Run YoloV3 detections on thousands of images and save outputs? #723

austinmw · 2018-04-21T21:26:45Z

I've only figured out how to run detections on one image at a time, typing a new image filename each time. Is there any build-in way to run on an entire folder of images and save images with predictions to another folder?

AlexeyAB · 2018-04-21T21:31:29Z

Using this fork: https://github.com/AlexeyAB/darknet
you can use this command:
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt

in the file data/train.txt you should have paths to images
in the file result.txt will be results of detections

austinmw · 2018-04-21T21:33:05Z

Thanks for the reply. does that work with YoloV3 config files? edit: looks like it should, gonna try now!

AlexeyAB · 2018-04-21T21:47:21Z

@austinmw Yes.
For Yolo v3:
./darknet detector test ./cfg/coco.data ./cfg/yolov3.cfg ./yolov3.weights -dont_show < data/train.txt > result.txt

austinmw · 2018-04-21T21:47:46Z

Thanks. Does this actually save images with bounding boxes overlaid or only save bounding box info into a txt file? Trying to piece the separate detection images into a video as my build is freezing when trying to pass videos

AlexeyAB · 2018-04-21T21:51:46Z

It only saves bounding box info into a txt file

austinmw · 2018-04-21T21:54:00Z

Ah ok, happen to know any way to save prediction images like ./darknet detect only with multiple images?

surajitkundu29 · 2018-06-04T17:41:51Z

@austinmw did you get the way to save the images instead of only text file

worldmovers · 2018-06-07T17:49:10Z

@AlexeyAB I am using darknet fork from the yolo website. I have already trained my model on yolov3 . Now I want to make prediction on a folder . I tried using this
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt
but that's not working. Can you please help me

austinmw · 2018-06-07T17:59:12Z

@surajitkundu29 I didn't find an option directly. One workaround is that it will save bounding boxes over video output. So what you could do is combine your images (if they are the same size) into a video, run detection on the video, then split them back up.

AlexeyAB · 2018-06-07T19:44:26Z

@worldmovers Try to use this fork for detection: https://github.com/AlexeyAB/darknet

mhusseinsh · 2018-07-30T08:49:28Z

@AlexeyAB Is there a way to save output images with bounding boxes in a different folder ?
I have a directory with thousands of input images, and I created an input.txt path for the images, and I am passing them in the command, but the output is always overriden for each frame on predictions.png
I need to save multiple outputs
what can I do ?

PeterQuinn925 · 2018-07-30T13:58:43Z

Mostafa, Write yourself a little bit of python to call Darknet and you do do whatever you want with the pictures. Example here: PeterQuinn925/Squirrel@d514aa2

On Mon, Jul 30, 2018 at 1:49 AM Mostafa Hussein ***@***.***> wrote: @AlexeyAB <https://github.com/AlexeyAB> Is there a way to save output images with bounding boxes in a different folder ? I have a directory with thousands of input images, and I created an input.txt path for the images, and I am passing them in the command, but the output is always overriden for each frame on predictions.png I need to save multiple outputs what can I do ? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#723 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ARocJbKTi38A63u87I0E3SvSYVWJcisKks5uLsivgaJpZM4Ten8t> .

-- Peter Quinn (415) 794-2264 (cell)

mhusseinsh · 2018-07-30T14:13:52Z

@PeterQuinn925
I already did a little bash, which performs the images one by one, but the problem which i am facing now, is that each time, the image is saved as predictions.png, so it is always overwritten

and I am trying to find a way to avoid that

here is how I do it
cat imagenames.txt | ./darknet detect cfg/yolov3.cfg yolov3.weights

berinhard · 2018-08-25T05:23:35Z

@mhusseinsh I've forked darknet and implemented an ad-hoc solution that worked for me. If you want to take a look, here's the commit.

