Add SPPF() layer (#4420)

* Add `SPPF()` layer

* Cleanup

* Add credit

models/yolo.py

@@ -237,8 +237,8 @@ def parse_model(d, ch):  # model_dict, input_channels(3)
                 pass
 
         n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
-                 C3, C3TR, C3SPP, C3Ghost]:
+        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
+                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
             c1, c2 = ch[f], args[0]
             if c2 != no:  # if not output
                 c2 = make_divisible(c2 * gw, 8)
@@ -279,6 +279,7 @@ if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
     parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--profile', action='store_true', help='profile model speed')
     opt = parser.parse_args()
     opt.cfg = check_file(opt.cfg)  # check file
     set_logging()
@@ -289,8 +290,9 @@ if __name__ == '__main__':
     model.train()
 
     # Profile
-    # img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 320, 320).to(device)
-    # y = model(img, profile=True)
+    if opt.profile:
+        img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+        y = model(img, profile=True)
 
     # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
     # from torch.utils.tensorboard import SummaryWriter