Introduction to Yolov8 for custom data

Act I. Making a prediction on foundation model

NB !ED! change runtime type to GPU omg!

# It should "just work"
!pip install ultralytics
!pip install opencv-python
import cv2
from IPython.display import display, Image

Collecting ultralytics
  Downloading ultralytics-8.0.220-py3-none-any.whl (645 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 646.0/646.0 kB 7.8 MB/s eta 0:00:00
Requirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (3.7.1)
Requirement already satisfied: numpy>=1.22.2 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.23.5)
Requirement already satisfied: opencv-python>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (4.8.0.76)
Requirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (9.4.0)
Requirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (6.0.1)
Requirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.31.0)
Requirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.11.3)
Requirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.1.0+cu118)
Requirement already satisfied: torchvision>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (0.16.0+cu118)
Requirement already satisfied: tqdm>=4.64.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (4.66.1)
Requirement already satisfied: pandas>=1.1.4 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.5.3)
Requirement already satisfied: seaborn>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (0.12.2)
Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from ultralytics) (5.9.5)
Requirement already satisfied: py-cpuinfo in /usr/local/lib/python3.10/dist-packages (from ultralytics) (9.0.0)
Collecting thop>=0.1.1 (from ultralytics)
  Downloading thop-0.1.1.post2209072238-py3-none-any.whl (15 kB)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.2.0)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.44.3)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.4.5)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (23.2)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (3.1.1)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.4->ultralytics) (2023.3.post1)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (2.0.7)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (2023.7.22)
Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.13.1)
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (4.5.0)
Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (1.12)
Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.2.1)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.1.2)
Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (2023.6.0)
Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (2.1.0)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.16.0)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (2.1.3)
Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.8.0->ultralytics) (1.3.0)
Installing collected packages: thop, ultralytics
Successfully installed thop-0.1.1.post2209072238 ultralytics-8.0.220
Requirement already satisfied: opencv-python in /usr/local/lib/python3.10/dist-packages (4.8.0.76)
Requirement already satisfied: numpy>=1.21.2 in /usr/local/lib/python3.10/dist-packages (from opencv-python) (1.23.5)

#command line way.  "This is the way (but not the easiest way)."
!yolo task=detect \
mode=predict \
model=yolov8n.pt \
conf=0.25 \
source='edowl.png'

Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt to 'yolov8n.pt'...
100% 6.23M/6.23M [00:00<00:00, 67.6MB/s]
Ultralytics YOLOv8.0.220 🚀 Python-3.10.12 torch-2.1.0+cu118 CUDA:0 (Tesla T4, 15102MiB)
YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs

image 1/1 /content/edowl.png: 640x480 1 person, 1 bird, 136.0ms
Speed: 15.3ms preprocess, 136.0ms inference, 42.8ms postprocess per image at shape (1, 3, 640, 480)
Results saved to runs/detect/predict
💡 Learn more at https://docs.ultralytics.com/modes/predict

# function way "This is probably the way"
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
model.predict(
   source='edowl.png',
   conf=0.25
)


image 1/1 /content/edowl.png: 640x480 1 person, 1 bird, 100.6ms
Speed: 4.4ms preprocess, 100.6ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 480)

[ultralytics.engine.results.Results object with attributes:
 
 boxes: ultralytics.engine.results.Boxes object
 keypoints: None
 masks: None
 names: {0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus', 6: 'train', 7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant', 11: 'stop sign', 12: 'parking meter', 13: 'bench', 14: 'bird', 15: 'cat', 16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear', 22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag', 27: 'tie', 28: 'suitcase', 29: 'frisbee', 30: 'skis', 31: 'snowboard', 32: 'sports ball', 33: 'kite', 34: 'baseball bat', 35: 'baseball glove', 36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle', 40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl', 46: 'banana', 47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli', 51: 'carrot', 52: 'hot dog', 53: 'pizza', 54: 'donut', 55: 'cake', 56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table', 61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard', 67: 'cell phone', 68: 'microwave', 69: 'oven', 70: 'toaster', 71: 'sink', 72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors', 77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush'}
 orig_img: array([[[248, 244, 243],
         [248, 244, 243],
         [248, 244, 243],
         ...,
         [ 24,  41,  29],
         [ 20,  39,  26],
         [ 17,  36,  23]],
 
        [[248, 244, 243],
         [248, 244, 243],
         [248, 244, 243],
         ...,
         [ 33,  50,  38],
         [ 33,  50,  37],
         [ 67,  84,  71]],
 
        [[247, 244, 243],
         [247, 244, 243],
         [247, 244, 243],
         ...,
         [ 27,  40,  29],
         [ 57,  72,  59],
         [141, 157, 144]],
 
        ...,
 
        [[ 63,  63,  63],
         [ 64,  64,  64],
         [ 64,  64,  64],
         ...,
         [ 62,  63,  63],
         [ 62,  63,  63],
         [ 65,  66,  66]],
 
