591 questions
0
votes
0
answers
30
views
PyTorch issue when trying to load the YOLOv5 model
I am using OpenCV and the YOLOv5 model as part of a larger project and wrote some basic code:
import torch
import cv2
device = torch.device("cpu")
model = torch.hub.load("ultralytics/...
0
votes
0
answers
47
views
adding attention mechanism to yolo algorithm
i'm trying to add Cbam attention mechanism to yolo architecture
this is my Cbam implementation added to common.py
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
...
0
votes
1
answer
105
views
Converting pt to tflite in Python
I am currently using Python 3.12.6, but I have noticed that there are limited TensorFlow package versions available for this newer version.
I would like to know which packages and versions are ...
1
vote
0
answers
29
views
Custom dataset with YOLOv5
I'm new to YOLOv5 and V8, I'm already having issues with Yolov5 and I wanted to train with v8 just to compare. I had different sets of toilets (4 classes, already annotated via Roboflow) that I merged ...
0
votes
0
answers
42
views
Ultralytics YOLO Error: Incompatibility with PyTorch and CUDA Versions
I'm encountering a persistent issue while running YOLOv5 using Ultralytics with the following basic code:
import torch
# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)...
0
votes
1
answer
63
views
How can I convert YOLOv5 to tflite MICRO using 8-Bit Quantization?
I successfully converted YOLOv5 Nano to tflite using a representative set of images
(Ultralytics export also does that). I can see the scale and zero point for the input and it is fine. I can also ask ...
1
vote
0
answers
36
views
yolov5 trained my data set on my laptop how I send it to my Raspberry Pi
I got yolov5 and trained my data set on my laptop now I want to send it to my Raspberry Pi 4b module for work. how I do it
direct copy to raspberry pi but not working
(myenv) h@raspberrypi:~/project/...
0
votes
0
answers
38
views
Slow Camera with YoloV5
I’m working with a Jetson Orin Nano and a Raspberry Pi Camera Module V2, aiming to run YOLOv5 for real-time image processing. I’ve tried using the following code, but the camera feed is extremely slow ...
0
votes
1
answer
156
views
YOLOv5 Class Imbalance and Overfitting Issues
I’m working on a seat belt and mobile phone detection system using YOLOv5s to detect the windshield, driver, passenger, seat belt, and mobile phone. My dataset has a class imbalance issue since not ...
0
votes
0
answers
76
views
How can I screen capture under a blur overlay?
When using PyQt5 and YOLOv5 to detect humans and blur them with an overlay, a flickering issue arises. This happens because the screen capture picks up the overlay itself. The script then mistakenly ...
0
votes
0
answers
51
views
Tesseract OCR fails to correctly recognize text in vehicle license plates
Question:
I am working on a project to detect and recognize vehicle license plates using YOLOv5, OpenCV, and Tesseract OCR. My script successfully detects the vehicle and isolates the license plate ...
0
votes
0
answers
171
views
Ultralytics YOLOv8 training failed for torch.cat(): expected a non-empty list of Tensors
I am using Ultralytics for YOLOv8. I am getting this error while training the model:
RuntimeError: torch.cat(): expected a non-empty list of Tensors
The images are already converted to 500x500, ...
0
votes
0
answers
84
views
Object Counting Across Frames in YOLOv5 Video Detection
I'm working on an object detection project using YOLOv5 in Python, where I need to detect and count bicycles and motorcycles in a video as they cross a vertical line in the middle of the frame. ...
-1
votes
1
answer
55
views
runs\train\exp10 is not a directory
I am trying to train a YoloV5 model with my custom data on my own computer, but I keep getting this error:
train: weights=yolov5s.pt, cfg=models/yolov5s.yaml, data=data.yaml, hyp=data\hyps\hyp.scratch-...
0
votes
1
answer
57
views
yolo5 Unity3D BarraCUDA
Is there documentation for what yolo-v5's output is?
We (or I) are trying to use YOLOv5 (for now) to detect faces in real time from an HDMI input.
Cartoon faces, video game faces, natural faces - all ...
0
votes
1
answer
99
views
How do I work with the result of model.predict in yolov8 with a webcam?
I have my webcam set up to be the input for my model.predict() function and want to trigger some code if the function detects a certain object. The model.predict() function does not seem to ever ...
0
votes
0
answers
74
views
onnxruntime::qnn::QnnModel::ParseGraphInputOrOutput Dynamic shape is not supported yet, for output: /model.12/Concat_output_0_QuantizeLinear_Output
I am trying to run yolov5 onnx model in Qualcomm NPU using OnnxRuntime QNN execution provider.
