ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ãããžã§ã¯ãã®äž»èŠã¹ããããç解ãã
ã¯ããã«
Computer vision is a subfield of artificial intelligence (AI) that helps computers see and understand the world like humans do. It processes and analyzes images or videos to extract information, recognize patterns, and make decisions based on that data.
èŠããã ïŒ How to Do [Computer Vision](https://www.ultralytics.com/glossary/computer-vision-cv) Projects | A Step-by-Step Guide
ç©äœæ€åºãç»ååé¡ãã€ã³ã¹ã¿ã³ã¹ã»ã°ã¡ã³ããŒã·ã§ã³ãªã©ã®ã³ã³ãã¥ãŒã¿ã»ããžã§ã³æè¡ã¯ãèªåŸèµ°è¡ãã å»ççšç»ååŠçãŸã§ãããŸããŸãªç£æ¥ã«å¿çšããã䟡å€ããæŽå¯ãåŸãããšãã§ããã
ç¬èªã®ã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ ãããžã§ã¯ãã«åãçµãããšã¯ãã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ãç解ããããæ·±ãåŠã¶ããã®åªããæ¹æ³ã§ãããã ããã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ ãããžã§ã¯ãã¯å€ãã®æé ã§æ§æãããå Žåããããæåã¯æ··ä¹±ããããã«æãããããããŸããããã®ã¬ã€ããèªã¿çµãããšãã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ ãããžã§ã¯ãã«é¢é£ããæé ãç解ã§ããããã«ãªããŸãããããžã§ã¯ãã®éå§ããçµäºãŸã§ãé ãè¿œã£ãŠèª¬æããåéšåãéèŠã§ããçç±ã説æããŸãããã£ããå§ããŠãã³ã³ãã¥ãŒã¿ãŒããžã§ã³ãããžã§ã¯ããæåãããŸãããã
ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ãããžã§ã¯ãã®æŠèŠ
ã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ ãããžã§ã¯ãã«é¢é£ããåã¹ãããã®è©³çŽ°ã«ã€ããŠèª¬æããåã«ãããã»ã¹å šäœãèŠãŠã¿ãŸããããä»æ¥ãã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ ãããžã§ã¯ããéå§ããå Žåã¯ã次ã®æé ãå®è¡ããŸãã
- æåªå äºé ã¯ããããžã§ã¯ãã®èŠä»¶ãç解ããããšã§ãã
- 次ã«ãã¢ãã«ã®ãã¬ãŒãã³ã°ã«åœ¹ç«ã€ç»åãåéããæ£ç¢ºã«ã©ãã«ä»ãããŸãã
- 次ã«ãããŒã¿ãã¯ãªãŒãã³ã°ããæ¡åŒµææ³ãé©çšããŠãã¢ãã«ã®ãã¬ãŒãã³ã°çšã«æºåããŸãã
- ã¢ãã«ã®ãã¬ãŒãã³ã°åŸãã¢ãã«ã培åºçã«ãã¹ãããŠè©äŸ¡ããããŸããŸãªæ¡ä»¶äžã§äžè²«ããŠå®è¡ãããããšã確èªããŸãã
- æåŸã«ãã¢ãã«ãçŸå®äžçã«ãããã€ããæ°ããåææ å ±ãšãã£ãŒãããã¯ã«åºã¥ããŠæŽæ°ããŸãã
ããŠãäœãæåŸ ãããããããã£ããšããã§ããã£ããã¹ãããã«å ¥ãããããžã§ã¯ããåé²ãããŸãããã
ã¹ããã 1: ãããžã§ã¯ãã®ç®æšãå®çŸ©ãã
ã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ ãããžã§ã¯ãã®æåã®ã¹ãããã¯ã解決ããããšããŠããåé¡ãæ確ã«å®çŸ©ããããšã§ããæçµç®æšãç¥ãããšã¯ããœãªã¥ãŒã·ã§ã³ã®æ§ç¯ãéå§ããã®ã«åœ¹ç«ã¡ãŸããããã¯ããããžã§ã¯ãã®ç®çãã©ã®ã³ã³ãã¥ãŒã¿ãŒããžã§ã³ã¿ã¹ã¯ã«çŠç¹ãåœãŠãå¿ èŠããããã«çŽæ¥åœ±é¿ãããããã³ã³ãã¥ãŒã¿ãŒããžã§ã³ã«é¢ããŠã¯ç¹ã«åœãŠã¯ãŸããŸãã
ããã§ã¯ããããžã§ã¯ãã®ç®çãšããã®ç®çãéæããããã«äœ¿çšã§ããã³ã³ãã¥ãŒã¿ããžã§ã³ã¿ã¹ã¯ã®äŸãããã€ã玹ä»ããŸãïŒ
