# YOLO **URL:** https://community.ultralytics.com/c/support/yolo/12.md?page=1 [Latest](https://community.ultralytics.com/latest.md) · [Categories](https://community.ultralytics.com/categories.md) · [Tags](https://community.ultralytics.com/tags.md) **Page:** 2 --- ## [Methods to Improve YOLOv11 Model Training Performance](https://community.ultralytics.com/t/methods-to-improve-yolov11-model-training-performance/1650)
**Author:** [@Grey\_Sky7](https://community.ultralytics.com/u/Grey_Sky7)\ **Replies:** 8\ **Last updated:** [November 20, 2025, 1:27pm UTC](https://community.ultralytics.com/t/methods-to-improve-yolov11-model-training-performance/1650 "2025-11-20T13:27:59Z")
Hey everyone, I have a question I hope you can help me with. I’m working on a project related to crop disease spot detection. Using the project dataset, which contains around 1,500 images, I trained my model. The results… --- ## [Model tune for Trained model](https://community.ultralytics.com/t/model-tune-for-trained-model/1612)
**Author:** [@peetey101](https://community.ultralytics.com/u/peetey101)\ **Replies:** 9\ **Last updated:** [November 16, 2025, 10:45pm UTC](https://community.ultralytics.com/t/model-tune-for-trained-model/1612 "2025-11-16T22:45:10Z")
from ultralytics import YOLO model = YOLO("/kaggle/input/convnext-yolo-100/pytorch/default/1/vit-100e-best.pt") search\_space = { "lr0": (1e-5, 1e-1), } # Tune hyperparameters on COCO8 for 30 epochs model.tune( d… --- ## [Standard epochs and imgsz for training YOLO11/YOLOv12 on VisDrone dataset](https://community.ultralytics.com/t/standard-epochs-and-imgsz-for-training-yolo11-yolov12-on-visdrone-dataset/1614)
**Author:** [@SwarnaReddy](https://community.ultralytics.com/u/SwarnaReddy)\ **Replies:** 7\ **Last updated:** [November 10, 2025, 2:09pm UTC](https://community.ultralytics.com/t/standard-epochs-and-imgsz-for-training-yolo11-yolov12-on-visdrone-dataset/1614 "2025-11-10T14:09:51Z")
I’m training YOLO11 and YOLOv12 models on the VisDrone dataset for small object detection. I know that for COCO dataset, the standards are: Epochs: 600 imgsz: 640 What are the recommended standard values for: Epoch… --- ## [How to reduce FP detections?](https://community.ultralytics.com/t/how-to-reduce-fp-detections/1629)
**Author:** [@Denis](https://community.ultralytics.com/u/Denis)\ **Replies:** 1\ **Last updated:** [November 10, 2025, 12:43am UTC](https://community.ultralytics.com/t/how-to-reduce-fp-detections/1629 "2025-11-10T00:43:44Z")
Hello. I train yolo to detect people. I get good metrics on the val subset, but on the production I came across FP detections of pillars, lanterns, elongated structures like people. How can such FP detections be fixed? --- ## [Modifying yolo architecture](https://community.ultralytics.com/t/modifying-yolo-architecture/1602)
**Author:** [@sisidipisi](https://community.ultralytics.com/u/sisidipisi)\ **Replies:** 4\ **Last updated:** [November 5, 2025, 1:04pm UTC](https://community.ultralytics.com/t/modifying-yolo-architecture/1602 "2025-11-05T13:04:14Z")
Hi everyone, I’m working on object and lane detection using YOLO, and I’ve been trying to choose a topic for my research project. We currently train two separate models for the two tasks, but I’m wondering if I could use… --- ## [My modified model show two different summaries](https://community.ultralytics.com/t/my-modified-model-show-two-different-summaries/1590)
**Author:** [@Mary\_C](https://community.ultralytics.com/u/Mary_C)\ **Replies:** 7\ **Last updated:** [November 1, 2025, 6:16pm UTC](https://community.ultralytics.com/t/my-modified-model-show-two-different-summaries/1590 "2025-11-01T18:16:47Z")
Please I very need to understand. I’m working on a modified yolo model but I faced this thing: I have different summary when start the training and when completed it: MM summary: 465 layers, 1,186,399 parameters, 1,186,… --- ## [Train model on new dataset](https://community.ultralytics.com/t/train-model-on-new-dataset/1589)