I am getting this error while intializing the sesssion. ort.InferenceSession()
ParseGraphInputOrOutput ...
0
votes
0
answers
26
views
I need a way to upload a newly generated image in a the FLET app
Goal: be able to upload an image in the flet app, show the image in-app along with the predictions, and then show the annotated image with bounding boxes based on the prediction.
I've trained the ...
0
votes
0
answers
22
views
Mouse Movement and Clicks Not Working Correctly in Game Using YOLOv5 and PyWin32
I am working on an AI project to detect and shoot objects in the game Aimlabs using a YOLOv5 model. The code works fine when the game is paused, but it does not move the mouse accurately when the game ...
0
votes
1
answer
62
views
Error loading .jpg images in tkinter window using tk.PhotoImage
Question:
I am working on a tkinter application where I need to display images in the GUI. While loading .png images works perfectly fine, I am encountering difficulties when attempting to load .jpg ...
1
vote
1
answer
177
views
How to get bounding box labels and it's format in Yolo 3D
I have had implemented Yolo 3D model in my workspace, and it is working fine. I am getting an image as an output. So I would like to know where I can get the labels for my 3D bounding boxes. And I ...
0
votes
0
answers
43
views
Run Yolov5 model in Max engine using Mojo
Issues in loading and compiling the yolov5s.torchscript model in MAX Engine using Mojo.
Referred the documents at https://docs.modular.com/max/mojo/get-started and https://docs.modular.com/max/model-...
0
votes
0
answers
66
views
COMET ERROR: Unable to verify Comet API key at this time
#@title Select YOLOv5 🚀 logger {run: 'auto'}
logger = 'Comet' #@param \['Comet', 'ClearML', 'TensorBoard'\]
if logger == 'Comet':
%pip install -q comet_ml
import comet_ml; comet_ml.init()
elif ...
0
votes
0
answers
26
views
Yolov5 trained with bdd100k: AttributeError: 'Namespace' object has no attribute 'label_smoothing'
I am trying to create model with yolov5, based on bdd100k dataset, images cached, last success i got is: "AutoAnchor: 4.96 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a ...
0
votes
0
answers
89
views
How do I the fix "Cache may be out of date" error?
I created a training model successfully with YOLOv5s as a pretrained model and ten images as a dataset.
But I got into trouble when I went to make a second model with another ten images.
My first and ...
0
votes
0
answers
41
views
YOLOv5 ptl model inference results out of bounds of classes array
I have a yolov5 model that I converted into ptl using the code below
import torch
from torch.utils.mobile_optimizer import optimize_for_mobile
torchscript_model = "best.torchscript"
...
0
votes
0
answers
41
views
Offsets and label creation for object detection training/inference
I am new to object detection. I know that in object detection anchors are used for detecting objects in the feature map using offsets instead of predicting actual location of the object w.r.t input ...
0
votes
0
answers
89
views
No bounding boxes generated for a trained YOLO NAS model using Pytorch
I have trained a YOLO NAS-s format model for image detection in a retail store using pytorch. I trained my model for approx ~8000 images, 20 epochs as per below training code. Due to memory issues my ...
0
votes
0
answers
42
views
Get_problem while cloning yolov5
ERROR: Cannot uninstall 'TBB'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.
get the error each ...
0
votes
1
answer
250
views
yolo training with low precision and low map
I am using YOLOv5 to train a model to recognize cards in a card game. I started with the pre-trained model yolov5s.pt and my dataset consists of 138 images. However, the accuracy and mAP are very low ...
0
votes
0
answers
23
views
How can I calculate the sizes of the bounding boxes for a particular YOLOv5 class?
I have n classes that the Ultralytics YOLOv5 model is currently detecting. How can I get the average of the sizes of the bounding boxes for one particular class?
I tried back calculating the bounding ...
0
votes
0
answers
142
views
Why is the YOLOv5 model performing differently in detect.py and val.py?
I trained the Ultralytics YOLOv5 model, https://github.com/ultralytics/yolov5/, on my custom dataset. Interestingly, when I run this trained model through the file val.py, the results I get do not ...
0
votes
1
answer
111
views
ModuleNotFound Error in Yolov5 using custom weights
I'm currently learning object detection using a custom trained module in YoloV5. I trained the dataset locally and that operation ran just fine but when i tried to implement the custom weights it gave ...
