215 questions
0
votes
0
answers
4
views
Running yolov4 with OpenVino - GPU
I'm trying to compile OpenVINO on my Windows system with GPU enabled.
code:
from openvino.runtime import Core
core = Core()
model = core.read(model_path)
compiled_model = core.compile_model(model, ...
0
votes
0
answers
59
views
Convert Yolov4-tiny model weights to tflite
I have trained a YoloV4-tiny object detecion model using darknet by referring this tutorial. My images are of size 1024x64.
I got yolov4-tiny_custom_training_last.weights as output.
I want to convert ...
- 13
0
votes
1
answer
245
views
How to modify YOLO object detection code for my project?
I am trying to modify YOLO code for my lane detection project but it does not work as I expected.
I modified darknet_images.py to not draw the bounding box but rather use the coordinates to draw the ...
0
votes
1
answer
113
views
YOLOv4-tiny Darknet: cannot generate results for video detection
I am trying to deploy the YOLOv4 tiny Darknet object detection model on an HPC.
I have trained and tested the YOLOv4-tiny model on Google Colab with no issues. Now I am trying to move the model to an ...
- 41
0
votes
0
answers
18
views
Using large files in the backend
I made an object detection website using Flask framework in the backend and am using yolov3.weights(240mb) file as a pre-trained model. I was just wondering what is the correct way of hosting these ...
1
vote
1
answer
86
views
Yolo makes one box for intersecting objects
Such a problem, I teach YOLO 4 for my son's cars, 1 car it finds easily, but if we start 2 and they drive next to each other and cross, for some reason it makes 1 big detection for 2 cars. Could the ...
- 11
0
votes
0
answers
14
views
Make file error while training YOLOv3-tiny image detection model
So im trying to train a custom yolov4-tiny model with google colab.
At the point Makefile i get this Error Message:
Compilation terminated due to -Wfatal-errors.
Makefile:162: recipe for target "...
- 21
1
vote
0
answers
104
views
How to resolve Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR) in Android Studio
I try to use a .tflite file in my Android Studio Application. This model is able to detect shape in an image. The objective is to create boundings boxes around the shape of interest. For that I made ...
- 11
0
votes
0
answers
49
views
people detection and counting using opencv and yolov4 code but the code is not showing anything
Im working in project for people detection and counting using opencv and yolov4 but the code is not showing anything when i run it and immediately closed , i dont know if wrote something wrong or am i ...
0
votes
0
answers
218
views
Object Tracking with YOLOv4 and DeepSORT: Merging Results from Two Videos
I'm working on a project where I use YOLOv4 for object detection and DeepSORT for tracking objects in videos. Initially, I process the first part of the video and successfully track objects.
Now, I ...
1
vote
2
answers
480
views
cuDNN Error: CUDNN_STATUS_BAD_PARAM. Can someone tell what does this mean, why this is occurring?
I am trying to train an object detection model with yolov4 using multiple GPUs (tesla T4), but between around 1000 or 2000 iterations it's giving the below error.
(next mAP calculation at 1214 ...
- 31
1
vote
1
answer
389
views
How to use Yolo as DLL after building Yolo as C++ DLL-file yolo_cpp_dll.dll
I have trained and built Darknet yolov4 with my custom dataset and made it work as darknet.exe file on windows with GPU. I run my exe with my custom parameters like
"`darknet.exe detector demo ...
- 19
0
votes
0
answers
96
views
Tflite Model for object detection with swift ios
I am using tflite model for object detection.
my model has input/output type float32.
could see lots of example in github having models type uint8.
I tried examples from github but input/output type ...
0
votes
1
answer
110
views
re train yolo4 weight with the .weights extension
I have trained yolo network weight with the ".weights" extension, and am trying to update it using darknet, and more dataset. Is there anyway I can use this weight and update it with more ...
- 1
1
vote
0
answers
80
views
Net.forward() gives right predictions in python but doesn't predict in c++
I am trying use yolov3 model to predict using opencv dnn module. It works perfectly in python but when I run in c++ (same configurations), it doesn't predict as the python code does. Neither there is ...
0
votes
1
answer
115
views
How to set the filters in the cfg file of Yolov4?
I was able to find tutorials in this field, such as the rule of filters:
filters = (classes + 5) * 3
But this only gives one number for the filters, but there are many filters in the cfg file!
with ...
0
votes
1
answer
194
views
How to convert YOLOv4 feature vectors to bounding boxes?
I implement object detection code for Yolov4 using tensorrt c++ pipeline. Although tensorrt c++ api is not user friendly at all, I managed to preprocess image and inference the model. I, however, have ...
