Vertopal.com YoloV8

Install the necessary libraries:
!pip install ultralytics
Requirement already satisfied: ultralytics in

/usr/local/lib/python3.10/dist-packages (8.2.31)
Requirement already satisfied: matplotlib>=3.3.0 in
/usr/local/lib/python3.10/dist-packages (from ultralytics) (3.7.1)
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
Requirement already satisfied: pyyaml>=5.3.1 in
Requirement already satisfied: requests>=2.23.0 in
Requirement already satisfied: scipy>=1.4.1 in
Requirement already satisfied: torch>=1.8.0 in
/usr/local/lib/python3.10/dist-packages (from ultralytics)
(2.3.0+cu121)
Requirement already satisfied: torchvision>=0.9.0 in
/usr/local/lib/python3.10/dist-packages (from ultralytics)
(0.18.0+cu121)
Requirement already satisfied: tqdm>=4.64.0 in
Requirement already satisfied: psutil in
Requirement already satisfied: py-cpuinfo in
Requirement already satisfied: pandas>=1.1.4 in
Requirement already satisfied: seaborn>=0.11.0 in
Requirement already satisfied: ultralytics-thop>=0.2.5 in
Requirement already satisfied: contourpy>=1.0.1 in
/usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0-
>ultralytics) (1.2.1)
Requirement already satisfied: cycler>=0.10 in
Requirement already satisfied: fonttools>=4.22.0 in
Requirement already satisfied: kiwisolver>=1.0.1 in
Requirement already satisfied: numpy>=1.20 in
Requirement already satisfied: packaging>=20.0 in
>ultralytics) (24.0)
Requirement already satisfied: pyparsing>=2.3.1 in
Requirement already satisfied: python-dateutil>=2.7 in
Requirement already satisfied: pytz>=2020.1 in
/usr/local/lib/python3.10/dist-packages (from pandas>=1.1.4-
Requirement already satisfied: tzdata>=2022.1 in
/usr/local/lib/python3.10/dist-packages (from pandas>=1.1.4-
Requirement already satisfied: charset-normalizer<4,>=2 in
/usr/local/lib/python3.10/dist-packages (from requests>=2.23.0-
Requirement already satisfied: idna<4,>=2.5 in
Requirement already satisfied: urllib3<3,>=1.21.1 in
Requirement already satisfied: certifi>=2017.4.17 in
Requirement already satisfied: filelock in
/usr/local/lib/python3.10/dist-packages (from torch>=1.8.0-
Requirement already satisfied: typing-extensions>=4.8.0 in
Requirement already satisfied: sympy in
Requirement already satisfied: networkx in
>ultralytics) (3.3)
Requirement already satisfied: jinja2 in
Requirement already satisfied: fsspec in
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105
in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0-
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in
Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in
>ultralytics) (8.9.2.26)
Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in
Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in
Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in
Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in
Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in
Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in
Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in
Requirement already satisfied: triton==2.3.0 in
Requirement already satisfied: nvidia-nvjitlink-cu12 in
/usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-
cu12==11.4.5.107->torch>=1.8.0->ultralytics) (12.5.40)
Requirement already satisfied: six in /usr/local/lib/python3.10/dist-
packages (from cycler>=0.10->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-
Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in
/usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.8.0-
from ultralytics import YOLO

import os
from IPython.display import display, Image
from IPython import display
display.clear_output()
!yolo mode=checks
Traceback (most recent call last):

File "/usr/local/bin/yolo", line 8, in <module>
sys.exit(entrypoint())
File
"/usr/local/lib/python3.10/dist-packages/ultralytics/cfg/__init__.py",
line 532, in entrypoint
raise ValueError(f"Invalid 'mode={mode}'. Valid modes are
{MODES}.\n{CLI_HELP_MSG}")
ValueError: Invalid 'mode=<module 'ultralytics.utils.checks' from
'/usr/local/lib/python3.10/dist-packages/ultralytics/utils/checks.py'>
'. Valid modes are {'benchmark', 'train', 'val', 'predict', 'track',
'export'}.
Arguments received: ['yolo', 'mode=checks']. Ultralytics 'yolo'

commands use the following syntax:
yolo TASK MODE ARGS
Where TASK (optional) is one of {'pose', 'detect',

