Merge branch 'master' into Maj-Pierre-1

segment/train.py

@@ -746,7 +746,7 @@ def run(**kwargs):
     """
     Executes YOLOv5 training with given parameters, altering options programmatically; returns updated options.
 
-    Example: mport train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
+    Example: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
     """
     opt = parse_opt(True)
     for k, v in kwargs.items():

utils/augmentations.py

@@ -353,7 +353,7 @@ def classify_albumentations(
                 if vflip > 0:
                     T += [A.VerticalFlip(p=vflip)]
                 if jitter > 0:
-                    color_jitter = (float(jitter),) * 3  # repeat value for brightness, contrast, satuaration, 0 hue
+                    color_jitter = (float(jitter),) * 3  # repeat value for brightness, contrast, saturation, 0 hue
                     T += [A.ColorJitter(*color_jitter, 0)]
         else:  # Use fixed crop for eval set (reproducibility)
             T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]

utils/dataloaders.py

@@ -136,7 +136,7 @@ class SmartDistributedSampler(distributed.DistributedSampler):
         g = torch.Generator()
         g.manual_seed(self.seed + self.epoch)
 
-        # determine the the eventual size (n) of self.indices (DDP indices)
+        # determine the eventual size (n) of self.indices (DDP indices)
         n = int((len(self.dataset) - self.rank - 1) / self.num_replicas) + 1  # num_replicas == WORLD_SIZE
         idx = torch.randperm(n, generator=g)
         if not self.shuffle:

utils/loggers/clearml/hpo.py

@@ -58,7 +58,7 @@ optimizer = HyperParameterOptimizer(
     # now we decide if we want to maximize it or minimize it (accuracy we maximize)
     objective_metric_sign="max",
     # let us limit the number of concurrent experiments,
-    # this in turn will make sure we do dont bombard the scheduler with experiments.
+    # this in turn will make sure we don't bombard the scheduler with experiments.
     # if we have an auto-scaler connected, this, by proxy, will limit the number of machine
     max_number_of_concurrent_tasks=1,
     # this is the optimizer class (actually doing the optimization)