-
ç®çé«ééè·¯ã«ãããæ§ã ãªè»çš®ã®æµããç£èŠã»ç®¡çãã亀é管çãšå®å šæ§ãåäžãããã·ã¹ãã ãéçºããããšã
- ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ã¿ã¹ã¯ïŒç©äœæ€åºã¯ãå¹ççã«è€æ°ã®è»äž¡ã®äœçœ®ãç¹å®ãèå¥ããããã亀éç£èŠã«æé©ã§ãããã®ã¿ã¹ã¯ã«äžå¿ èŠãªè©³çŽ°ãæäŸããç»ååå²ãããèšç®è² è·ãäœããããé«éã§ãªã¢ã«ã¿ã€ã ã®è§£æãå¯èœã§ãã
-
ç®çå»çšç»åã¹ãã£ã³ã«ãããè «çã®æ£ç¢ºãªãã¯ã»ã«ã¬ãã«ã®èŒªéãæäŸããããšã«ãããæŸå°ç·ç§å»ãæ¯æŽããããŒã«ãéçºããããšã
- ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã®èª²é¡ïŒç»åã»ã°ã¡ã³ããŒã·ã§ã³ã¯ãè «çã®å€§ããã圢ç¶ãæ²»çèšç»ãè©äŸ¡ããããã«éèŠãªãæ£ç¢ºã§è©³çŽ°ãªå¢çãæäŸãããããå»çç»å蚺æã«é©ããŠããã
-
ç®çæ§ã ãªææžïŒè«æ±æžãé åæžãæ³çæžé¡ãªã©ïŒãåé¡ããããžã¿ã«ã·ã¹ãã ãæ§ç¯ããçµç¹ã®å¹çåãšææžã®æ€çŽ¢æ§ãåäžãããã
- Computer Vision Task: Image classification is ideal here as it handles one document at a time, without needing to consider the document's position in the image. This approach simplifies and accelerates the sorting process.
ã¹ããã1.5ïŒé©åãªã¢ãã«ãšãã¬ãŒãã³ã°æ¹æ³ã®éžæ
ãããžã§ã¯ãã®ç®çãšé©åãªã³ã³ãã¥ãŒã¿ããžã§ã³ã®ã¿ã¹ã¯ãç解ããåŸããããžã§ã¯ãã®ç®æšãå®çŸ©ããããã«äžå¯æ¬ ãªã®ã¯ãé©åãªã¢ãã«ãšãã¬ãŒãã³ã°ã¢ãããŒããéžæããããšã§ãã
ç®çã«ãã£ãŠãæåã«ã¢ãã«ãéžæããããã¹ããã2ã§åéã§ããããŒã¿ã確èªããåŸã«ã¢ãã«ãéžæããããéžæããŸããäŸãã°ããããžã§ã¯ããç¹å®ã®çš®é¡ã®ããŒã¿ã®å ¥æå¯èœæ§ã«å€§ããäŸåããŠãããšããŸãããã®å Žåãã¢ãã«ãéžæããåã«ãŸãããŒã¿ãåéããåæããæ¹ãçŸå®çãããããŸãããäžæ¹ãã¢ãã«ã®èŠä»¶ãæ確ã«ç解ããŠããå Žåã¯ããŸãã¢ãã«ãéžæãããã®ä»æ§ã«é©åããããŒã¿ãåéããããšãã§ããŸãã
Choosing between training from scratch or using transfer learning affects how you prepare your data. Training from scratch requires a diverse dataset to build the model's understanding from the ground up. Transfer learning, on the other hand, allows you to use a pre-trained model and adapt it with a smaller, more specific dataset. Also, choosing a specific model to train will determine how you need to prepare your data, such as resizing images or adding annotations, according to the model's specific requirements.
Note: When choosing a model, consider its deployment to ensure compatibility and performance. For example, lightweight models are ideal for edge computing due to their efficiency on resource-constrained devices. To learn more about the key points related to defining your project, read our guide on defining your project's goals and selecting the right model.
ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ãããžã§ã¯ãã®å®äœæ¥ã«å ¥ãåã«ããããã®è©³çŽ°ãæ確ã«ç解ããŠããããšãéèŠã§ããã¹ããã2ã«é²ãåã«ã以äžã®ããšãèæ ®ããŠãããå確èªããŠãã ããïŒ
- 解決ããããšããŠããåé¡ãæ確ã«å®çŸ©ããŸãã
- ãããžã§ã¯ãã®æçµç®æšã決ããã
- å¿ èŠãšãããç¹å®ã®ã³ã³ãã¥ãŒã¿ããžã§ã³ã¿ã¹ã¯ãç¹å®ããïŒäŸïŒç©äœæ€åºãç»ååé¡ãç»åã»ã°ã¡ã³ããŒã·ã§ã³ïŒã
- ãŒãããã¢ãã«ãèšç·Žãããã転移åŠç¿ã䜿ããã決ããã
- ã¿ã¹ã¯ãšé åã®ããŒãºã«åãããŠé©åãªã¢ãã«ãéžæããŠãã ããã
ã¹ããã2ïŒããŒã¿åéãšããŒã¿æ³šé
ã³ã³ãã¥ãŒã¿ããžã§ã³ã¢ãã«ã®å質ã¯ãããŒã¿ã»ããã®å質ã«äŸåããŸããã€ã³ã¿ãŒãããããç»åãéããããèªåã§æ®åœ±ããããæ¢åã®ããŒã¿ã»ããã䜿çšãããããããšãã§ããŸããé«å質ã®ããŒã¿ã»ãããããŠã³ããŒãããããã®çŽ æŽããããªãœãŒã¹ãããã€ã玹ä»ããŸãïŒGoogle Dataset Search EngineãUC Irvine Machine Learning RepositoryãKaggle Datasetsã
Ultralytics ã®ããã«ãæ§ã ãªããŒã¿ã»ããããã«ãã€ã³ã§ãµããŒãããŠããã©ã€ãã©ãªããããé«å質ãªããŒã¿ãç°¡åã«äœ¿ãå§ããããšãã§ããããããã®ã©ã€ãã©ãªã«ã¯ããã䜿ãããããŒã¿ã»ãããã·ãŒã ã¬ã¹ã«äœ¿ãããã®ãŠãŒãã£ãªãã£ãå«ãŸããŠããããšãå€ãããããžã§ã¯ãã®åæ段éã§ã®æéãšåŽåãå€§å¹ ã«ç¯çŽããããšãã§ããã
ãã ããç»åãåéããããèªåã§åçãæ®ã£ããããå Žåã¯ãããŒã¿ã«æ³šéãä»ããå¿ èŠããããŸããããŒã¿æ³šéã¯ãããŒã¿ã«ã©ãã«ãä»ããŠã¢ãã«ã«ç¥èãä»äžããããã»ã¹ã§ãã䜿çšããããŒã¿æ³šéã®çš®é¡ã¯ãç¹å®ã®ã³ã³ãã¥ãŒã¿ãŒ ããžã§ã³ææ³ã«ãã£ãŠç°ãªããŸãã次ã«äŸãããã€ã瀺ããŸãã
- ç»åã®åé¡ïŒç»åå šäœã1ã€ã®ã¯ã©ã¹ãšããŠã©ãã«ä»ãããŸãã
- Object Detection: You'll draw bounding boxes around each object in the image and label each box.
- Image Segmentation: You'll label each pixel in the image according to the object it belongs to, creating detailed object boundaries.