Muhammad057 · 2018-08-25T11:38:17Z

@mhusseinsh
Here's a python code to save multiple images from a test.txt file.

import os
import glob
os.system
import PIL
import PIL.Image as Image

d = 0
test_Path = r'E:\ANPR\darknet\build\darknet\x64\data\test'
with open((test_Path + '.txt'),'r') as fobj:
for line in fobj:
image_List = [[num for num in line.split()] for line in fobj]
for images in image_List:
commands = ['darknet.exe detector test data/obj.data yolo-obj_test.cfg backup/yolo-obj_4900.weights -dont_show', images[0]]
os.system(' '.join(commands))
predicted_image = Image.open("E:/ANPR/darknet/build/darknet/x64/predictions.jpg")
output = "E:/ANPR/darknet/build/darknet/x64/data/predictedimages/predicted_image%d.jpg"%d
predicted_image.save(output)
d+=1

buzdarbalooch · 2018-11-09T11:47:27Z

hi,

i ran that script successfully, in the result.txt file it stores the predicted class of each image in the train.txt and % of the prediction. What if for each prediction. One wants the coordinates of the bounding boxes of the predicted class in the image.

buzdarbalooch · 2018-11-11T09:49:53Z

@AlexeyAB can you please help?

vikasmishra591 · 2018-11-23T09:01:26Z

Hi,
I am getting prediction for single images but when I tried for multiple images it is creating result.txt file but empty and showing error like could not open names.list file.

rodrigoap · 2018-12-03T18:38:06Z

There is a -out option:

./darknet detect cfg/yolov3-tiny.cfg yolov3-tiny.weights data/dog.jpg -out myfile

Will write the image to myfile.jpg

srhtyldz · 2018-12-11T12:50:53Z

There is a -out option:

./darknet detect cfg/yolov3-tiny.cfg yolov3-tiny.weights data/dog.jpg -out myfile

Will write the image to myfile.jpg

can you do that for the folder that contains test images =?

srhtyldz · 2018-12-11T13:47:14Z

@AlexeyAB I am using darknet fork from the yolo website. I have already trained my model on yolov3 . Now I want to make prediction on a folder . I tried using this
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt
but that's not working. Can you please help me

That script also does not worked for me .How did you find a solution to save output of test data ?

vincentgong7 · 2018-12-13T00:51:14Z

Updated: May 07, 2020

I added the function of exporting the bounding box coordinates and classes names, confidence for each image in an input folder.

Now it supports:

Detect objects for multiple images in an input folder.
Export detected result (images) into the output folder.
Export a TXT file with image names, detected classes, confidence and bounding box coordinates.
Export a JSON file with image names, detected classes, confidence and bounding box coordinates.

Try now:

https://darknet.gong.im/

Updated: May 14, 2019

Batch images detection using Yolo on AexeyAB Darknet:
https://darknet.gong.im/

I added this function in the source code and resolve this problem with command:

Command

./darknet detector batch cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch exp/in_images/ exp/out_images/ > result/results.txt

Parameter explain:

The input images are: in_images/
The output images are: out_images/
The detection classes with percentage is saved in: exp/results/results.txt

As AlexeyAB updates frequently, hereby I added a stable version of AlexeyAB Darknet with extra convenient functions into my Github repos.
https://github.com/vincentgong7/VG_AlexeyAB_darknet

Usage

Clone this project. See the repo in above link.
Download pre-trained weights file into foder ./weights/. Such as:
https://pjreddie.com/media/files/yolov3-openimages.weights
Make the project with command in VG_AlexeyAB_darknet/ folder:

make

Use the command described above to perform batch detecting images.

Contact

Any questions please let me know.
vincent.gong7[at]gmail.com
http://www.gong.im

Best Regards,
Vincent

vincentgong7 · 2018-12-13T00:51:56Z

@AlexeyAB I am using darknet fork from the yolo website. I have already trained my model on yolov3 . Now I want to make prediction on a folder . I tried using this
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt
but that's not working. Can you please help me

That script also does not worked for me .How did you find a solution to save output of test data ?

Solved! Please see my answer above.

vincentgong7 · 2018-12-13T00:52:55Z

hi,

i ran that script successfully, in the result.txt file it stores the predicted class of each image in the train.txt and % of the prediction. What if for each prediction. One wants the coordinates of the bounding boxes of the predicted class in the image.

