Stack Overflow
Stack Overflow

Questions tagged [yolov7]

You Only Look Once (YOLO) is a real-time object detection system written in C. Use this tag for questions about YOLO version 7.

You Only Look Once (YOLO) is a real-time object detection system developed for high speed object detection within images.

87 questions
4
votes
2 answers

How can I convert a YOLOv8s model to coreML model using a custom dataset?

I have trained a YOLOv8 object detection model using a custom dataset, and I want to convert it to a Core ML model so that I can use it on iOS. After exporting the model, I have a converted model to core ml, but I need the coordinates or boxes of…
Dhiman Das
  • 45
  • 6
3
votes
4 answers

I got NaN for all losses while training YOLOv8 model

I am training yolov8 model on cuda using this code : from ultralytics import YOLO import torch import os os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training) results =…
Mohamed Abu ElNasr
  • 41
  • 3
2
votes
0 answers

YOLOv7 does not working well after adding the Early Stopping

After adding the earlystopping function, the training result is weird. There are full of zeros and all the classes do not train well. Why does this happened? Refer (Early Stopping): Code: Dataset: I have changing some other dataset to test either…
Candy
  • 21
  • 3
2
votes
0 answers

Is it possible to merge two Yolov7 models to inference in just one instance?

I have two Yolo v7 models (*.pt weights) that I need to merge: Pose estimation https://github.com/RizwanMunawar/yolov7-pose-estimation Model that detect helmets Is it possible to create a model from the weights of the models I am talking about? I…
Adrián Rodríguez
  • 21
  • 2
2
votes
1 answer

YoloV8 Segmentation mask problem (masks looks 2 parts but outputs only first part)

My code is as shown below: import numpy as np from ultralytics import YOLO from PIL import Image import cv2 from google.colab.patches import cv2_imshow model = YOLO("yolov8n-seg.pt") results = model.predict("payload.jpeg") masks =…
jawamba
  • 21
  • 4
2
votes
2 answers

Is there any limit to detected objects in YOLOv7?

I have trained a YOLOv7 model using the Roboflow notebook and my own dataset: https://colab.research.google.com/drive/1X9A8odmK4k6l26NDviiT6dd6TgR-piOa I worked with these notebooks before, but never had images with more than 100 objects, but now, I…
juan carlos
  • 184
  • 1
  • 11
2
votes
2 answers

How to increase processing speed of python code through parallelization

I currently have a sequential code with the following parts (all parts are properly encapsulated and isolated in class methods and so on): Frame capture from network stream with opencv VideoCapture Processing of the image with yolov7 through…
Jordi Fuentes
  • 47
  • 5
2
votes
1 answer

what are keypoints in yolov7 pose?

I am trying to understad the keypoint output of the yolov7, but I didn't find enough information about that. I have the following output: array([ 0, 0, 430.44, 476.19, 243.75, 840, 0.94348, 402.75, …
Tlaloc-ES
  • 4,825
  • 7
  • 38
  • 84
1
vote
0 answers

Unable to use exported YOLOv7 to TensorFlow Lite, in ObjectDetector

I have a YOLOv7 model trained on my custom dataset. I exported the model to TensorFlow lite successfully and was able to use it for inference in Python. But when I try to use the same model in Android, using the object detection project with…
mmheydari97
  • 31
  • 4
1
vote
0 answers

GPU out of memory in PyTorch with Ubuntu 20.04

I'm trying to translate yolov7 model using torch to '.ts' file using the next code: gc.collect() torch.cuda.empty_cache() traced_model = torch.jit.trace(model, torch.empty([10, 3, 768, 1280]).half().to(self.device)) trt_script_module =…
Victor Rosario
  • 11
  • 2
1
vote
1 answer

How can i use Tensorflows official models from the TF Model Garden?

Through the TensorFlow Model Garden TensorFlow provides official models. However it isn't really clear, how you can use the models. Let's say I would want to use TensorFlows Version of YOLOv7, how could I do that?
Only-A-User
  • 41
  • 1
  • 4
1
vote
1 answer

YOLO label format, when images doesn't have bounding box

If an image (abc.jpg) doesn't have any bounding box, how should look its corresponding label file (abc.txt)? The regular label format is: label x_center/width y_center/height width/image_width, height/image_height.
Michael D
  • 1,711
  • 4
  • 23
  • 38
1
vote
0 answers

Add New Classes to Yolov7 Object Detection Model

I have been trying to apply transfer learning technique on Yolov7 (https://github.com/WongKinYiu/yolov7) object detection model which in simpler word adding new classes into the model. I have been following the tutorial and instruction from…
HAO TEE
  • 11
  • 1
1
vote
0 answers

libpng warning: iCCP: known incorrect sRGB profile occurs when i m training neural network

I am training a neural network for custom dataset which has ~7000 images with official yolov7 , while training the model using !python train.py --workers 1 --device 0 --batch-size 4 --epochs 100 --img 640 --data data/custom.yaml --hyp…
Roopam Maurya
  • 11
  • 1
1
vote
0 answers

Tensorboard error while training with Yolov7

I'm trying to use tensorboard according to training instructions of yolov7 to see the results as I'm training. It said to run this command to view it at http://localhost:6006/ However, I get this error when I run it: (yolov7)…
Mike Azatov
  • 402
  • 6
  • 22
1
2 3 4 5 6