ããŒã¿åéãšæ³šéä»ãã¯ãæéã®ãããæäœæ¥ãšãªããã¢ãããŒã·ã§ã³ã»ããŒã«ã¯ããã®ããã»ã¹ã容æã«ããã®ã«åœ¹ç«ã€ã䟿å©ãªãªãŒãã³ã¢ãããŒã·ã§ã³ããŒã«ãããã€ã玹ä»ãããïŒLabeI StudioãCVATãLabelmeã
Step 3: Data Augmentation and Splitting Your Dataset
ç»åããŒã¿ãåéããã¢ãããŒã·ã§ã³ãè¡ã£ãåŸãããŒã¿ã®ãªãŒã°ã¡ã³ããŒã·ã§ã³ãè¡ãåã«ããŸãããŒã¿ã»ããããã¬ãŒãã³ã°ãæ€èšŒããã¹ãã»ããã«åå²ããããšãéèŠã§ãããªãŒã°ã¡ã³ããŒã·ã§ã³ã®åã«ããŒã¿ã»ãããåå²ããããšã¯ããªãªãžãã«ã®å€æŽãããŠããªãããŒã¿ã§ã¢ãã«ããã¹ããæ€èšŒããããã«éåžžã«éèŠã§ããããã¯ãã¢ãã«ãæ°ããæªç¥ã®ããŒã¿ã«å¯ŸããŠã©ã®çšåºŠæ±åããããæ£ç¢ºã«è©äŸ¡ããã®ã«åœ¹ç«ã¡ãŸãã
ããã§ã¯ããŒã¿ãåå²ããæ¹æ³ã説æããïŒ
- ãã¬ãŒãã³ã°ã»ããïŒã¢ãã«ã®åŠç¿ã«äœ¿çšããããããŒã¿ã®æã倧ããªéšåã§ãããéåžžã¯å šäœã®70ïœ80ïŒ ã§ããã
- Validation Set: Usually around 10-15% of your data; this set is used to tune hyperparameters and validate the model during training, helping to prevent overfitting.
- ãã¹ãã»ããïŒæ®ãã®10ïœ15ïŒ ã®ããŒã¿ããã¹ãã»ãããšããŠç¢ºä¿ããããã¬ãŒãã³ã°çµäºåŸãæªç¥ã®ããŒã¿ã«å¯Ÿããã¢ãã«ã®ããã©ãŒãã³ã¹ãè©äŸ¡ããããã«äœ¿çšããŸãã
ããŒã¿ãåå²ããåŸãç»åã®å転ãæ¡å€§çž®å°ãå転ãªã©ã®å€æãé©çšããŠããŒã¿ã»ããã®ãµã€ãºã人çºçã«å€§ããããããšã§ãããŒã¿ã®æ¡åŒµãè¡ãããšãã§ããŸããããŒã¿å¢åŒ·ã«ãããã¢ãã«ã¯ããªãšãŒã·ã§ã³ã«å¯ŸããŠããããã¹ãã«ãªããæªèŠã®ç»åã«å¯Ÿããããã©ãŒãã³ã¹ãåäžããŸãã
Libraries like OpenCV, Albumentations, and TensorFlow offer flexible augmentation functions that you can use. Additionally, some libraries, such as Ultralytics, have built-in augmentation settings directly within its model training function, simplifying the process.
ããŒã¿ãããããç解ããããã«ãMatplotlibã Seabornã®ãããªããŒã«ã䜿ã£ãŠç»åãèŠèŠåãããã®ååžãç¹åŸŽãåæããããšãã§ããŸããããŒã¿ãèŠèŠåããããšã§ããã¿ãŒã³ãç°åžžãå¢åŒ·æè¡ã®æå¹æ§ãç¹å®ããããšãã§ããŸãããŸããã»ãã³ãã£ãã¯æ€çŽ¢ãSQLã¯ãšãªããã¯ãã«é¡äŒŒæ§æ€çŽ¢ã§ã³ã³ãã¥ãŒã¿ããžã§ã³ããŒã¿ã»ãããæ¢çŽ¢ããããã®ããŒã«ãUltralytics Explorerã䜿çšããããšãã§ããŸãã
ããŒã¿ãé©åã«ç解ããåå²ããè£åŒ·ããããšã§ãå®äžçã®ã¢ããªã±ãŒã·ã§ã³ã§åªããæ§èœãçºæ®ãããååã«èšç·Žãããæ€èšŒããããã¹ããããã¢ãã«ãéçºããããšãã§ããŸãã
ã¹ããã4ïŒã¢ãã«ã®ãã¬ãŒãã³ã°
ããŒã¿ã»ããããã¬ãŒãã³ã°ã®æºåãã§ããããå¿ èŠãªç°å¢ã®ã»ããã¢ãããããŒã¿ã»ããã®ç®¡çãã¢ãã«ã®ãã¬ãŒãã³ã°ã«éäžããããšãã§ããŸãã
ãŸããç°å¢ãæ£ããæ§æãããŠããããšã確èªããå¿ èŠããããŸããéåžžãããã«ã¯æ¬¡ã®ãã®ãå«ãŸããŸãã
- Installing essential libraries and frameworks like TensorFlow, PyTorch, or Ultralytics.