        [[ 63,  63,  63],
         [ 64,  64,  64],
         [ 65,  65,  65],
         ...,
         [ 63,  64,  64],
         [ 64,  65,  65],
         [ 61,  62,  62]],
 
        [[ 63,  63,  63],
         [ 64,  64,  64],
         [ 63,  63,  63],
         ...,
         [ 61,  62,  62],
         [ 62,  63,  63],
         [ 63,  64,  64]]], dtype=uint8)
 orig_shape: (1255, 939)
 path: '/content/edowl.png'
 probs: None
 save_dir: None
 speed: {'preprocess': 4.355430603027344, 'inference': 100.57592391967773, 'postprocess': 2.0024776458740234}]

# display your results
display(Image(filename='runs/detect/predict/edowl.png'))

Note: If there is time for an experiment:

maybe try a set of weights from a different, better model: https://github.com/ultralytics/ultralytics
Try your own picture… just drag and drop.

Act II. Custom data, Yolo model

Transfer learning

Transfer learning, used in machine learning, is the reuse of a pre-trained model on a new problem. In transfer learning, a machine exploits the knowledge gained from a previous task to improve generalization about another.

To do this you need to create your own training data

We are going to look at an example today on a platform called Roboflow.

# NB API key is fiddley
!pip install roboflow
from roboflow import Roboflow
from google.colab import userdata

rf = Roboflow(api_key=userdata.get('roboflowkey')) # << explain briefly!
project = rf.workspace("roboflow-gw7yv").project("raccoon")
dataset = project.version(38).download("yolov8")

loading Roboflow workspace...
loading Roboflow project...
Dependency ultralytics==8.0.196 is required but found version=8.0.220, to fix: `pip install ultralytics==8.0.196`

Downloading Dataset Version Zip in Raccoon-38 to yolov8:: 100%|██████████| 11800/11800 [00:00<00:00, 32613.29it/s]


Extracting Dataset Version Zip to Raccoon-38 in yolov8:: 100%|██████████| 799/799 [00:00<00:00, 8040.91it/s]

!yolo task=detect \
mode = train \
model = yolov8s.pt \
data = /content/Raccoon-38/data.yaml \
epochs = 10 \
imgsz = 640

Ultralytics YOLOv8.0.220 🚀 Python-3.10.12 torch-2.1.0+cu118 CUDA:0 (Tesla T4, 15102MiB)
engine/trainer: task=detect, mode=train, model=yolov8s.pt, data=/content/Raccoon-38/data.yaml, epochs=10, patience=50, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train2, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train2
Downloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'...
100% 755k/755k [00:00<00:00, 12.3MB/s]
2023-11-29 15:19:03.571951: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-29 15:19:03.572023: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-29 15:19:03.572079: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
Overriding model.yaml nc=80 with nc=1

                   from  n    params  module                                       arguments                     
  0                  -1  1       928  ultralytics.nn.modules.conv.Conv             [3, 32, 3, 2]                 
  1                  -1  1     18560  ultralytics.nn.modules.conv.Conv             [32, 64, 3, 2]                
  2                  -1  1     29056  ultralytics.nn.modules.block.C2f             [64, 64, 1, True]             
  3                  -1  1     73984  ultralytics.nn.modules.conv.Conv             [64, 128, 3, 2]               
  4                  -1  2    197632  ultralytics.nn.modules.block.C2f             [128, 128, 2, True]           
  5                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]              
  6                  -1  2    788480  ultralytics.nn.modules.block.C2f             [256, 256, 2, True]           
  7                  -1  1   1180672  ultralytics.nn.modules.conv.Conv             [256, 512, 3, 2]              
  8                  -1  1   1838080  ultralytics.nn.modules.block.C2f             [512, 512, 1, True]           
  9                  -1  1    656896  ultralytics.nn.modules.block.SPPF            [512, 512, 5]                 
 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          
 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           
 12                  -1  1    591360  ultralytics.nn.modules.block.C2f             [768, 256, 1]                 
 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          
 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           
 15                  -1  1    148224  ultralytics.nn.modules.block.C2f             [384, 128, 1]                 
 16                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]              
 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           
 18                  -1  1    493056  ultralytics.nn.modules.block.C2f             [384, 256, 1]                 
 19                  -1  1    590336  ultralytics.nn.modules.conv.Conv             [256, 256, 3, 2]              
 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           
 21                  -1  1   1969152  ultralytics.nn.modules.block.C2f             [768, 512, 1]                 
 22        [15, 18, 21]  1   2116435  ultralytics.nn.modules.head.Detect           [1, [128, 256, 512]]          
Model summary: 225 layers, 11135987 parameters, 11135971 gradients, 28.6 GFLOPs

