Stack Overflow
Stack Overflow

Questions tagged [yolov4]

75 questions
0
votes
1 answer

How do I understand whether yolov4 training is overfitting?

I'm training to make human detection with YOLOv4 in the custom dataset. I used this command to train the dataset: !./darknet detector train data/obj.data cfg/custom-yolov4-detector.cfg yolov4.conv.137 -dont_show -map At the end of the training, it…
John Amell
  • 13
  • 4
0
votes
0 answers

Trying to implement tensor flow and flutter Application for mp4 processing

My team and I have been trying to implement the Yolov4 model with flutter, all of the tutorials and information I have found seem to be about either live image processing or image processing. Would anyone have any idea how to either take the live…
lola Nolan
  • 1
0
votes
2 answers

Problem in conversion of .pb to tflite int8 for Coral Devboard (coral.ai)

I have done the training of model for object detection using yolov4 darkenet Alexyab and then converted the weight file generated to tensorflow lite using this repository https://github.com/hunglc007/tensorflow-yolov4-tflite and I was able to…
Yassa Fareed
  • 3
  • 1
0
votes
0 answers

Is there a way to do image detection and regression instead of classification

I need to detect specific insects on images and predict day of their lifecycle. It's hard to label each single insect, so we label groups of mostly uniform objects with day of their lifecycle (1-20). I want to use YOLO-v4 for detection of those…
Sergey Kulikov
  • 1
0
votes
0 answers

Run YOLOv4 tiny on raspberry pi

I need to run a custom pre-trained yolov4 tiny model. I cant seem to be able to install darknet-nnpcak , keep getting errors. not sure how to have it running on the raspberry pi3 . i tried installing darknet and running it but nothing. any clue?
Zuzu
  • 1
  • 1
0
votes
0 answers

Image labelling, How to annotate a picture which don't have an object but i should have its xml file as i explained in the question

I find a dataset which some of the pictures is not annotated but it has like this format in xml. But this another picture has an annotated object which look like this: Can any one tell me How and by which tools i can annotated a picture which…
user12579252
  • 11
  • 3
0
votes
0 answers

AttributeError: module 'cv2' has no attribute 'dnn'

I am trying to detect objects in a picture. I am using my trained weights and configuration file. The code runs completely fine on my laptop but it shows AttributeError: module 'cv2' has no attribute 'dnn' when I run it on my Raspberry Pi 4B. I have…
Tuba Siddiqui
  • 1
0
votes
0 answers

How can I see the graph of my training results in yolov4 if my colab stopped running when it finished in train?

I have train with yolov4 using Google Colab. But, when it finished, my Colab stopped running and I cannot see the charts of my training results. Is there any ways to see the graphs? Thanks. I follow this code for training:…
Nimas Ayu Setianingrum
  • 11
  • 2
0
votes
2 answers

How to train YoloV4 for custom object detection on grayscale images?

I am working with images of text which have diagrams in it. My images are basically black and white I do not see why I want colors in my images. I got some decent results with default settings but I want to test on grayscale Images too. I am using…
Deshwal
  • 1,382
  • 1
  • 6
  • 30
0
votes
0 answers

How to run YOLO on a output video in real time?

I know how to run YOLO on images, videos, and webcam but now, I want to run YOLOv4 on a live video after performing Perspective Transform. I am using a webcam to capture live video and I perform Perspective Transform on it using this code to get an…
Hassaan Awan
  • 3
  • 2
0
votes
1 answer

Which one is the correct YOLOv4 total loss function formula?

I couldn't find the total loss function in the main YOLOv4 paper. However, I found two differing formulas from two different papers (difference is highlighted/marked in the images below). Which formula is the correct default total loss formula for…
A. Parico
  • 326
  • 16
0
votes
0 answers

Error when run !make and !rm darknet on google colab

I am training a model using yolov4 and I use google colab for training. When I run %cd /content/drive/MyDrive/Colab Notebooks/Test_self_train_yolo_v4/darknet !rm darknet !make I got errors: /content/drive/MyDrive/Colab…
Hai Luu
  • 33
  • 6
0
votes
0 answers

YOLO: Wrong annotation: class_id = 6. But class_id should be [from 0 to 0]

I'm trying to train YOLO for object detection based on 8 classes by using Darknet. However, while training I receive the error Wrong annotation: class_id = 4. But class_id should be [from 0 to 0], file: data/obj/images/IMG_8943.txt IMG_8943.txt is…
Sunshine
  • 75
  • 7
0
votes
2 answers

How can I edit or remove the bounding box label text in YOLO (V4)?

I want to edit the bounding box label to show only the probability of detection and not the class label, How shall I do this? I found a file called image.c in darknet/src which I think is where my edits need to be made. But there are multiple…
varungupta
  • 125
  • 2
  • 7
0
votes
1 answer

absl.flags._exceptions.UnparsedFlagAccessError: Trying to access flag --tiny before flags were parsed

trying to build a webapp using yolov4,converted the yolov4 weights to tensorflow weights.Using tensorflow==2.3.0rc0 using 2 files helper2.py and app.py Please explain me what changes do i need to make in this code to run it properly helper2.py…
Varun Singh
  • 25
  • 2
  • 11
1 2
3
4 5