- GPU ã䜿çšããŠããå ŽåãCUDA ã cuDNN ã®ãããªã©ã€ãã©ãªãã€ã³ã¹ããŒã«ããããšã§ãGPU ã¢ã¯ã»ã©ã¬ãŒã·ã§ã³ãæå¹ã«ããåŠç¿ããã»ã¹ãé«éåããããšãã§ããŸãã
Then, you can load your training and validation datasets into your environment. Normalize and preprocess the data through resizing, format conversion, or augmentation. With your model selected, configure the layers and specify hyperparameters. Compile the model by setting the loss function, optimizer, and performance metrics.
Libraries like Ultralytics simplify the training process. You can start training by feeding data into the model with minimal code. These libraries handle weight adjustments, backpropagation, and validation automatically. They also offer tools to monitor progress and adjust hyperparameters easily. After training, save the model and its weights with a few commands.
å¹ççãªãã¬ãŒãã³ã°ã«ã¯ãé©åãªããŒã¿ã»ãã管çãäžå¯æ¬ ã§ããããšã念é ã«çœ®ãããšãéèŠã§ãããå€æŽã远跡ããåçŸæ§ã確ä¿ããããã«ãããŒã¿ã»ããã®ããŒãžã§ã³ç®¡çãè¡ããŸããããDVCïŒData Version ControlïŒã®ãããªããŒã«ã¯ã倧èŠæš¡ãªããŒã¿ã»ããã®ç®¡çã«åœ¹ç«ã¡ãŸãã
Step 5: Model Evaluation and Model Finetuning
It's important to assess your model's performance using various metrics and refine it to improve accuracy. Evaluating helps identify areas where the model excels and where it may need improvement. Fine-tuning ensures the model is optimized for the best possible performance.
- Performance Metrics: Use metrics like accuracy, precision, recall, and F1-score to evaluate your model's performance. These metrics provide insights into how well your model is making predictions.
-
ãã€ããŒãã©ã¡ãŒã¿ã®ãã¥ãŒãã³ã°ïŒã¢ãã«ã®æ§èœãæé©åããããã«ãã€ããŒãã©ã¡ãŒã¿ã調æŽãããã°ãªããæ¢çŽ¢ãã©ã³ãã æ¢çŽ¢ã®ãããªææ³ã¯ãæé©ãªãã€ããŒãã©ã¡ãŒã¿å€ãèŠã€ããã®ã«åœ¹ç«ã¡ãŸãã
-
Fine-Tuning: Make small adjustments to the model architecture or training process to enhance performance. This might involve tweaking learning rates, batch sizes, or other model parameters.
ã¹ããã6ïŒã¢ãã«ã®ãã¹ã
ãã®ã¹ãããã§ã¯ãã¢ãã«ããŸã£ããèŠãããšã®ãªãããŒã¿ã§ããŸãæ©èœããããšã確èªããé åã®æºåãæŽã£ãŠããããšã確èªããããšãã§ããŸããã¢ãã«ãã¹ããšã¢ãã«è©äŸ¡ã®éãã¯ãã¢ãã«ãå埩çã«æ¹åããã®ã§ã¯ãªããæçµçãªã¢ãã«ã®ããã©ãŒãã³ã¹ãæ€èšŒããããšã«éç¹ã眮ãããšã§ãã
ããããåé¡ã培åºçã«ãã¹ããããããã°ããããšãéèŠã§ãããã¬ãŒãã³ã°ãããªããŒã·ã§ã³ã§äœ¿çšããªãã£ãå¥ã®ãã¹ãããŒã¿ã»ããã§ã¢ãã«ããã¹ãããŸãããã®ããŒã¿ã»ããã¯ãã¢ãã«ã®ããã©ãŒãã³ã¹ãäžè²«ããŠä¿¡é Œã§ããããšã確èªããããã«ãå®äžçã®ã·ããªãªãè¡šãå¿ èŠããããŸãã
Also, address common problems such as overfitting, underfitting, and data leakage. Use techniques like cross-validation and anomaly detection to identify and fix these issues.