Solved! Please see my answer above.

vincentgong7 · 2018-12-13T00:54:13Z

@AlexeyAB Is there a way to save output images with bounding boxes in a different folder ?
I have a directory with thousands of input images, and I created an input.txt path for the images, and I am passing them in the command, but the output is always overriden for each frame on predictions.png
I need to save multiple outputs
what can I do ?

Solved! Please see my answer above.

vincentgong7 · 2018-12-13T00:54:38Z

@surajitkundu29 I didn't find an option directly. One workaround is that it will save bounding boxes over video output. So what you could do is combine your images (if they are the same size) into a video, run detection on the video, then split them back up.

Solved! Please see my answer above.

Yddeon · 2018-12-14T09:40:00Z

I added this function in the source code and resolve this problem with command:

./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt

Parameter explain:
* The input images are: `./in_images/`

* The output images are: `./out_images/`

* The detection classes with percentage is saved in: `./results.txt`
To reach this, you need to replace the attached detector.c into ./src/ folder and re-make the AlexeyAB darknet.

Detail process:
1. Install the AlexeyAB/darknet, see: [github link](https://github.com/AlexeyAB/darknet). The darknet is installed in the folder: `darknet/`

2. Replace the `darknet/src/detector.c` with the detector.c in attached.
   [detector.c.zip](https://github.com/pjreddie/darknet/files/2674089/detector.c.zip)

3. Make the project with command in `darknet/` folder:
   `make`

4. If you have already did the make, you may do re-make with commands:
   `clean`
   `make`
You may still do for one image with:
./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights ./data/dog.jpg

Any questions please let me know.
vincent.gong7[at]gmail.com

Best Regards,
Vincent

I managed to make your solution work but I'm still having some issues with the output!
I have a bunch of .jpg images ordered in in_images folder (1.jpg, 2.jpg ... 30.jpg) and it's succesfully saving them all but as 1.jpg.png, 2.jpg.png..

Is there a way to remove the .jpg from input files? Or keep them as jpg when saving

I'm currently solving this by running find -type f -name '*.png' | while read f; do mv "$f" "${f%.png}"; done
after the program is done but it would be nice if the oput was already the one I'm expecting without running anything afterwards

vincentgong7 · 2018-12-14T13:41:24Z

I added this function in the source code and resolve this problem with command:

./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt

Parameter explain:
* The input images are: `./in_images/`

* The output images are: `./out_images/`

* The detection classes with percentage is saved in: `./results.txt`
To reach this, you need to replace the attached detector.c into ./src/ folder and re-make the AlexeyAB darknet.

Detail process:
1. Install the AlexeyAB/darknet, see: [github link](https://github.com/AlexeyAB/darknet). The darknet is installed in the folder: `darknet/`

2. Replace the `darknet/src/detector.c` with the detector.c in attached.
   [detector.c.zip](https://github.com/pjreddie/darknet/files/2674089/detector.c.zip)

3. Make the project with command in `darknet/` folder:
   `make`

4. If you have already did the make, you may do re-make with commands:
   `clean`
   `make`
You may still do for one image with:
./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights ./data/dog.jpg
Any questions please let me know.
vincent.gong7[at]gmail.com
Best Regards,
Vincent
I managed to make your solution work but I'm still having some issues with the output!
I have a bunch of .jpg images ordered in in_images folder (1.jpg, 2.jpg ... 30.jpg) and it's succesfully saving them all but as 1.jpg.png, 2.jpg.png..

Is there a way to remove the .jpg from input files? Or keep them as jpg when saving

I'm currently solving this by running find -type f -name '*.png' | while read f; do mv "$f" "${f%.png}"; done
after the program is done but it would be nice if the oput was already the one I'm expecting without running anything afterwards

Thanks Yddeon, I'll modify on it before next week.
BR,
Vincent

vincentgong7 · 2020-07-03T13:38:50Z

Hi, I guess that you want to detect objects from multiple images, correct?

On Fri, 3 Jul 2020 at 15:24, RoshniKoli ***@***.***> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ> .

