Dynamic ONNX engine generation (#2208)

* add: dynamic onnx export

* delete: test onnx inference

* fix dynamic output axis

* Code reduction

* fix: dynamic output axes, dynamic input naming

* Remove fixed axes

Co-authored-by: Shivam Swanrkar <ss8464@nyu.edu>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

models/export.py

     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')
     opt = parser.parse_args()
     opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
         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'])
+                          output_names=['classes', 'boxes'] if y is None else ['output'],
+                          dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # size(1,3,640,640)
+                                        'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
 
         # Checks
         onnx_model = onnx.load(f)  # load onnx model