**Author:** [@Sergey\_Suslov](https://community.ultralytics.com/u/Sergey_Suslov)\ **Replies:** 4\ **Last updated:** [October 31, 2025, 1:12pm UTC](https://community.ultralytics.com/t/train-model-on-new-dataset/1589 "2025-10-31T13:12:21Z")
Hi, there! I have well trained model YOLO11n for passangers counting (in the bus). My model was trained on day light dataset (about 4000 pics) and works quite well. Now I need to train this model for night time detecti… --- ## [How to convert YOLO's CLS or OBB model to an OpenVINO model](https://community.ultralytics.com/t/how-to-convert-yolos-cls-or-obb-model-to-an-openvino-model/1158)
**Author:** [@MalcomYJ](https://community.ultralytics.com/u/MalcomYJ)\ **Replies:** 20\ **Last updated:** [October 24, 2025, 12:35am UTC](https://community.ultralytics.com/t/how-to-convert-yolos-cls-or-obb-model-to-an-openvino-model/1158 "2025-10-24T00:35:44Z")
from ultralytics import YOLO import os import sys model\_path = “punch\_obb.pt” Export the model model.export(format=“openvino”) I use the code to export a punch\_openvion\_model, but the result model end to error when… --- ## [Can I use SAHI Tiled Inference with YOLO11 Segmentation Model?](https://community.ultralytics.com/t/can-i-use-sahi-tiled-inference-with-yolo11-segmentation-model/1559)
**Author:** [@autkucakan](https://community.ultralytics.com/u/autkucakan)\ **Replies:** 1\ **Last updated:** [October 20, 2025, 4:03pm UTC](https://community.ultralytics.com/t/can-i-use-sahi-tiled-inference-with-yolo11-segmentation-model/1559 "2025-10-20T16:03:25Z")
I have a segmentation dataset for my project and I thought if I could use SAHI with the segmentation model because it’s looking beneficial to me but there is no source I could figure out that from. In docs I could only f… --- ## [Changing default padding](https://community.ultralytics.com/t/changing-default-padding/1552)
**Author:** [@Rodrigo\_M](https://community.ultralytics.com/u/Rodrigo_M)\ **Replies:** 5\ **Last updated:** [October 17, 2025, 11:28am UTC](https://community.ultralytics.com/t/changing-default-padding/1552 "2025-10-17T11:28:48Z")
Hi, can someone confirm if I’m correctly modifying the YOLO convolution module? I’m editing the ultralytics/nn/modules/conv.py file directly (inside the modules folder) to change how Conv blocks behave. Is that the prop… --- ## [YOLOv5 object detection performance boosting!](https://community.ultralytics.com/t/yolov5-object-detection-performance-boosting/1486)
**Author:** [@shaheembacker](https://community.ultralytics.com/u/shaheembacker)\ **Replies:** 1\ **Last updated:** [September 23, 2025, 12:23am UTC](https://community.ultralytics.com/t/yolov5-object-detection-performance-boosting/1486 "2025-09-23T00:23:38Z")
Hello, I am trying to develop an object detection model using yolov5s. The challenging object under consideration include cables. All other objects are massive in size, therefore easy to detect. But the cables are a bit… --- ## [Help with Yolo Pose 1.0 Export](https://community.ultralytics.com/t/help-with-yolo-pose-1-0-export/1464)
**Author:** [@Christoph\_Hesse](https://community.ultralytics.com/u/Christoph_Hesse)\ **Replies:** 8\ **Last updated:** [September 17, 2025, 12:49pm UTC](https://community.ultralytics.com/t/help-with-yolo-pose-1-0-export/1464 "2025-09-17T12:49:45Z")
Hi, i am experiencing an issue training a yolo dataset. I have only 5 keypoints (skeleton) and im exporting in YOLO 1.0 Pose (in CVAT). Labels format (4,3): 0 0.438824 0.522189 0.463846 0.347398 0.347192 0.348490 2 0.5… --- ## [GPU memory leak](https://community.ultralytics.com/t/gpu-memory-leak/967)
**Author:** [@MaestroV](https://community.ultralytics.com/u/MaestroV)\ **Replies:** 20\ **Last updated:** [September 9, 2025, 12:44pm UTC](https://community.ultralytics.com/t/gpu-memory-leak/967 "2025-09-09T12:44:13Z")
python NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4 NVIDIA GeForce RTX 4060 ultralytics==8.3.107 ultralytics-thop==2.0.14 ubuntu 24.04 torch==2.6.0 Hello. Please help me. Ye… --- ## [Balance Classes During Training - Yolov11](https://community.ultralytics.com/t/balance-classes-during-training-yolov11/692)
