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
opt = parser.parse_args()
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
Expand Down Expand Up @@ -69,8 +70,14 @@

print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
f = opt.weights.replace('.pt', '.onnx') # filename
torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
output_names=['classes', 'boxes'] if y is None else ['output'])
if opt.dynamic:
torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
output_names=['output'], dynamic_axes={'images': {0: 'batch_size', 2: 'image_width',
3: 'image_height'},
'output': {0: 'batch_size', 2: 'op1', 3: 'op2'}})
else:
torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
output_names=['classes', 'boxes'] if y is None else ['output'])

# Checks
onnx_model = onnx.load(f) # load onnx model
Expand Down