- 13
0
votes
1
answer
337
views
Yolo version to run Oak D on CPU
In 2021 I was able to train a Yolov4-Tiny model to deploy on an Oak-D camera, and I was able to run the model on the camera on my PC using only CPU (I trained on Google Colab using GPU but for running ...
- 205
1
vote
1
answer
3k
views
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, ...
- 1,737
0
votes
2
answers
86
views
API Integration: IndexError: invalid index to scalar variable
I am trying to integrate my Yolov4 darknet customed trained model using fast api but am getting an IndexError: invalid index to scalar variable on console and Internal Server Error on Fastapi local ...
0
votes
0
answers
751
views
Yolov4 Weights into ONNX format
How can I convert Yolov4 Custom object-trained weights(best weights) into an ONNX format before starting the inferencing part with TensorRT?
After training my image(custom dataset) in Yolov4 using ...
1
vote
0
answers
86
views
Simple object count on frame with Yolo has error Not enough values to unpack
I'm trying to count the number of cars visible in a frame. Here is an excerpt:
while True:
# Read frame from video
ret, frame = cv2.VideoCapture(input_video).read()
if not ret:
...
- 11
1
vote
0
answers
276
views
Attempting to run yolov4.onnx model in ubuntu 20.04 docker, but getting protobuf error
Traceback (most recent call last): File "yolov4.py", line 342, in <module> main() File "yolov4.py", line 286, in main sess = rt.InferenceSession(args.model, so, providers=['...
- 11
1
vote
1
answer
106
views
Only the initial frame is being tracked in YOLOv4 with DeepSORT on Colab
I am currently trying to do object tracking with YOLOv4 and DeepSORT algorithm on Google Colab by utilizing this repository from the AIGuysCode.
Previously, everything was fine and the following ...
- 11
0
votes
0
answers
57
views
Multithreading on yolo4
I made this code finally work but I need to make it multithreaded because I am running it on a raspberry pi and runs really laggy. The pi is the 8gb ram pi4 model
This is the code, I only want to make ...
0
votes
1
answer
464
views
How to solve this error? RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
This is WongKinYiu / PyTorch_YOLOv4 problem. I found many solutions of this problem in YOLOv7, and no solution in YOLOv4. Since, the community here is more active. Thus, I try to ask here also.
This ...
- 143
0
votes
1
answer
673
views
Matlab add string variable as column in table
I'm trying to use YOLOv4 in MATLAB R2022b to carry out detections on all images in a directory, and append results to a text file.
I can append just the detection results to each line, but when I try ...
- 45
1
vote
0
answers
538
views
Difference between predictions of exported TensorRT engine and PyTorch pth models
Problem: inference results from deepstream and local inference do not match (using same png images).
While testing what percentage of predictions match between engine and pth models, only 26% matched ...
- 11
2
votes
2
answers
955
views
How can I improve my dataset for increased mAP in yolov4 object detection framework
I want to use Yolov4 object detector to detect LED matrices like the one in the attached picture. The goal of my project is to perform automated RoI of these types of LED matrices in vehicular ...
0
votes
2
answers
381
views
Solutions to 'make_dirs' problem in labelbox_json2yolo.py code
I'd like to convert my label file in *json to YOLO * txt with to class ('bsb','wsb') using the labelbox_json2yolo.py (https://github.com/ultralytics/JSON2YOLO/blob/master/labelbox_json2yolo.py) in ...
- 1,801
0
votes
2
answers
1k
views
Solution for : QCoreApplication::exec: The event loop is already running [closed]
So, I am a complete beginner in Python. This is my first ever application in this. I have these several files of Python classes. Using PyQT5 to make a desktop GUI object tracking app. When I am ...
- 118
0
votes
0
answers
25
views
YOLOv4 modification
I try to use yolov4 for my school project to detect certain fruit seeds, however, I have tried to add in some backgorund images into the dataset, and also try increase the max_batches as well as ...
- 1
0
votes
1
answer
797
views
TensorFlow custom loop training model: multi GPU is slower than a single GPU
I am using:
TensorFlow 2.6
CUDA 11.2
4 GPUs (GeForce RTX 3070)
TensorFlow uses Keras to define the training model, and multiple GPUs can accelerate normally. However, when using a custom loop ...
0
votes
1
answer
324
views
How can you implement transfer learning with Yolov4 on colab?
I am trying to follow this tutorial for using Yolov4 with transfer learning for a new object to detect: https://sandipanweb.wordpress.com/2022/01/17/custom-object-detection-with-transfer-learning-with-...
