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

Jump to bottom

GPU export options #2297

Merged
merged 7 commits into from
Mar 6, 2021
Merged

GPU export options #2297

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
49bd2fe
option for skip last layer and cuda export support
Feb 25, 2021
93b41d7
added parameter device
Mar 2, 2021
e3f5bdb
fix import
Mar 2, 2021
6373c3f
cleanup 1
glenn-jocher Mar 6, 2021
b482563
cleanup 2
glenn-jocher Mar 6, 2021
435cb83
opt-in grid
glenn-jocher Mar 6, 2021
2b2c800
default --device cpu
glenn-jocher Mar 6, 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: 8 additions & 3 deletions models/export.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,22 +24,24 @@
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 axes')
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
parser.add_argument('--skip-last-layer', action='store_true', help='skip export of last (detect) layer')
opt = parser.parse_args()
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
print(opt)
set_logging()
t = time.time()

# Load PyTorch model
model = attempt_load(opt.weights, map_location=torch.device('cpu')) # load FP32 model
device = torch.device("cuda:0") if torch.cuda.is_available() else "cpu"
model = attempt_load(opt.weights, map_location=device) # load FP32 model
labels = model.names

# Checks
gs = int(max(model.stride)) # grid size (max stride)
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples

# Input
img = torch.zeros(opt.batch_size, 3, *opt.img_size) # image size(1,3,320,192) iDetection
img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection

# Update model
for k, m in model.named_modules():
Expand All @@ -51,7 +53,10 @@
m.act = SiLU()
# elif isinstance(m, models.yolo.Detect):
# m.forward = m.forward_export # assign forward (optional)
model.model[-1].export = True # set Detect() layer export=True
if opt.skip_last_layer:
model.model[-1].export = False # set Detect() layer export=False
else:
model.model[-1].export = True # set Detect() layer export=True
y = model(img) # dry run

# TorchScript export
Expand Down