-- Regards, Vincent X. Gong

RoshniKoli · 2020-07-03T14:42:26Z

Hi, I guess that you want to detect objects from multiple images, correct?
On Fri, 3 Jul 2020 at 15:24, RoshniKoli @.***> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ .
-- Regards, Vincent X. Gong

Yes.

vincentgong7 · 2020-07-03T15:46:33Z

Try this: https://darknet.gong.im It’s made for the batch images detection using Yolo.

On Fri, 3 Jul 2020 at 16:42, RoshniKoli ***@***.***> wrote: Hi, I guess that you want to detect objects from multiple images, correct? On Fri, 3 Jul 2020 at 15:24, RoshniKoli *@*.***> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment) <#723 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Yes. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEIZ66THIA4M7THXRU7DRZXU6BANCNFSM4E32P4WQ> .

-- Regards, Vincent X. Gong

RoshniKoli · 2020-07-04T14:44:45Z

Try this: https://darknet.gong.im It’s made for the batch images detection using Yolo.
On Fri, 3 Jul 2020 at 16:42, RoshniKoli @.> wrote: Hi, I guess that you want to detect objects from multiple images, correct? On Fri, 3 Jul 2020 at 15:24, RoshniKoli @.> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment) <#723 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Yes. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEIZ66THIA4M7THXRU7DRZXU6BANCNFSM4E32P4WQ .
-- Regards, Vincent X. Gong

Hi Vincent,

I built your project and tried using the batch command. In that command, do I have to specify the path to images folder or a list of paths ? Can you please clarify? Thanks in advance.

vincentgong7 · 2020-07-04T14:59:14Z

Hi, You just need to specify the input folder folder and the output folder. The input folder: a folder contain all images to be detected. The output folder: the folder that the yolo will save detected images to. In the web page (https//darknet.gong.im) there is a explanation of each parameters in the command. Let me know if you have any questions. BR, Vincent

On Sat, 4 Jul 2020 at 16:44, RoshniKoli ***@***.***> wrote: Try this: https://darknet.gong.im It’s made for the batch images detection using Yolo. On Fri, 3 Jul 2020 at 16:42, RoshniKoli *@*.*> wrote: Hi, I guess that you want to detect objects from multiple images, correct? On Fri, 3 Jul 2020 at 15:24, RoshniKoli @.*> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 <#723> (comment) <#723 (comment) <#723 (comment)>>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Yes. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment) <#723 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEIZ66THIA4M7THXRU7DRZXU6BANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Hi Vincent, I built your project and tried using the batch command. In that command, do I have to specify the path to images folder or a list of paths ? Can you please clarify? Thanks in advance. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI5CNO222UI5OQ7OFRDRZ456TANCNFSM4E32P4WQ> .

-- Regards, Vincent X. Gong

neheteakshay · 2020-07-05T11:21:05Z

@vincentgong7 Sir, Can you help me to get only detected object(Licence plate) only from video?

RoshniKoli · 2020-07-05T13:24:43Z

Hi, You just need to specify the input folder folder and the output folder. The input folder: a folder contain all images to be detected. The output folder: the folder that the yolo will save detected images to. In the web page (https//darknet.gong.im) there is a explanation of each parameters in the command. Let me know if you have any questions. BR, Vincent
On Sat, 4 Jul 2020 at 16:44, RoshniKoli @.*> wrote: Try this: https://darknet.gong.im It’s made for the batch images detection using Yolo. On Fri, 3 Jul 2020 at 16:42, RoshniKoli @.> wrote: Hi, I guess that you want to detect objects from multiple images, correct? On Fri, 3 Jul 2020 at 15:24, RoshniKoli @.> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 <#723> (comment) <#723 (comment) <#723 (comment)>>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Yes. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment) <#723 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEIZ66THIA4M7THXRU7DRZXU6BANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Hi Vincent, I built your project and tried using the batch command. In that command, do I have to specify the path to images folder or a list of paths ? Can you please clarify? Thanks in advance. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI5CNO222UI5OQ7OFRDRZ456TANCNFSM4E32P4WQ .
-- Regards, Vincent X. Gong

I tried that as well, the build on windows went right. But the command darknet.exe is not giving any output. The sample command doesn't execute as well. I am not sure what went wrong.

