GPU export options (ultralytics#2297)

* option for skip last layer and cuda export support

* added parameter device

* fix import

* cleanup 1

* cleanup 2

* opt-in grid

--grid will export with grid computation, default export will skip grid (same as current)

* default --device cpu

GPU export causes ONNX and CoreML errors.

Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

models/export.py

@@ -17,29 +17,33 @@
 from models.experimental import attempt_load
 from utils.activations import Hardswish, SiLU
 from utils.general import set_logging, check_img_size
+from utils.torch_utils import select_device
 
 if __name__ == '__main__':
     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 axes')
     parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes')
+    parser.add_argument('--grid', action='store_true', help='export Detect() layer grid')
+    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
     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 = select_device(opt.device)
+    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():
@@ -51,7 +55,7 @@
                 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
+    model.model[-1].export = not opt.grid  # set Detect() layer grid export
     y = model(img)  # dry run
 
     # TorchScript export