- 71
-1
votes
1
answer
70
views
what is the meaning of the line bboxes= utils.format_boxes(bboxes,height,weight)
I'm trying for object tracking using webcam using yolov4. I want to know the meaning of this line -> bboxes = utils.format_boxes(bboxes, original_h, original_w). I'm using https://github.com/...
1
vote
1
answer
743
views
In yolo Can I continue to training from final .weight with different class of images?
I want to train a few products for image classification in Yolo. Let's say I have trained with 10 products (means 10 classes) and saved the best file. Now I want to add some more data of other ...
2
votes
1
answer
377
views
How to convert Polygon format to YOLO forma
POLYGON ((799 1776, 799 2016, 490 2016, 490 1776, 799 1776))
This is the bounding box in POLYGON
i want this in YOLO v5 format
import logging
from pathlib import Path
import pandas as pd
from shapely....
0
votes
1
answer
513
views
yolov4 bounding box ext_output
Im using the ext_output parameter in yolov4 to get the coordinates of the bounding box in my image. Everything works fine, but im not sure how to reach this coordinates to crop the img. For example ...
- 63
0
votes
1
answer
341
views
Can Darknet YOLOv4 be used in Windows as a library in Pycharm without compil using CMake?
I need to use Darknet YOLOv4 in the Pycharm project on Windows. Can I use it directly without compiling using CMake and Visual Studio? Is there any way to use Darknet YOLOv4 as a library to detect ...
0
votes
0
answers
197
views
Multi-threading on absl.app.run to run yolov4 and tkinter
I'm working on a tensorflow yolov4 project, but to end it, I need to display the cv2 image into the tkinter interface.
#Import general library
import time
import datetime as dt
#Import tkinter ui ...
1
vote
1
answer
1k
views
How can I calculate metrics like mAP, F1 score and confusion matrix for Yolov4 for object detection?
I'm really new to this field of computer vision.
I have used this repo https://github.com/theAIGuysCode/yolov4-custom-functions.
system: Win 10
name: yolov4-gpu
dependencies:
python==3.7
pip
...
- 11
0
votes
1
answer
256
views
How to incorporate tflite-yolov4 in Android App ?(Kotlin)
Thanks for watch this post.I'm new to Android development.
If any information is missing for verification, please let me know.
I'm trying to incorporate yolov4.tflite in my App.
For confirmation of ...
- 35
0
votes
1
answer
264
views
YOLOv4-deepsort does not detect while running on Google Colab's GPU
I'm trying to do some object tracking on a video using Google Colab but I'm facing the issue below. Tracking is only done in the first frame of the video and not in the rest. I'm working with exactly ...
- 47
4
votes
4
answers
14k
views
How to load custom yolo v-7 trained model
How do I load a custom yolo v-7 model.
This is how I know to load a yolo v-5 model :
model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5/runs/train/exp15/weights/last.pt', force_reload=...
- 102
1
vote
0
answers
85
views
The size of byte buffer and the shape do not match. I'm having a error while implementing a tensorflow.lite model in android
I'm creating my first ML Android App. But I got this error
java.lang.IllegalArgumentException: The size of byte buffer and the shape do not match.
This is the code that I run on android studio.
...
0
votes
1
answer
781
views
can't open camera by index in Colab
I am using https://github.com/theAIGuysCode/yolov4-custom-functions this repository. I want to crop and save pictures while running on webcam. I'm using Colab. But when I run the following code:
!...
- 73
1
vote
0
answers
129
views
How to fill out the bounding boxes with a gaussian blur while streaming yolov4?
i am new to yolov4 and I have the following problem. I trained my yolov4 tiny network to detect faces and it runs on a jetson nano. I am using the following code to run the detection over my zed ...
- 11
1
vote
1
answer
2k
views
YOLOv4 custom model: is final.weights or last.weights better?
I'm training a custom YOLOv4 model using darknet, and at the end of training it produces two files: last.weights and final.weights. What is the difference between them, and which one should I use? ...
- 78.1k
0
votes
1
answer
303
views
yolov4-tiny on Colab. ConverterError: Variable constant folding is failed
I'm trying to convert the tensorflow weights to tensorflow lite. First of all, I converted.tflite from generating TensorFlow SavedModel. I do this in Google colab. Can I execute this code?
%cd /...
0
votes
0
answers
84
views
YoloV4 Darknet issue
I am trying to run ./darknet imtest data/eagle.jpg
on my Mac m1 terminal after installation of darknet
but it is showing me this -
'/opt/homebrew/opt/ffmpeg/lib/libavcodec.58.dylib' (no such file),
- 1