vincentgong7 · 2020-07-05T18:05:27Z

Hi, you may find some error messages. Otherwise, consider run your task on Ubuntu or directly online (Google Colab), which I provide an example and it works for sure. Regards, Vincent X. Gong

…

On Sun, Jul 5, 2020 at 3:24 PM RoshniKoli ***@***.***> wrote: Hi, You just need to specify the input folder folder and the output folder. The input folder: a folder contain all images to be detected. The output folder: the folder that the yolo will save detected images to. In the web page (https//darknet.gong.im) there is a explanation of each parameters in the command. Let me know if you have any questions. BR, Vincent On Sat, 4 Jul 2020 at 16:44, RoshniKoli *@*.**> wrote: Try this: https://darknet.gong.im <https://darknet.gong.im> It’s made for the batch images detection using Yolo. On Fri, 3 Jul 2020 at 16:42, RoshniKoli @.> wrote: Hi, I guess that you want to detect objects from multiple images, correct? On Fri, 3 Jul 2020 at 15:24, RoshniKoli @.*> wrote: Using command - Get-Content | .\darknet.exe detector test .\cfg\Data.data .\cfg\yolov3_cvfashion_test.cfg .\yolov3_cvfashion_train.backup -dont_show -ext_output > result_cv.txt The program runs but i get this error - [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 139.683 avg_outputs = 1108870 Loading weights from .\yolov3_cvfashion_train.backup...Done! Loaded 107 layers from weights-file Cannot load image ???? Cannot load image � Cannot load image �� The image paths work when I test it one at a time using detector test command. The same paths as input to above code throw that error. Please suggest. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 <#723> <#723 <#723>> (comment) <#723 <#723> (comment) <#723 (comment) <#723 (comment)>>>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI6DMVUVTVYG6R7A2KTRZXLYDANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Yes. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 <#723> (comment) <#723 (comment) <#723 (comment)>>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEIZ66THIA4M7THXRU7DRZXU6BANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong Hi Vincent, I built your project and tried using the batch command. In that command, do I have to specify the path to images folder or a list of paths ? Can you please clarify? Thanks in advance. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment) <#723 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABSXEI5CNO222UI5OQ7OFRDRZ456TANCNFSM4E32P4WQ . -- Regards, Vincent X. Gong I tried that as well, the build on windows went right. But the command darknet.exe is not giving any output. The sample command doesn't execute as well. I am not sure what went wrong. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI6JQLTQEA775UUHWPTR2B5KPANCNFSM4E32P4WQ> .

vincentgong7 · 2020-07-05T18:06:34Z

Hi, Sorry, I have not yet worked on the video, please refer to the official document about detecting objects on videos. Regards, Vincent X. Gong

…

On Sun, Jul 5, 2020 at 1:21 PM neheteakshay ***@***.***> wrote: @vincentgong7 <https://github.com/vincentgong7> Sir, Can you help me to get only detected object(Licence plate) only from video? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI56XF2YK5Q3SNKSYI3R2BO25ANCNFSM4E32P4WQ> .

peijason · 2020-07-22T03:10:59Z

What is the data/coco.data for darknet detector test ? It looks while testing, data/coco.data is pointless?

murari2401 · 2020-07-31T16:27:49Z

@AlexeyAB I am using darknet fork from the yolo website. I have already trained my model on yolov3 . Now I want to make prediction on a folder . I tried using this
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt
but that's not working. Can you please help me

you can use this :

import os
import glob
import cv2
#os.system
import time
import PIL
import PIL.Image as Image

d = 0
test_Path = r"E:\yolo_v4\darknet\build\darknet\x64\c910"

images=[]
for filename in os.listdir(test_Path):
img=cv2.imread(os.path.join(test_Path,filename))

if img is not None:
	images.append(img)
commands = ['darknet.exe detector test data/objc.data cfg/yolov3-objc.cfg backup3/yolov3-objc_last.weights -dont_show', os.path.join(test_Path,filename)]
os.system(' '.join(commands))
predicted_image = Image.open("E:\\yolo_v4\\darknet\\build\\darknet\\x64\\predictions.jpg")

output = "E:/yolo_v4/darknet/build/darknet/x64/c910r/"+str(filename)

predicted_image.save(output)
d+=1

print(len(images))
print(d)

vincentgong7 · 2020-07-31T16:32:32Z

Hi, For the detecting images in folder, please try this: https://darknet.gong.im There I provide instructions and online demo. Should be easy for you. Let me know if you have any questions. BR, Vincent