'segment', 'obb', 'classify'}
MODE (required) is one of {'benchmark', 'train',
'val', 'predict', 'track', 'export'}
ARGS (optional) are any number of custom 'arg=value'
pairs like 'imgsz=320' that override defaults.
See all ARGS at
https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'
1. Train a detection model for 10 epochs with an initial

learning_rate of 0.01
yolo train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01
2. Predict a YouTube video using a pretrained segmentation model

at image size 320:
yolo predict model=yolov8n-seg.pt
source='https://youtu.be/LNwODJXcvt4' imgsz=320
3. Val a pretrained detection model at batch-size 1 and image size

640:
yolo val model=yolov8n.pt data=coco8.yaml batch=1 imgsz=640
4. Export a YOLOv8n classification model to ONNX format at image

size 224 by 128 (no TASK required)
yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
6. Explore your datasets using semantic search and SQL with a

simple GUI powered by Ultralytics Explorer API
yolo explorer
5. Run special commands:
yolo help
yolo checks
yolo version
yolo settings
yolo copy-cfg
yolo cfg
Docs: https://docs.ultralytics.com
Community: https://community.ultralytics.com
GitHub: https://github.com/ultralytics/ultralytics
Download and extract the dataset
!pip install roboflow
from roboflow import Roboflow

rf = Roboflow(api_key="QU8p8L2XCFWqiwia8Yes")
project = rf.workspace("vinit-gtshu").project("pizza-ddydk")
version = project.version(1)
dataset = version.download("yolov8")
Requirement already satisfied: roboflow in

/usr/local/lib/python3.10/dist-packages (1.1.32)
Requirement already satisfied: certifi==2023.7.22 in
/usr/local/lib/python3.10/dist-packages (from roboflow) (2023.7.22)
Requirement already satisfied: chardet==4.0.0 in
Requirement already satisfied: cycler==0.10.0 in
Requirement already satisfied: idna==2.10 in
/usr/local/lib/python3.10/dist-packages (from roboflow) (2.10)
Requirement already satisfied: kiwisolver>=1.3.1 in
Requirement already satisfied: matplotlib in
Requirement already satisfied: numpy>=1.18.5 in
Requirement already satisfied: opencv-python-headless==4.8.0.74 in
/usr/local/lib/python3.10/dist-packages (from roboflow) (4.8.0.74)
Requirement already satisfied: Pillow>=7.1.2 in
Requirement already satisfied: python-dateutil in
Requirement already satisfied: python-dotenv in
Requirement already satisfied: requests in
Requirement already satisfied: six in /usr/local/lib/python3.10/dist-
packages (from roboflow) (1.16.0)
Requirement already satisfied: urllib3>=1.26.6 in
Requirement already satisfied: tqdm>=4.41.0 in
Requirement already satisfied: PyYAML>=5.3.1 in
Requirement already satisfied: requests-toolbelt in
Requirement already satisfied: python-magic in
Requirement already satisfied: contourpy>=1.0.1 in
/usr/local/lib/python3.10/dist-packages (from matplotlib->roboflow)
(1.2.1)
Requirement already satisfied: fonttools>=4.22.0 in
(4.53.0)
Requirement already satisfied: packaging>=20.0 in
(24.0)
Requirement already satisfied: pyparsing>=2.3.1 in
(3.1.2)
Requirement already satisfied: charset-normalizer<4,>=2 in
/usr/local/lib/python3.10/dist-packages (from requests->roboflow)
(3.3.2)
loading Roboflow workspace...
loading Roboflow project...
Dependency ultralytics==8.0.196 is required but found version=8.2.31,
to fix: `pip install ultralytics==8.0.196`
Downloading Dataset Version Zip in Pizza-1 to yolov8:: 100%|

██████████| 118867/118867 [00:04<00:00, 25510.79it/s]
Extracting Dataset Version Zip to Pizza-1 in yolov8:: 100%|██████████|

3874/3874 [00:01<00:00, 2633.33it/s]
Train the YOLOv8 Model
from ultralytics import YOLO
model = YOLO('yolov8n.yaml') # Load a YOLOv8 model, e.g.,

'yolov8n.yaml' for a nano model
Start the training process:

results = model.train(data='/content/Pizza-1/data.yaml', epochs=20)
Ultralytics YOLOv8.2.31 🚀 Python-3.10.12 torch-2.3.0+cu121 CUDA:0