Step 7: Model Deployment
ã¢ãã«ã培åºçã«ãã¹ããããããããããããããããã€ããŸãããããã€ãšã¯ãã¢ãã«ãæ¬çªç°å¢ã§äœ¿çšã§ããããã«ããããšã§ãã以äžã¯ãã³ã³ãã¥ãŒã¿ããžã§ã³ã¢ãã«ããããã€ããæé ã§ãïŒ
-
ç°å¢ã®èšå®ïŒã¯ã©ãŠãããŒã¹ïŒAWSãGoogle CloudãAzureïŒã§ããããšããžããŒã¹ïŒããŒã«ã«ããã€ã¹ãIoTïŒã§ãããéžæããå±éãªãã·ã§ã³ã«å¿ èŠãªã€ã³ãã©ãæ§æããã
-
Exporting the Model: Export your model to the appropriate format (e.g., ONNX, TensorRT, CoreML for YOLO11) to ensure compatibility with your deployment platform.
- ã¢ãã«ããããã€ããAPIãããã¯ãšã³ããã€ã³ããèšå®ããã¢ããªã±ãŒã·ã§ã³ãšçµ±åããããšã§ã¢ãã«ããããã€ããŸãã
- ã¹ã±ãŒã©ããªãã£ã®ç¢ºä¿ïŒããŒããã©ã³ãµãŒããªãŒãã¹ã±ãŒãªã³ã°ã°ã«ãŒããã¢ãã¿ãªã³ã°ããŒã«ãå°å ¥ããŠãªãœãŒã¹ã管çããå¢å€§ããããŒã¿ãšãŠãŒã¶ãŒãªã¯ãšã¹ãã«å¯Ÿå¿ããã
ã¹ããã8ïŒã¢ãã¿ãªã³ã°ãã¡ã³ããã³ã¹ãææžå
ã¢ãã«ããããã€ãããããã®ããã©ãŒãã³ã¹ãç¶ç¶çã«ç£èŠããåé¡ãåŠçããããã«ã¢ãã«ãç¶æããå°æ¥ã®åç §ãšæ¹åã®ããã«ããã»ã¹å šäœãææžåããããšãéèŠã§ãã
ã¢ãã¿ãªã³ã°ããŒã«ã¯ãäž»èŠæ§èœææšïŒKPIïŒã远跡ããç°åžžã粟床ã®äœäžãæ€åºããã®ã«åœ¹ç«ã¡ãŸããã¢ãã«ãã¢ãã¿ãªã³ã°ããããšã§ãå ¥åããŒã¿ã®å€åã«ããã¢ãã«ã®æ§èœãæéãšãšãã«äœäžããã¢ãã«ã»ããªããã«æ°ã¥ãããšãã§ããŸãã粟床ãšåŠ¥åœæ§ãç¶æããããã«ãå®æçã«æŽæ°ãããããŒã¿ã§ã¢ãã«ãåãã¬ãŒãã³ã°ããŸãã
ã¢ãã¿ãªã³ã°ãšã¡ã³ããã³ã¹ã«å ããŠãææžåãéèŠã§ãããã¢ãã«ã»ã¢ãŒããã¯ãã£ããã¬ãŒãã³ã°æé ããã€ããŒãã©ã¡ãŒã¿ãããŒã¿ååŠçã¹ããããããã³ãããã€ã¡ã³ããšã¡ã³ããã³ã¹äžã«è¡ãããå€æŽãå«ããããã»ã¹å šäœã培åºçã«ææžåãããåªããææžåã¯åçŸæ§ãä¿èšŒããå°æ¥ã®ã¢ããããŒãããã©ãã«ã·ã¥ãŒãã£ã³ã°ã容æã«ããŸããã¢ãã«ãå¹æçã«ã¢ãã¿ãªã³ã°ããä¿å®ããææžåããããšã§ãã¢ãã«ã®ã©ã€ããµã€ã¯ã«ã«ããã£ãŠãæ£ç¢ºæ§ãä¿¡é Œæ§ã管çãããããç¶æããããšãã§ããŸãã
å°å瀟äŒãšã®é¢ãã
ã³ã³ãã¥ãŒã¿ããžã§ã³æ奜家ã®ã³ãã¥ããã£ãšã€ãªããããšã§ãã³ã³ãã¥ãŒã¿ããžã§ã³ãããžã§ã¯ãã®äœæ¥äžã«çŽé¢ããåé¡ã«èªä¿¡ãæã£ãŠåãçµãããšãã§ããŸããããã§ã¯ãåŠç¿ããã©ãã«ã·ã¥ãŒãã£ã³ã°ãå¹æçãªãããã¯ãŒã¯æ§ç¯ã®æ¹æ³ãã玹ä»ããŸãã
å°åè³æº
- GitHub Issues: Check out the YOLO11 GitHub repository and use the Issues tab to ask questions, report bugs, and suggest new features. The active community and maintainers are there to help with specific issues.
