ultralytics 8.0.190 add thop>=0.1.1 to requirements.txt (#5162)

Co-authored-by: JohanWesto <Johan.westo@gmail.com>
Co-authored-by: Muhammad Rizwan Munawar <62513924+RizwanMunawar@users.noreply.github.com>
Co-authored-by: StephenBeirlaen <11806615+StephenBeirlaen@users.noreply.github.com>

docs/modes/predict.md

@@ -23,6 +23,13 @@ In the world of machine learning and computer vision, the process of making sens
   <strong>Watch:</strong> How to Extract the Outputs from Ultralytics YOLOv8 Model for Custom Projects.
 </p>
 
+## Real-world Applications
+
+| Manufacturing | Sports | Safety |
+|:-----------------------------------:|:-----------------------:|:-----------:|
+| ![Vehicle Spare Parts Detection](https://github.com/RizwanMunawar/ultralytics/assets/62513924/a0f802a8-0776-44cf-8f17-93974a4a28a1) | ![Football Player Detection](https://github.com/RizwanMunawar/ultralytics/assets/62513924/7d320e1f-fc57-4d7f-a691-78ee579c3442)| ![People Fall Detection](https://github.com/RizwanMunawar/ultralytics/assets/62513924/86437c4a-3227-4eee-90ef-9efb697bdb43) |
+| Vehicle Spare Parts Detection | Football Player Detection | People Fall Detection |
+
 ## Why Use Ultralytics YOLO for Inference?
 
 Here's why you should consider YOLOv8's predict mode for your various inference needs:

docs/modes/track.md

@@ -30,6 +30,13 @@ The output from Ultralytics trackers is consistent with standard object detectio
   <strong>Watch:</strong> Object Detection and Tracking with Ultralytics YOLOv8.
 </p>
 
+## Real-world Applications
+
+| Transportation | Retail | Aquaculture |
+|:-----------------------------------:|:-----------------------:|:-----------:|
+| ![Vehicle Tracking](https://github.com/RizwanMunawar/ultralytics/assets/62513924/ee6e6038-383b-4f21-ac29-b2a1c7d386ab) | ![People Tracking](https://github.com/RizwanMunawar/ultralytics/assets/62513924/93bb4ee2-77a0-4e4e-8eb6-eb8f527f0527) | ![Fish Tracking](https://github.com/RizwanMunawar/ultralytics/assets/62513924/a5146d0f-bfa8-4e0a-b7df-3c1446cd8142) |
+| Vehicle Tracking | People Tracking | Fish Tracking |
+
 ## Features at a Glance
 
 Ultralytics YOLO extends its object detection features to provide robust and versatile object tracking:
@@ -321,4 +328,4 @@ By contributing to this section, you help expand the scope of tracking solutions
 
 To initiate your contribution, please refer to our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for comprehensive instructions on submitting a Pull Request (PR) 🛠️. We are excited to see what you bring to the table!
 
-Together, let's enhance the tracking capabilities of the Ultralytics YOLO ecosystem 🙏!
+Together, let's enhance the tracking capabilities of the Ultralytics YOLO ecosystem 🙏!

requirements.txt

@@ -38,7 +38,7 @@ seaborn>=0.11.0
 # Extras --------------------------------------
 psutil  # system utilization
 py-cpuinfo  # display CPU info
-# thop>=0.1.1  # FLOPs computation
+thop>=0.1.1  # FLOPs computation
 # ipython  # interactive notebook
 # albumentations>=1.0.3  # training augmentations
 # pycocotools>=2.0.6  # COCO mAP

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = '8.0.189'
+__version__ = '8.0.190'
 
 from ultralytics.models import RTDETR, SAM, YOLO
 from ultralytics.models.fastsam import FastSAM

ultralytics/data/augment.py

@@ -791,14 +791,14 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
 
 
 # Classification augmentations -----------------------------------------------------------------------------------------
-def classify_transforms(size=224, mean=(0.0, 0.0, 0.0), std=(1.0, 1.0, 1.0)):  # IMAGENET_MEAN, IMAGENET_STD
-    # Transforms to apply if albumentations not installed
+def classify_transforms(size=224, rect=False, mean=(0.0, 0.0, 0.0), std=(1.0, 1.0, 1.0)):  # IMAGENET_MEAN, IMAGENET_STD
+    """Transforms to apply if albumentations not installed."""
     if not isinstance(size, int):
         raise TypeError(f'classify_transforms() size {size} must be integer, not (list, tuple)')
+    transforms = [ClassifyLetterBox(size, auto=True) if rect else CenterCrop(size), ToTensor()]
     if any(mean) or any(std):
-        return T.Compose([CenterCrop(size), ToTensor(), T.Normalize(mean, std, inplace=True)])
-    else:
-        return T.Compose([CenterCrop(size), ToTensor()])
+        transforms.append(T.Normalize(mean, std, inplace=True))
+    return T.Compose(transforms)
 
 
 def hsv2colorjitter(h, s, v):
@@ -864,9 +864,9 @@ class ClassifyLetterBox:
         imh, imw = im.shape[:2]
         r = min(self.h / imh, self.w / imw)  # ratio of new/old
         h, w = round(imh * r), round(imw * r)  # resized image
-        hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else self.h, self.w
+        hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else (self.h, self.w)
         top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1)
-        im_out = np.full((self.h, self.w, 3), 114, dtype=im.dtype)
+        im_out = np.full((hs, ws, 3), 114, dtype=im.dtype)
         im_out[top:top + h, left:left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
         return im_out
 

ultralytics/data/dataset.py

@@ -222,7 +222,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
         self.cache_disk = cache == 'disk'
         self.samples = self.verify_images()  # filter out bad images
         self.samples = [list(x) + [Path(x[0]).with_suffix('.npy'), None] for x in self.samples]  # file, index, npy, im
-        self.torch_transforms = classify_transforms(args.imgsz)
+        self.torch_transforms = classify_transforms(args.imgsz, rect=args.rect)
         self.album_transforms = classify_albumentations(
             augment=augment,
             size=args.imgsz,

ultralytics/engine/exporter.py

@@ -627,6 +627,9 @@ class Exporter:
         if builder.platform_has_fast_fp16 and self.args.half:
             config.set_flag(trt.BuilderFlag.FP16)
 
+        del self.model
+        torch.cuda.empty_cache()
+
         # Write file
         with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
             # Metadata