On Fri, 31 Jul 2020 at 18:28, murari2401 ***@***.***> wrote: @AlexeyAB <https://github.com/AlexeyAB> I am using darknet fork from the yolo website. I have already trained my model on yolov3 . Now I want to make prediction on a folder . I tried using this ./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt but that's not working. Can you please help me import os import glob import cv2 #os.system import time import PIL import PIL.Image as Image d = 0 test_Path = r"E:\yolo_v4\darknet\build\darknet\x64\c910" images=[] for filename in os.listdir(test_Path): img=cv2.imread(os.path.join(test_Path,filename)) if img is not None: images.append(img) commands = ['darknet.exe detector test data/objc.data cfg/yolov3-objc.cfg backup3/yolov3-objc_last.weights -dont_show', os.path.join(test_Path,filename)] os.system(' '.join(commands)) predicted_image = Image.open("E:\\yolo_v4\\darknet\\build\\darknet\\x64\\predictions.jpg") output = "E:/yolo_v4/darknet/build/darknet/x64/c910r/"+str(filename) predicted_image.save(output) d+=1 print(len(images)) print(d) — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI7XODOFBECYHVGGPK3R6LWJPANCNFSM4E32P4WQ> .

-- Regards, Vincent X. Gong

murari2401 · 2020-08-02T10:17:17Z

Using this fork: https://github.com/AlexeyAB/darknet
you can use this command:
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt

in the file data/train.txt you should have paths to images
in the file result.txt will be results of detections

I Have given a input image and YOLOv3 gace output with bouding boxes. I tried to subtract input and output image then I observed yolo is modifying most of pixels in output .(When I have subtracted input and output images I should only get bounding box but instead I got much noisy image in output)

Fetulhak · 2020-11-01T09:14:15Z

import os
import glob
os.system
import PIL
import PIL.Image as Image

d = 0
test_Path = r'E:\ANPR\darknet\build\darknet\x64\data\test'
with open((test_Path + '.txt'),'r') as fobj:
for line in fobj:
image_List = [[num for num in line.split()] for line in fobj]
for images in image_List:
commands = ['darknet.exe detector test data/obj.data yolo-obj_test.cfg backup/yolo-obj_4900.weights -dont_show', images[0]]
os.system(' '.join(commands))
predicted_image = Image.open("E:/ANPR/darknet/build/darknet/x64/predictions.jpg")
output = "E:/ANPR/darknet/build/darknet/x64/data/predictedimages/predicted_image%d.jpg"%d
predicted_image.save(output)
d+=1

This works well. Here I have modified to save your predicted images based on the exact filename of your original image. This code also runs on Google Colab.

import os
import glob
os.system
import PIL
import PIL.Image as Image

test_Path = r'build/darknet/x64/data/test'
with open((test_Path + '.txt'),'r') as fobj:
for line in fobj:
image_List = [[num for num in line.split()] for line in fobj]
for images in image_List:
commands = ['./darknet detector test build/darknet/x64/data/trainer.data build/darknet/x64/cfg/yolo-obj.cfg build/darknet/x64/backup/yolo-obj_2000.weights -thresh 0.3 -iou_thresh 0.3 -dont_show', images[0]]
os.system(' '.join(commands))
predicted_image = Image.open("./predictions.jpg")
#based on the output of 'images[0]' you can manupilate the filename below
filename = images[0][27:]
#creat predictedimages folder in google colab based on your current working directory
output = "build/darknet/x64/data/predictedimages/%s"%filename
predicted_image.save(output)

panban-ux · 2020-11-09T19:13:24Z

Where in the code will i be able to extract the recognized class as word or hex to transfer it on the fly to my python lora python code?
Instead of say hello world over the lora i would like to transfer the detected objects, which of them or the number of them if i'll be able to count the same class object

vincentgong7 · 2020-11-09T19:21:00Z

Hi, You can export the detect result as json or text and then use python to parse them. Regards, Vincent X. Gong