Transferred 349/355 items from pretrained weights
TensorBoard: Start with 'tensorboard --logdir runs/detect/train2', view at http://localhost:6006/
Freezing layer 'model.22.dfl.conv.weight'
AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n...
AMP: checks passed ✅
train: Scanning /content/Raccoon-38/train/labels... 150 images, 0 backgrounds, 0 corrupt: 100% 150/150 [00:00<00:00, 1576.78it/s]
train: New cache created: /content/Raccoon-38/train/labels.cache
albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))
val: Scanning /content/Raccoon-38/valid/labels... 29 images, 0 backgrounds, 0 corrupt: 100% 29/29 [00:00<00:00, 919.25it/s]
val: New cache created: /content/Raccoon-38/valid/labels.cache
Plotting labels to runs/detect/train2/labels.jpg... 
optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... 
optimizer: AdamW(lr=0.002, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)
Image sizes 640 train, 640 val
Using 2 dataloader workers
Logging results to runs/detect/train2
Starting training for 10 epochs...
Closing dataloader mosaic
albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       1/10      3.93G      1.783      7.084      2.412          6        640: 100% 10/10 [00:07<00:00,  1.31it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:01<00:00,  1.84s/it]
                   all         29         29      0.666      0.655      0.717      0.279

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       2/10      3.99G      1.371      2.883      2.013          8        640: 100% 10/10 [00:02<00:00,  3.42it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.12it/s]
                   all         29         29      0.603      0.828      0.721      0.277

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       3/10      4.01G      1.178      1.829      1.895          6        640: 100% 10/10 [00:02<00:00,  3.72it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.28it/s]
                   all         29         29      0.813      0.759      0.807       0.39

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       4/10      4.01G       1.26      1.564      1.923          6        640: 100% 10/10 [00:03<00:00,  2.74it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  1.17it/s]
                   all         29         29      0.744      0.703      0.757      0.348

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       5/10         4G      1.155      1.257      1.845          7        640: 100% 10/10 [00:02<00:00,  3.72it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.27it/s]
                   all         29         29      0.632      0.862      0.807      0.364

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       6/10      4.01G      1.269       1.26      1.864          7        640: 100% 10/10 [00:02<00:00,  3.79it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.39it/s]
                   all         29         29      0.893      0.862      0.928      0.386

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       7/10         4G      1.111       1.15      1.714          6        640: 100% 10/10 [00:03<00:00,  3.06it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  1.12it/s]
                   all         29         29      0.878      0.828      0.882      0.391

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       8/10      4.01G      1.183      1.044      1.792          6        640: 100% 10/10 [00:02<00:00,  3.58it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.09it/s]
                   all         29         29      0.848      0.966      0.955      0.491

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
       9/10         4G       1.08      1.052      1.692          6        640: 100% 10/10 [00:02<00:00,  3.78it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.24it/s]
                   all         29         29      0.917      0.966      0.958      0.545

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
      10/10         4G      0.962     0.8895      1.587          6        640: 100% 10/10 [00:02<00:00,  3.40it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  1.23it/s]
                   all         29         29      0.893       0.86      0.933      0.555

10 epochs completed in 0.016 hours.
Optimizer stripped from runs/detect/train2/weights/last.pt, 22.5MB
Optimizer stripped from runs/detect/train2/weights/best.pt, 22.5MB

Validating runs/detect/train2/weights/best.pt...
Ultralytics YOLOv8.0.220 🚀 Python-3.10.12 torch-2.1.0+cu118 CUDA:0 (Tesla T4, 15102MiB)
Model summary (fused): 168 layers, 11125971 parameters, 0 gradients, 28.4 GFLOPs
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  2.54it/s]
                   all         29         29      0.893       0.86      0.933      0.555
Speed: 0.2ms preprocess, 6.0ms inference, 0.0ms loss, 1.8ms postprocess per image
Results saved to runs/detect/train2
💡 Learn more at https://docs.ultralytics.com/modes/train

Readings and sources:

Redmon, J., Divvala, S., Girshick, R. and Farhadi, A., 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).
https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Redmon_You_Only_Look_CVPR_2016_paper.html

Joseph Redmon et al. presents YOLO, a novel approach to object detection framing it as a regression problem, predicting bounding boxes and class probabilities from full images in a single network evaluation. YOLO is unique for its speed, processing images in real-time, and its unified architecture, which allows for end-to-end optimization directly on detection performance, making it significantly faster and more accurate than existing detection systems.

Jiang, P., Ergu, D., Liu, F., Cai, Y. and Ma, B., 2022. A Review of Yolo algorithm developments. Procedia Computer Science, 199, pp.1066-1073.
https://www.sciencedirect.com/science/article/pii/S1877050922001363

A comprehensive overview of the development and advancements of the You Only Look Once (YOLO) algorithm and its versions, focusing on their differences, features, and performance improvements in object detection. It highlights YOLO’s evolution from its initial version to advanced iterations like YOLO V5, discussing their architectural changes, efficiency in detecting objects, and contributions to the field of object detection, particularly in applying and enhancing features for accuracy and detector performance.

https://blog.roboflow.com/how-to-train-yolov8-on-a-custom-dataset/

Tutorial on training the YOLOv8 model, the latest in the YOLO series, known for its object detection, instance segmentation, and image classification capabilities. The article guides readers through the process of using the new API to prepare a dataset and train and validate the YOLOv8 model on a custom dataset.