- Ultralytics DiscordãµãŒããŒïŒ Ultralytics Discord ãµãŒããŒã«åå ããŠãä»ã®ãŠãŒã¶ãŒãéçºè ãšäº€æµãããããµããŒããåããããæŽå¯ãå ±æãããããŸãããã
å ¬åŒææž
- Ultralytics YOLO11 Documentation: Explore the official YOLO11 documentation for detailed guides with helpful tips on different computer vision tasks and projects.
ãããã®ãªãœãŒã¹ã䜿çšããããšã§ã課é¡ãå æããã³ã³ãã¥ãŒã¿ããžã§ã³ã³ãã¥ããã£ã®ææ°ãã¬ã³ãããã¹ããã©ã¯ãã£ã¹ãåžžã«ææ¡ããããšãã§ããŸãã
ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ãããžã§ã¯ããä»ããå§ãããïŒ
ã³ã³ãã¥ãŒã¿ããžã§ã³ã®ãããžã§ã¯ãã«ææŠããããšã¯ããšããµã€ãã£ã³ã°ã§ããããã®ããããšã§ãããã®ã¬ã€ãã®ã¹ãããã«åŸãããšã§ãæåã®ããã®åŒ·åºãªåºç€ãç¯ãããšãã§ããŸããåã¹ãããã¯ãç®çãæºãããå®äžçã®ã·ããªãªã§ããŸãæ©èœãããœãªã¥ãŒã·ã§ã³ãéçºããããã«éåžžã«éèŠã§ããçµéšãç©ãã«ã€ãããããžã§ã¯ããæ¹åããããã®é«åºŠãªãã¯ããã¯ãããŒã«ãçºèŠã§ããã§ãããã奜å¥å¿ã倱ãããåŠã³ç¶ããæ°ããææ³ãã€ãããŒã·ã§ã³ãæ¢æ±ããŠãã ããïŒ
ããããã質å
ãããžã§ã¯ãã«é©ããã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ã¿ã¹ã¯ã®éžã³æ¹ã¯ïŒ
é©åãªã³ã³ãã¥ãŒã¿ããžã§ã³ã¿ã¹ã¯ãéžæãããã©ããã¯ããããžã§ã¯ãã®æçµç®æšã«ãã£ãŠç°ãªããŸããäŸãã°ã亀éç¶æ³ãç£èŠãããå Žåã¯ããªã¢ã«ã¿ã€ã ã§è€æ°ã®è»äž¡ã¿ã€ããç¹å®ã»èå¥ã§ããç©äœæ€åºãé©ããŠããŸããå»ççšç»ååŠçã§ã¯ãç»åã»ã°ã¡ã³ããŒã·ã§ã³ãè «çã®è©³çŽ°ãªå¢çãæäŸãã蚺æãæ²»çèšç»ã«åœ¹ç«ã¡ãŸããç©äœæ€åºãç»ååé¡ãã€ã³ã¹ã¿ã³ã¹ã»ã°ã¡ã³ããŒã·ã§ã³ãªã©ã®ç¹å®ã®ã¿ã¹ã¯ã«ã€ããŠè©³ããç¥ãã
ã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã®ãããžã§ã¯ãã«ãããŠããªãããŒã¿æ³šéãéèŠãªã®ã§ããããïŒ
ããŒã¿ã«æ³šéãä»ããããšã¯ãã¢ãã«ã«ãã¿ãŒã³ãèªèãããããã«äžå¯æ¬ ã§ããã泚éã®çš®é¡ã¯ã¿ã¹ã¯ã«ãã£ãŠç°ãªããŸãïŒ
- ç»åã®åé¡ïŒç»åå šäœã1ã€ã®ã¯ã©ã¹ãšããŠã©ãã«ä»ãã
- ãªããžã§ã¯ãã®æ€åºïŒãªããžã§ã¯ãã®åšãã«æãããããŠã³ãã£ã³ã°ããã¯ã¹ã