(Tesla T4, 15102MiB)
engine/trainer: task=detect, mode=train, model=yolov8n.yaml,
data=/content/Pizza-1/data.yaml, epochs=20, time=None, patience=100,
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, multi_scale=False, 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,
embed=None, 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, bgr=0.0, mosaic=1.0, mixup=0.0,
copy_paste=0.0, auto_augment=randaugment, erasing=0.4,
crop_fraction=1.0, 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, 15.3MB/s]
Overriding model.yaml nc=80 with nc=2
from n params module

arguments
0 -1 1 464 ultralytics.nn.modules.conv.Conv
[3, 16, 3, 2]
[16, 32, 3, 2]
2 -1 1 7360 ultralytics.nn.modules.block.C2f
[32, 32, 1, True]
[32, 64, 3, 2]
[64, 64, 2, True]
[64, 128, 3, 2]
[128, 128, 2, True]
[128, 256, 3, 2]
[256, 256, 1, True]
9 -1 1 164608
ultralytics.nn.modules.block.SPPF [256, 256, 5]
10 -1 1 0
torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
11 [-1, 6] 1 0
ultralytics.nn.modules.conv.Concat [1]
[384, 128, 1]
13 -1 1 0
torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
14 [-1, 4] 1 0
[192, 64, 1]
[64, 64, 3, 2]
17 [-1, 12] 1 0
[192, 128, 1]
[128, 128, 3, 2]
20 [-1, 9] 1 0
[384, 256, 1]
22 [15, 18, 21] 1 751702
ultralytics.nn.modules.head.Detect [2, [64, 128, 256]]
YOLOv8n summary: 225 layers, 3011238 parameters, 3011222 gradients,

8.2 GFLOPs
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...
Downloading
https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n
.pt to 'yolov8n.pt'...
100%|██████████| 6.23M/6.23M [00:00<00:00, 75.3MB/s]

Plan failed with a cudnnException:
CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor
Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally
at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
AMP: checks passed ✅
train: Scanning /content/Pizza-1/train/labels... 1507 images, 0

backgrounds, 0 corrupt: 100%|██████████| 1507/1507 [00:00<00:00,
1931.65it/s]
train: New cache created: /content/Pizza-1/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))
os.fork() was called. os.fork() is incompatible with multithreaded

code, and JAX is multithreaded, so this will likely lead to a
deadlock.
val: Scanning /content/Pizza-1/valid/labels... 280 images, 0
backgrounds, 0 corrupt: 100%|██████████| 280/280 [00:00<00:00,
1228.34it/s]
val: New cache created: /content/Pizza-1/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=0.001667, momentum=0.9) with parameter groups 57
weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)
TensorBoard: model graph visualization added ✅
Image sizes 640 train, 640 val
Using 2 dataloader workers
Logging results to runs/detect/train2
Starting training for 20 epochs...
Epoch GPU_mem box_loss cls_loss dfl_loss Instances

Size
1/20 2.87G 3.237 2.733 3.721 81

640: 100%|██████████| 95/95 [00:50<00:00, 1.89it/s]
Class Images Instances Box(P R
mAP50 mAP50-95): 100%|██████████| 9/9 [00:07<00:00, 1.15it/s]
all 280 4710 0.273 0.151
0.182 0.0651

Size
2/20 2.6G 1.933 1.404 2.289 62

640: 100%|██████████| 95/95 [00:34<00:00, 2.78it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 2.02it/s]
all 280 4710 0.421 0.414

0.472 0.268

Size
3/20 2.82G 1.551 1.046 1.838 47

640: 100%|██████████| 95/95 [00:34<00:00, 2.79it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:03<00:00, 2.70it/s]
all 280 4710 0.618 0.84

0.833 0.426

Size
4/20 2.55G 1.404 0.8861 1.693 83

640: 100%|██████████| 95/95 [00:34<00:00, 2.73it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:03<00:00, 2.87it/s]
all 280 4710 0.916 0.897

0.965 0.591

Size
5/20 2.73G 1.261 0.7707 1.558 68

640: 100%|██████████| 95/95 [00:35<00:00, 2.70it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:03<00:00, 2.91it/s]
all 280 4710 0.908 0.896

0.961 0.635

Size
6/20 3.03G 1.19 0.7151 1.481 92

640: 100%|██████████| 95/95 [00:34<00:00, 2.79it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:03<00:00, 2.57it/s]
all 280 4710 0.9 0.919