**Author:** [@speendo](https://community.ultralytics.com/u/speendo)\ **Replies:** 7\ **Last updated:** [August 29, 2025, 3:51pm UTC](https://community.ultralytics.com/t/balance-classes-during-training-yolov11/692 "2025-08-29T15:51:29Z")
Hello and thank you for this help forum. I try to train a yolov11 model with a certain subset of classes from the CityScapes dataset. As my results so far are only moderate, I would like to try another approach and use… --- ## [Ultralytics YOLOv11 QAT](https://community.ultralytics.com/t/ultralytics-yolov11-qat/926)
**Author:** [@srezas](https://community.ultralytics.com/u/srezas)\ **Replies:** 11\ **Last updated:** [August 29, 2025, 3:18pm UTC](https://community.ultralytics.com/t/ultralytics-yolov11-qat/926 "2025-08-29T15:18:51Z")
Hello everyone, I’m trying to perform Quantization-Aware Training (QAT) on YOLOv11 using Ultralytics. However, I’m facing an issue where my modifications to the model are being reset before training starts. Here’s the … --- ## [Larger obejcts detection boxes being cropped](https://community.ultralytics.com/t/larger-obejcts-detection-boxes-being-cropped/1379)
**Author:** [@yucath](https://community.ultralytics.com/u/yucath)\ **Replies:** 5\ **Last updated:** [August 20, 2025, 6:47pm UTC](https://community.ultralytics.com/t/larger-obejcts-detection-boxes-being-cropped/1379 "2025-08-20T18:47:27Z")
I have noticed that larger objects seem to be truncated at aroudn 950 pixels in both widhth and heght, no matter what resolution I run the inference at. Is that intentional or there is soem paramaeters that can be change… --- ## [Choose appropriate configurations for YOLO model exported to OpenVINO format](https://community.ultralytics.com/t/choose-appropriate-configurations-for-yolo-model-exported-to-openvino-format/1380)
**Author:** [@tommerfrancis](https://community.ultralytics.com/u/tommerfrancis)\ **Replies:** 5\ **Last updated:** [August 19, 2025, 1:34pm UTC](https://community.ultralytics.com/t/choose-appropriate-configurations-for-yolo-model-exported-to-openvino-format/1380 "2025-08-19T13:34:59Z")
Suppose that I have exported a custom model trained with YOLO12x to the OpenVINO format, then I have used this exported model to detect some kinds of objects in the videos, and my expectation is that the inference time f… --- ## [Unable to Submit License Inquiry via Website – Requesting Commercial License Information](https://community.ultralytics.com/t/unable-to-submit-license-inquiry-via-website-requesting-commercial-license-information/1219)
**Author:** [@takikomi](https://community.ultralytics.com/u/takikomi)\ **Replies:** 8\ **Last updated:** [August 19, 2025, 1:27pm UTC](https://community.ultralytics.com/t/unable-to-submit-license-inquiry-via-website-requesting-commercial-license-information/1219 "2025-08-19T13:27:44Z")
Hello, I’ve been trying to inquire about a commercial license for YOLO. About two weeks ago, I submitted a message via the contact form on the website, but I haven’t received a response. I also tried the license reque… --- ## [How does the training of a object detection dataset happen, with segmentation datasets, and how are the transformation handled](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351)
**Author:** [@Kallinteris-Andreas](https://community.ultralytics.com/u/Kallinteris-Andreas)\ **Replies:** 6\ **Last updated:** [August 18, 2025, 12:18pm UTC](https://community.ultralytics.com/t/how-does-the-training-of-a-object-detection-dataset-happen-with-segmentation-datasets-and-how-are-the-transformation-handled/1351 "2025-08-18T12:18:31Z")
In Ultralytics HUB the COCO dataset includes segmentation polygons, not bounding boxes, but it can be used to train object detection dataset are the polygon masks simply converted to bounding boxes during training how … --- ## [Extracting Wind Turbine Blade Tips as Keypoints](https://community.ultralytics.com/t/extracting-wind-turbine-blade-tips-as-keypoints/731)