- ç»ååå²ïŒåç»çŽ ã¯ããããå±ãããªããžã§ã¯ãã«åŸã£ãŠã©ãã«ä»ããããã
Label StudioãCVATãLabelmeã®ãããªããŒã«ã¯ããã®ããã»ã¹ãæ¯æŽããããšãã§ããŸãã詳现ã«ã€ããŠã¯ãããŒã¿åéãšæ³šéã¬ã€ããåç §ããŠãã ããã
ããŒã¿ã»ãããå¹æçã«å¢åŒ·ã»åå²ããã«ã¯ãã©ã®ãããªæé ãèžãã°ããã®ã ãããïŒ
ãªãŒã°ã¡ã³ããŒã·ã§ã³ã®åã«ããŒã¿ã»ãããåå²ããããšã§ãå€æŽãããŠããªãå ã®ããŒã¿ã§ã®ã¢ãã«ã»ããã©ãŒãã³ã¹ãæ€èšŒããããšãã§ããŸãã以äžã®æé ã«åŸã£ãŠãã ããïŒ
- ãã¬ãŒãã³ã°ã»ããïŒããŒã¿ã®70ïœ80ïŒ ã
- Validation Set: 10-15% for hyperparameter tuning.
- ãã¹ãã»ããïŒæ®ãã®10ïœ15%ãæçµè©äŸ¡ã«äœ¿çšã
åå²åŸãå転ãã¹ã±ãŒãªã³ã°ãå転ãªã©ã®ããŒã¿æ¡åŒµæè¡ãé©çšããŠãããŒã¿ã»ããã®å€æ§æ§ãé«ãããAlbumentationsãOpenCVã®ãããªã©ã€ãã©ãªã圹ã«ç«ã€ãUltralytics ã䟿å©ãªãªãŒã°ã¡ã³ããŒã·ã§ã³èšå®ãçµã¿èŸŒãŸããŠããã
åŠç¿ããã³ã³ãã¥ãŒã¿ã»ããžã§ã³ã»ã¢ãã«ãé åçšã«ãšã¯ã¹ããŒãããã«ã¯ã©ãããã°ããã§ããïŒ
Exporting your model ensures compatibility with different deployment platforms. Ultralytics provides multiple formats, including ONNX, TensorRT, and CoreML. To export your YOLO11 model, follow this guide:
- ã䜿çšããã
export
é¢æ°ã«åžæããæžåŒãã©ã¡ãŒã¿ãæå®ããã - ãšã¯ã¹ããŒããããã¢ãã«ãå±éç°å¢ïŒãšããžããã€ã¹ãã¯ã©ãŠããªã©ïŒã®ä»æ§ã«é©åããŠããããšã確èªããã
詳ããã¯ãã¢ãã«ã»ãšã¯ã¹ããŒãã»ã¬ã€ããã芧ãã ããã
é åãããã³ã³ãã¥ãŒã¿ããžã§ã³ã¢ãã«ãç£èŠã»ç¶æããããã®ãã¹ããã©ã¯ãã£ã¹ãšã¯ïŒ
ã¢ãã«ã®é·æçãªæåã«ã¯ãç¶ç¶çãªã¢ãã¿ãªã³ã°ãšã¡ã³ããã³ã¹ãäžå¯æ¬ ã§ããäž»èŠæ¥çžŸè©äŸ¡ææšïŒKPIïŒã远跡ããç°åžžãæ€åºããããã®ããŒã«ãå°å ¥ãããã¢ãã«ã®ããªãããé²æ¢ããããã«ãæŽæ°ãããããŒã¿ã§ã¢ãã«ãå®æçã«åãã¬ãŒãã³ã°ãããã¢ãã«ã»ã¢ãŒããã¯ãã£ããã€ããŒãã©ã¡ãŒã¿ãå€æŽãå«ãããã»ã¹å šäœãææžåããåçŸæ§ã確ä¿ããå°æ¥ã®æŽæ°ã容æã«ããã詳ããã¯ãã¢ãã¿ãªã³ã°ãšã¡ã³ããã³ã¹ã®ã¬ã€ããã芧ãã ããã