0.98 0.68

Size
7/20 2.92G 1.131 0.6627 1.431 72

640: 100%|██████████| 95/95 [00:39<00:00, 2.43it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:05<00:00, 1.54it/s]
all 280 4710 0.978 0.953

0.989 0.745

Size
8/20 2.97G 1.101 0.6364 1.414 105

640: 100%|██████████| 95/95 [00:34<00:00, 2.76it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:03<00:00, 2.66it/s]
all 280 4710 0.98 0.974

0.99 0.75

Size
9/20 2.58G 1.068 0.6011 1.381 102
640: 100%|██████████| 95/95 [00:35<00:00, 2.70it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:03<00:00, 2.89it/s]
all 280 4710 0.978 0.979

0.991 0.736

Size
10/20 3.29G 1.037 0.5747 1.353 124

640: 100%|██████████| 95/95 [00:35<00:00, 2.66it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:02<00:00, 3.02it/s]
all 280 4710 0.982 0.981

0.992 0.789
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))
os.fork() was called. os.fork() is incompatible with multithreaded

code, and JAX is multithreaded, so this will likely lead to a
deadlock.

Size
11/20 2.61G 0.9842 0.5438 1.417 80

640: 100%|██████████| 95/95 [00:39<00:00, 2.38it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 1.82it/s]
all 280 4710 0.981 0.981

0.991 0.795

Size
12/20 2.21G 0.9463 0.5088 1.399 79

640: 100%|██████████| 95/95 [00:31<00:00, 3.03it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:05<00:00, 1.78it/s]
all 280 4710 0.981 0.981

0.991 0.81

Size
13/20 2.2G 0.9274 0.4899 1.373 26

640: 100%|██████████| 95/95 [00:31<00:00, 3.06it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:05<00:00, 1.64it/s]
all 280 4710 0.982 0.987

0.991 0.827

Size
14/20 2.23G 0.8904 0.4556 1.334 88

640: 100%|██████████| 95/95 [00:36<00:00, 2.59it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 1.89it/s]
all 280 4710 0.985 0.988

0.992 0.843

Size
15/20 2.22G 0.8961 0.4484 1.338 76

640: 100%|██████████| 95/95 [00:31<00:00, 3.02it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 1.81it/s]
all 280 4710 0.986 0.986

0.993 0.848

Size
16/20 2.23G 0.8762 0.4279 1.32 43
640: 100%|██████████| 95/95 [00:31<00:00, 3.01it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:05<00:00, 1.78it/s]
all 280 4710 0.988 0.991

0.994 0.863

Size
17/20 2.2G 0.8607 0.4182 1.31 49

640: 100%|██████████| 95/95 [00:31<00:00, 2.99it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 1.80it/s]
all 280 4710 0.989 0.992

0.994 0.867

Size
18/20 2.23G 0.8523 0.4177 1.3 46

640: 100%|██████████| 95/95 [00:31<00:00, 2.97it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:05<00:00, 1.60it/s]
all 280 4710 0.989 0.993

0.993 0.865

Size
19/20 2.21G 0.8352 0.4035 1.277 24

640: 100%|██████████| 95/95 [00:31<00:00, 2.98it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 1.96it/s]
all 280 4710 0.992 0.99

0.994 0.877
Size
20/20 2.23G 0.8221 0.3982 1.271 23

640: 100%|██████████| 95/95 [00:32<00:00, 2.94it/s]
mAP50 mAP50-95): 100%|██████████| 9/9 [00:04<00:00, 1.99it/s]
all 280 4710 0.99 0.996

0.994 0.878
20 epochs completed in 0.225 hours.

Optimizer stripped from runs/detect/train2/weights/last.pt, 6.2MB
Optimizer stripped from runs/detect/train2/weights/best.pt, 6.2MB
Validating runs/detect/train2/weights/best.pt...
Ultralytics YOLOv8.2.31 🚀 Python-3.10.12 torch-2.3.0+cu121 CUDA:0
(Tesla T4, 15102MiB)
YOLOv8n summary (fused): 168 layers, 3006038 parameters, 0 gradients,
8.1 GFLOPs

mAP50 mAP50-95): 100%|██████████| 9/9 [00:18<00:00, 2.02s/it]
all 280 4710 0.99 0.995