**Author:** [@Nikelnack](https://community.ultralytics.com/u/Nikelnack)\ **Replies:** 5\ **Last updated:** [August 12, 2025, 1:08pm UTC](https://community.ultralytics.com/t/extracting-wind-turbine-blade-tips-as-keypoints/731 "2025-08-12T13:08:25Z")
My project is looking to estimate the yaw angle of a Wind Turbine relative to the camera. My idea was to extract the Blade Tips as Keypoints, which I can then use to calculate the excentricity of an elllipse formed by th… --- ## [SAM/SAM 2, how to generate feature embedings and run inference based on the embedings](https://community.ultralytics.com/t/sam-sam-2-how-to-generate-feature-embedings-and-run-inference-based-on-the-embedings/1275)
**Author:** [@Kallinteris-Andreas](https://community.ultralytics.com/u/Kallinteris-Andreas)\ **Replies:** 1\ **Last updated:** [July 26, 2025, 5:30pm UTC](https://community.ultralytics.com/t/sam-sam-2-how-to-generate-feature-embedings-and-run-inference-based-on-the-embedings/1275 "2025-07-26T17:30:23Z")
the inference process of SAM has 2 main stages, (1) Generated image embedding, (2) Generated mask based on prompt. (1) takes up most of the compute time, so it is a common practice to run (1) once and (2) multiple times… --- ## [Multiple model formats support for the Live Inference with Streamlit Application using Ultralytics YOLO11](https://community.ultralytics.com/t/multiple-model-formats-support-for-the-live-inference-with-streamlit-application-using-ultralytics-yolo11/1270)
**Author:** [@tommerfrancis](https://community.ultralytics.com/u/tommerfrancis)\ **Replies:** 3\ **Last updated:** [July 26, 2025, 8:51am UTC](https://community.ultralytics.com/t/multiple-model-formats-support-for-the-live-inference-with-streamlit-application-using-ultralytics-yolo11/1270 "2025-07-26T08:51:40Z")
I have known that the Live Inference with Streamlit Application using Ultralytics YOLO11 supports PyTorch models (.pt extenstion), but I would like that it also allows users to import other model formats, such as .onnx, o… --- ## [Speed up inference time for Live Inference with Streamlit Application using Ultralytics YOLO11](https://community.ultralytics.com/t/speed-up-inference-time-for-live-inference-with-streamlit-application-using-ultralytics-yolo11/1244)
**Author:** [@tommerfrancis](https://community.ultralytics.com/u/tommerfrancis)\ **Replies:** 9\ **Last updated:** [July 26, 2025, 12:41am UTC](https://community.ultralytics.com/t/speed-up-inference-time-for-live-inference-with-streamlit-application-using-ultralytics-yolo11/1244 "2025-07-26T00:41:24Z")
Suppose that I have a custom model trained with YOLO12x, then I have applied this model to the Live Inference with Streamlit Application using Ultralytics YOLO11 to detect some kinds of objects in the videos, but the inf… --- ## [Yolov8m pose - post-processing error after exporting to onnx and tensorrt](https://community.ultralytics.com/t/yolov8m-pose-post-processing-error-after-exporting-to-onnx-and-tensorrt/1255)
**Author:** [@Bastin\_Bajiyo\_Job](https://community.ultralytics.com/u/Bastin_Bajiyo_Job)\ **Replies:** 5\ **Last updated:** [July 25, 2025, 9:53am UTC](https://community.ultralytics.com/t/yolov8m-pose-post-processing-error-after-exporting-to-onnx-and-tensorrt/1255 "2025-07-25T09:53:36Z")
I was implementing a YOLOv8 pose estimation model for detecting keypoints (not hums pose), with both Python ONNX and C++ TensorRT implementations. The model should detect 10 objects with 4 keypoints each (40 total keypoi… --- ## [Yolo11 Object Detection on Jetson Orin Nano with Live Video](https://community.ultralytics.com/t/yolo11-object-detection-on-jetson-orin-nano-with-live-video/1221)
