yolo v3 custom object detection in bbox-label-tool converting into yolo format

install cuda cudnn and every dependency of open cv needed for yolo in windows 7 ,10 ,8 for full gpu acceleration and video object detection use this site

a word on the resolution of image to be use for this project

Okay I've just looked at the dataset and it seems like the images are really small compared to what yolo expects. Not sure what input resolution you have in your cfg but you should have images with resolution greater than network resolution (i.e. greater than width=416 height=416), but what I can see it that the dataset have images with resolution 156x195 (didn't look all through just took one sample). YOLO might not be the best framework for detecting numbers and symbols, you might have better luck using something like tesseract ocr but if you want to continue with YOLO you should consider another dataset.

and the issues faced is tracked in this website

get BBox-Label-Tool

if errors and issues shows up while instaling BBox-Label-Tool follow these video in my you tube channel

****************************************************************

How to Use Custom Tiny YOLOv2 Model on Android

Yolo training does not stop, and what type of images can be used #11

No detection is found after training #294

TRY LATEST CUSTOM OBJECT DETECTION WITH PYTHON

this first one is the best software the yolo boobs only thing youy have to do is you have to name the files as 1,2,3,4,5 and

or use this yolo -mark another tool which save times as boobs the yolo mark

** : ) so now you can cont on boobs for yolo : )**********

friends for a seem less gpu acceleration
try to make the file in vim as command given below

$ vi Makefile
now it gets into the vim editor now press insert in your keyboard and now change the GPU = 0 to GPU =1 and CUDNN=1 and OPENCV =1 then
get to the bottom of the vim editor and press esc
and type
:wq and press enter
now it gets out of the vim editor and now
type
$ make -j4

and type the following command for training after training give the test commands the train and test commands are below

for trainig give the command with correct path below

for testing put the weights and start the training as below

these commands depend on the user name and location of these files

[peymanrostami]

Hi.
Excellent work.

is there a way I can make the selection bounding box of an object resizeable?

[zul]

I got an error it says cannot convert the string to float . how am i gonna solve it, any idea?

[cillianbao]

Traceback (most recent call last):
File "convert.py", line 93, in <module>
b = (float(xmin), float(xmax), float(ymin), float(ymax))
ValueError: invalid literal for float(): 1
531
how to solve it

[bantikumar]

how will i revert from yolo to original dimension of bounding box

[koutinimarwan]

hello, i have annotation with three valuers and i i don't understand how to convert annotation with three valuers to yolo format

[yontenjamtsho]

Thank you very much for the code. I am getting this error:

im = Image.open(img_path)
File "/Users/yonten/anaconda2/lib/python2.7/site-packages/PIL/Image.py", line 2609, in open
fp = builtins.open(filename, "rb")

Can you help me to rectify this?

[hasbyfahrudin]

what if there are multiple object that you want to detect in one image? please explain it to me

[preetikumari]

Hello, I wanted to know what can be maximum resolution of the image we can label using this BBox label tool.
For my case I want it to be of 1301 X 670 resolution.
Can you please help me with this.
Images are not completely coming in ths BBox label Tool.It is cropped form right side when I am using 2048*2048 in main.py file

[saadnaik]

can the training be done using Intel(R) UHD Graphics 620???

[doukain]

Thanks for video, but you are really confusing man :)