0.994 0.878
1 279 279 0.997 1
0.995 0.97
pepperonipizza 269 4431 0.983 0.991
0.994 0.787
Speed: 0.7ms preprocess, 3.6ms inference, 0.0ms loss, 5.2ms
postprocess per image
Results saved to runs/detect/train2
from pytube import YouTube
video_url = 'https://www.youtube.com/watch?v=5lKsyMu6pAk'
yt = YouTube(video_url)
stream = yt.streams.filter(file_extension='mp4').first()
stream.download(filename='input_video.mp4')
{"type":"string"}
yt
<pytube.__main__.YouTube object: videoId=5lKsyMu6pAk>

import cv2
from IPython.display import display, Image
video_url = 'https://www.youtube.com/watch?v=5lKsyMu6pAk'
cap = cv2.VideoCapture(video_url)
output_video_path = 'output.mp4'
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
out = cv2.VideoWriter(output_video_path, fourcc, 20.0, (640, 480))
frame_count = 0
max_frames = 60 * 20 # 1 minute of video at 20 FPS
while cap.isOpened() and frame_count < max_frames:

ret, frame = cap.read()
if not ret:
break
results = model(frame)
out.write(results.render()[0]) # Assuming results.render()
returns frames
frame_count += 1
cap.release()
out.release()
# Display the output video

from IPython.display import HTML
HTML("""
<video width=400 controls>
<source src="output.mp4" type="video/mp4">
</video>
""")
<IPython.core.display.HTML object>

Vertopal.com YoloV8

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Vertopal.com YoloV8

Uploaded by

Copyright:

Available Formats

Install the necessary libraries:

!pip install ultralytics

Requirement already satisfied: ultralytics in

from ultralytics import YOLO

Traceback (most recent call last):

Arguments received: ['yolo', 'mode=checks']. Ultralytics 'yolo'

yolo TASK MODE ARGS

Where TASK (optional) is one of {'pose', 'detect',

1. Train a detection model for 10 epochs with an initial

2. Predict a YouTube video using a pretrained segmentation model

3. Val a pretrained detection model at batch-size 1 and image size

4. Export a YOLOv8n classification model to ONNX format at image

6. Explore your datasets using semantic search and SQL with a

Download and extract the dataset

!pip install roboflow

from roboflow import Roboflow

Requirement already satisfied: roboflow in

Downloading Dataset Version Zip in Pizza-1 to yolov8:: 100%|

Extracting Dataset Version Zip to Pizza-1 in yolov8:: 100%|██████████|

Train the YOLOv8 Model

from ultralytics import YOLO

model = YOLO('yolov8n.yaml') # Load a YOLOv8 model, e.g.,

Start the training process:

Ultralytics YOLOv8.2.31 🚀 Python-3.10.12 torch-2.3.0+cu121 CUDA:0

100%|██████████| 755k/755k [00:00<00:00, 15.3MB/s]

Overriding model.yaml nc=80 with nc=2

from n params module

YOLOv8n summary: 225 layers, 3011238 parameters, 3011222 gradients,

TensorBoard: Start with 'tensorboard --logdir runs/detect/train2',

100%|██████████| 6.23M/6.23M [00:00<00:00, 75.3MB/s]

AMP: checks passed ✅

train: Scanning /content/Pizza-1/train/labels... 1507 images, 0

train: New cache created: /content/Pizza-1/train/labels.cache

os.fork() was called. os.fork() is incompatible with multithreaded

val: New cache created: /content/Pizza-1/valid/labels.cache

Plotting labels to runs/detect/train2/labels.jpg...

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

1/20 2.87G 3.237 2.733 3.721 81

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

2/20 2.6G 1.933 1.404 2.289 62

all 280 4710 0.421 0.414

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

3/20 2.82G 1.551 1.046 1.838 47

all 280 4710 0.618 0.84

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

4/20 2.55G 1.404 0.8861 1.693 83

all 280 4710 0.916 0.897

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

5/20 2.73G 1.261 0.7707 1.558 68

all 280 4710 0.908 0.896

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

6/20 3.03G 1.19 0.7151 1.481 92

all 280 4710 0.9 0.919

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

7/20 2.92G 1.131 0.6627 1.431 72

all 280 4710 0.978 0.953

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

8/20 2.97G 1.101 0.6364 1.414 105

all 280 4710 0.98 0.974

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

all 280 4710 0.978 0.979

Epoch GPU_mem box_loss cls_loss dfl_loss Instances

10/20 3.29G 1.037 0.5747 1.353 124

all 280 4710 0.982 0.981

<pytube.main.YouTube object: videoId=5lKsyMu6pAk>