Questions tagged [yolov4]
75 questions
0
votes
0 answers
iou_loss and avg iou_loss remain 0.00 constantly YOLOv4
I am using YOLOv4 to train only one class which is traffic light. Here is some setting for my .cfg file. The iou loss function used is default one, ciou.
[net]
# Testing
#batch=1
#subdivisions=1
#…
![](../../users/profiles/15156875.webp)
Lasven Loke
- 35
- 5
0
votes
1 answer
BeagleBone AI OpenCL
I have a project to run yolov4 on BeagleBone AI. To run this CNN I needed to install Darknet using following guide: https://iblog.isowa.io/2020/04/29/darknet-in-opencl-on-beagleboard-ai/ . I suggest that installation held good.
The key is that with…
![](../../users/profiles/14387309.webp)
Daniil Maltsev
- 13
- 2
0
votes
0 answers
darknet_images.py doesn't detect any objects. Darknet YOLOv4
So I'm running the default darknet_images.py script in pycharm (the one from Alexey's github repo) and when I give the img path, the img shows but the bounding boxes don't. I tried to solve the problem but couldn't find a solution. I found that my…
![](../../users/profiles/15846880.webp)
RaresTamaian
- 3
- 1
0
votes
0 answers
Wrong anotation : x =0 , y =0 , < 0 or >1 , file: My all .txt files
I am using Yolo V4 to train the Gun Dataset for gun Object detection I have marked my object using bbox_tool the format of my .txt looks like :
0 0.8170028818443803 1.2137931034482758 0.46974063400576366 0.7172413793103448
Training yoloV4 give me…
![](../../users/profiles/13220835.webp)
Daniya Niazi
- 39
- 6
0
votes
0 answers
is that possible to apply exposure fusion technique in yolov4 algorithm?
is that possible to apply exposure fusion technique in yolov4 ? i'm using RGB images for training. changing the exposure in the configuration file would be helpful or not?
![](../../users/profiles/15877588.webp)
jesil kb
- 1
0
votes
0 answers
yolov4 does not work properly with google cloud platform
Yolov4 works fine on the local computer.
I ran it on ubuntu using google cloud platform, but
Object recognition is not possible.
All environments required for ubuntu have been built.
I am using yolo-v4 using only numpy and opencv.
When I run it on…
![](../../users/profiles/15783433.webp)
ygh
- 1
0
votes
1 answer
Using Darknet YOLOv4 in python to detect objects from an image opens and closes the image and doesn't print detected objects
So I'm using the Darknet Framework with YoloV4.
This is my yolo_image.py code:
import darknet
import cv2
# darknet helper function to run detection on image
def darknet_helper(img, width, height):
darknet_image = darknet.make_image(width,…
![](../../users/profiles/15846880.webp)
RaresTamaian
- 3
- 1
0
votes
0 answers
Graphic interface for safety hat and vest detection with Yolo v4
it happens that i am working on a openCV graphic interface for my Yolo v4 object detetction model, I tried to write the code but i am getting some erros from the yolo files paths that i need to test the model, i get most of the time this…
0
votes
0 answers
How to reduce classes in yolov4 object detection with Tensorflow
I'm learning how to use yolov4 with tensorflow to detect objects. This is my reference,
https://github.com/theAIGuysCode/tensorflow-yolov4-tflite
Now I need to reduce the classes from 80 to 10. What I did is delete the classes in coco.names, then…
![](../../users/profiles/15357176.webp)
Super Ray
- 21
- 3
0
votes
0 answers
Looking for street tree image dataset
I have already tried google open image but label of available images are not up to mark and lack of street tree images. Want to train model using yolov4.
![](../../users/profiles/15786068.webp)
Tashfik Salehin
- 1
- 1
0
votes
0 answers
YOLOv4 on tensorRT INVALID_ARGUMENT: Cannot find binding of given name: nmsed_classes
I have an issue while trying to run my code based on yolov4.engine that I generated from my onnx file, and I get this error:
[E] [TRT] INVALID_ARGUMENT: Cannot find binding of given name: num_detections
[E] [TRT] INVALID_ARGUMENT: Cannot find…
![](../../users/profiles/15745915.webp)
gojo
- 1
0
votes
0 answers
Darknet YoloV4 weights suddenly stopped working
mAp chart
For my project(license plate number detection) i decided to train my weights in batches of 300 dataset size. Total size of data set is 1500,therefore i trained the first weight(first 300 images) using a pre-trained downloaded weight that i…
![](../../users/profiles/15735007.webp)
ekolmas
- 1
- 2
0
votes
1 answer
Custom YoloV4 Detection Time
I have trained a custom YoloV4, single class object detector using AlexeyAB's darknet.
The best weight files of my model result in the following performance
I obtained this evaluation using the command,
darknet.exe detector map data/obj.data…
![](../../users/profiles/11942102.webp)
varungupta
- 125
- 2
- 7
0
votes
0 answers
Safety hat and vest detection with Yolo v4
I am training a Yolo v4 object detection model that detects the wearing of safety hats and vest on construction sites, I want to show as a result if the person is wearing the hat and vest or not, The bounding box of the person must show "person…
0
votes
0 answers
What is bad.list file in YOLO v4
after training YOLOV4, a file "bad.list" is made and containing the name of multiple images. What is the significance of this file and does it affect the trainig results and how can I fix this problem cause the images in bad.list are correctly…
![](../../users/profiles/15369854.webp)
SSSSSSSSS
- 3
- 1