Unverified 提交 d45e349a authored 作者: Glenn Jocher's avatar Glenn Jocher 提交者: GitHub

Rearrange export input after checks (#1118)

img size checks are warnings rather than errors, so current implementation allows improperly formed model inputs.
上级 d87cf7ec
......@@ -29,9 +29,6 @@ if __name__ == '__main__':
set_logging()
t = time.time()
# Input
img = torch.zeros((opt.batch_size, 3, *opt.img_size)) # image size(1,3,320,192) iDetection
# Load PyTorch model
model = attempt_load(opt.weights, map_location=torch.device('cpu')) # load FP32 model
labels = model.names
......@@ -40,6 +37,9 @@ if __name__ == '__main__':
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
# Update model
for k, m in model.named_modules():
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论