**Author:** [@xplanescientist](https://community.ultralytics.com/u/xplanescientist)\ **Replies:** 8\ **Last updated:** [July 22, 2025, 11:51am UTC](https://community.ultralytics.com/t/yolo11-object-detection-on-jetson-orin-nano-with-live-video/1221 "2025-07-22T11:51:26Z")
I have a Jetson Orin Nano devkit with JetPack 6.2.1. Yolo11 object detection with a photo or mp4 video functions properly. Now I’m trying to input live video from the CSI camera (CAM0), but it’s not working. See pytho… --- ## [Conversion between the number of epochs of YOLO12x and that of YOLO12n](https://community.ultralytics.com/t/conversion-between-the-number-of-epochs-of-yolo12x-and-that-of-yolo12n/1241)
**Author:** [@tommerfrancis](https://community.ultralytics.com/u/tommerfrancis)\ **Replies:** 1\ **Last updated:** [July 19, 2025, 10:00am UTC](https://community.ultralytics.com/t/conversion-between-the-number-of-epochs-of-yolo12x-and-that-of-yolo12n/1241 "2025-07-19T10:00:51Z")
Suppose that I trained a dataset using the YOLO12x model for 300 epochs and got the satisfied results, then at the moment, I want to train this dataset using the YOLO12n model, and thus how many training epochs should I … --- ## [Regarding to the Live Inference with Streamlit Application using Ultralytics YOLO11](https://community.ultralytics.com/t/regarding-to-the-live-inference-with-streamlit-application-using-ultralytics-yolo11/1230)
**Author:** [@tommerfrancis](https://community.ultralytics.com/u/tommerfrancis)\ **Replies:** 2\ **Last updated:** [July 16, 2025, 7:50am UTC](https://community.ultralytics.com/t/regarding-to-the-live-inference-with-streamlit-application-using-ultralytics-yolo11/1230 "2025-07-16T07:50:55Z")
I have known that the Live Inference with Streamlit Application using Ultralytics YOLO11 supports video files and webcam sources, but I would like that it also allows users to insert images, and thus what should I do to … --- ## [How does YOLOv8 reduce false recognition? How does it reduce false recognition of similar objects](https://community.ultralytics.com/t/how-does-yolov8-reduce-false-recognition-how-does-it-reduce-false-recognition-of-similar-objects/1143)
**Author:** [@hhhFuture](https://community.ultralytics.com/u/hhhFuture)\ **Replies:** 14\ **Last updated:** [July 12, 2025, 2:17pm UTC](https://community.ultralytics.com/t/how-does-yolov8-reduce-false-recognition-how-does-it-reduce-false-recognition-of-similar-objects/1143 "2025-07-12T14:17:57Z")
Hello everyone, I’d like to ask a question and hope to receive your help. Thank you all in advance. When recognizing the scissors gesture, I had 50,000 samples and obtained a dataset of 150,000 samples by rotating ±90°. … --- ## [YOLOv11 ONNX Export Error with Batch \> 1 and NMS](https://community.ultralytics.com/t/yolov11-onnx-export-error-with-batch-1-and-nms/1207)
**Author:** [@M\_M\_M](https://community.ultralytics.com/u/M_M_M)\ **Replies:** 6\ **Last updated:** [July 10, 2025, 3:37pm UTC](https://community.ultralytics.com/t/yolov11-onnx-export-error-with-batch-1-and-nms/1207 "2025-07-10T15:37:25Z")
Environment: Ubuntu 22.04 Python 3.10.12 Ultralytics 8.3.155 Executing: yolo export format='onnx' dynamic=True model=yolo11n.pt nms=True yolo predict task=segment source=images batch=4 model=yolo11n.onnx Expected B… --- ## [Ultralytics 8.3.6 with torch==2.6.0 + torchvision==0.21.0 is silently falling back to CPU during model.predict() despite .to('cuda') and device=0](https://community.ultralytics.com/t/ultralytics-8-3-6-with-torch-2-6-0-torchvision-0-21-0-is-silently-falling-back-to-cpu-during-model-predict-despite-to-cuda-and-device-0/1211)
**Author:** [@Paramesh\_Ganireddy](https://community.ultralytics.com/u/Paramesh_Ganireddy)\ **Replies:** 3\ **Last updated:** [July 10, 2025, 1:51pm UTC](https://community.ultralytics.com/t/ultralytics-8-3-6-with-torch-2-6-0-torchvision-0-21-0-is-silently-falling-back-to-cpu-during-model-predict-despite-to-cuda-and-device-0/1211 "2025-07-10T13:51:19Z")
from ultralytics import YOLO results = model.predict( source=“VIDEO.mp4”, device=0, stream=True, save=True, show=True ) [Previous page](https://community.ultralytics.com/c/support/yolo/12.md) [Next page](https://community.ultralytics.com/c/support/yolo/12.md?page=2)