0
votes
0
answers
27
views
Image processing with YOLOv5
I'm working on an image processing project. I was working with the YOLO model, but the error I got was that the libraries in the requirements.txt file in YOLOv5 are conflicting with each other. Even ...
0
votes
0
answers
36
views
How to pass arguments to fine-tuned yolov5 model?
I have some fine tuned weights, and I am trying to apply the model to an image, but I want to hide the image label and confidence interval. When I am running the model from the command line I would ...
0
votes
0
answers
57
views
Yolov5 transfer learning - runs/train/exp and runs/val/exp problem
I did transfer learning with yolov5 and obtained weights and everything. The val_labels are marked with bounding box crtly but val_pred doesnt have a bounding box at all . nothing is present in ...
0
votes
0
answers
89
views
Yolov5 Custom Model Deployment in Raspberry Pi 3
I want to deploy my pre-trained Yolov5 Custom object detection model where my datasets had used. But I did not know how to deploy this model and test it into raspberry pi 3. I did not find any ...
0
votes
1
answer
244
views
I am using the YOLOv5 model provided by Ultralytics in PyTorch. How can I see which images the model is struggling with?
This is the YOLOv5 implementation I am talking about and this is the file I am using to test the model.
For some classes, it performing decently enough. However, for the rest of the classes, it is not ...
0
votes
1
answer
137
views
Correct way to tag objects with YOLOv5
I need to tag a series of images for sewing detection on fabric. I work with the YOLOv5 algorithm.
The problem I have is that it is not clear to me what should be the optimal way to label these ...
0
votes
0
answers
47
views
Is there a way to get the images where the Ultralytics YOLOv5 model missed the object?
I am using the version developed by Ultralytics (https://github.com/ultralytics/yolov5) for my application. It is performing well but is, obviously, not correct everytime.
Is there a way to see the ...
0
votes
0
answers
54
views
I need to share a list between these 2 functions that are being called in different threads
I want to use the list frame_buffer in both functions update_frame and get_stream these 2 fucntions are called in different threads but I am using a lock object so I am stumped by this please help.
...
0
votes
0
answers
225
views
Object detection bounding boxes using yolov5s with onnx on ml.net
I know its been a while. I am using yolov5 with MAUI as well but in an ONNX form. I am having no trouble in getting the predictions but issue is with the bounding boxes they are way off.
my model has ...
0
votes
0
answers
107
views
How to Convert 16:9 Video to 9:16 Ratio While Ensuring Speaker Presence in Frame?
I am tried so many time to figure out the problem in detecting the face and also it's not so smooth enough to like other tools out there.
So basically I am using python and Yolo in this project but I ...
0
votes
0
answers
38
views
yolov5 can't find images for training
!cd yolov5 && python train.py --img 320 --batch 16 --epochs 1500 --data dataset.yml --weights yolov5s.pt --workers 2
This is for training the yolov5 model to recognize the labels awake and ...
1
vote
0
answers
106
views
yolov5 running custom model, do I have a training problem?
I have this dataset from Roboflow and I want to train it and run it locally. I have trained it and all looks good but when I run the py script in terminal it gives me like errors.
It works when I
...
0
votes
0
answers
73
views
attributeError when loading yolov5s from torch hub
I am trying to build a driver drowsiness detection model. I wanted to load in the yolov5s ultralytics implementation using torch hub but I am getting an error.
The code I wrote:
model=torch.hub.load('...
0
votes
0
answers
197
views
yolo v5 export to torchscript: how to generate constants.pkl
i cloned yolo5 and
setted up an virtenv
pip install -r requirements.txt
python export.py --weights yolov5s-seg.pt --include torchscript --img 640 --device cpu
all went fine: TorchScript: export ...
0
votes
0
answers
26
views
I have question about the meanings of words coming out during training YOLOv7(WongKinYiu)
After training with YOLOv7(WongKinYiu), I realize that in the results, it has box value and I have no idea how this value is calculated.
Is it some kind of IoU loss?
0
votes
0
answers
198
views
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory when running command to train yolov5 on custom data
the command
!cd yolov5 && python train.py --img 320 --batch 16 --epochs 5 --data dataset.yml --weights yolov5s.pt --workers 2
i get the error below when i run the command above
train: weights=...
-1
votes
1
answer
271
views
YoloV5 hangs in a container
I'm stuck on a problem combining docker, python (3.11) and YOLOV5.
I have reduced the problem to the the following script, which works as expected when debugging under windows 10, but hangs (output ...