yolo.py profiling updates (#7178)

* yolo.py profiling updates

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

models/yolo.py

@@ -25,7 +25,8 @@ from models.experimental import *
 from utils.autoanchor import check_anchor_order
 from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
 from utils.plots import feature_visualization
-from utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device, time_sync
+from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
+                               time_sync)
 
 try:
     import thop  # for FLOPs computation
@@ -300,8 +301,10 @@ def parse_model(d, ch):  # model_dict, input_channels(3)
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
     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')
+    parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
     parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
     opt = parser.parse_args()
     opt.cfg = check_yaml(opt.cfg)  # check YAML
@@ -309,24 +312,19 @@ if __name__ == '__main__':
     device = select_device(opt.device)
 
     # Create model
+    im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
     model = Model(opt.cfg).to(device)
 
-    # Profile
-    if opt.profile:
-        model.eval().fuse()
-        img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
-        y = model(img, profile=True)
+    # Options
+    if opt.line_profile:  # profile layer by layer
+        _ = model(im, profile=True)
 
-    # Test all models
-    if opt.test:
+    elif opt.profile:  # profile forward-backward
+        results = profile(input=im, ops=[model], n=3)
+
+    elif opt.test:  # test all models
         for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
             try:
                 _ = Model(cfg)
             except Exception as e:
                 print(f'Error in {cfg}: {e}')
-
-    # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
-    # from torch.utils.tensorboard import SummaryWriter
-    # tb_writer = SummaryWriter('.')
-    # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
-    # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), [])  # add model graph