…

On Mon, Nov 9, 2020 at 8:13 PM Panagiotis ***@***.***> wrote: Where in the code will i be able to extract the recognized class as word or hex to transfer it on the fly to my python lora python code? Instead of say hello world over the lora i would like to transfer the detected objects, which of them or the number of them if i'll be able to count the same class object — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEI6E7XWPL3UHOL43AQ3SPA5OHANCNFSM4E32P4WQ> .

panban-ux · 2020-11-09T19:26:54Z

Thanks Vincent, what im currently using is the Darknet-NNPACK for an SBC. How can effectively extract those JSON or .txt as happens in your repo? Then i will be able to write a python parser code.

panban-ux · 2020-11-11T17:46:59Z

Is there an example in python on how to print how many boats and how many persons of this JSON example:
{
"frame_id":2,
"filename":"sample_imgs/2.jpg",
"objects": [
{"class_id":8, "name":"boat", "relative_coordinates":{"left_x":1547, "top_y":1126, "width": 298, "height": 149}, "confidence":0.348690},
{"class_id":0, "name":"person", "relative_coordinates":{"left_x": 128, "top_y":1327, "width": 30, "height": 89}, "confidence":0.972903},
{"class_id":0, "name":"person", "relative_coordinates":{"left_x": 179, "top_y":1332, "width": 26, "height": 72}, "confidence":0.689888}

Used something like that but getting blanks
j = json.load(f)
c = Counter(k[4:] for d in j for k, v in d.items() if k.startswith('name'))
print(json.dumps(c, indent=2, sort_keys=True))

pentanol2 · 2020-12-11T19:54:40Z

Using this fork: https://github.com/AlexeyAB/darknet
you can use this command:
./darknet detector test data/voc.data yolo-voc.cfg yolo-voc.weights -dont_show < data/train.txt > result.txt

in the file data/train.txt you should have paths to images
in the file result.txt will be results of detections

This does not work for me. I get the following error

Cannot load image "-dont_show"
STB Reason: can't fopen

paulaceccon · 2020-12-18T19:42:17Z

./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -ext_output -dont_show -out result.json < data/train.txt produces something like:

[
    {
     "frame_id":1, 
     "filename":"lpr/1.jpg", 
     "objects": [ 
      {"class_id":0, "name":"licence_plate", "relative_coordinates":{"center_x":0.739712, "center_y":0.930132, "width":0.138180, "height":0.062141}, "confidence":0.979332}
     ] 
    }
]

rk8650 · 2020-12-20T18:05:09Z

Hi @paulaceccon ,

I tried the command on my custom dataset:
! ./darknet detector test /content/data/obj.data /content/yolov4-obj.cfg /content/drive/MyDrive/sketch_backup/yolov4-obj_best.weights -ext_output -dont_show -out /content/result.json < /content/images.txt

But I am getting blank result.json while I am getting correct output

Also getting below error at end, is it stopping to put the output in json file ?
darknet: ./src/image.c:41: get_pixel: Assertion `x < m.w && y < m.h && c < m.c' failed.
/bin/bash: line 1: 2077 Aborted (core dumped) ./darknet detector test /content/data/ob

I am stuck with it from last 2 days. Please help

paulaceccon · 2020-12-21T22:38:22Z

What worked for me was:

./darknet detector test my.data yolov4-tiny.cfg yolov4-tiny_best.weights -ext_output -dont_show -out result.json < test.txt

shubham-shahh · 2021-02-09T06:04:40Z

What worked for me was:

./darknet detector test my.data yolov4-tiny.cfg yolov4-tiny_best.weights -ext_output -dont_show -out result.json < test.txt

Hi @paulaceccon @rk8650 @pentanol2
you can use this PR AlexeyAB#7282
it will run detections on all the images in the folder and also allows you to save the cropped images in a folder by un commenting the lines https://github.com/AlexeyAB/darknet/blob/master/src/image_opencv.cpp#L980-L996

shubham-shahh · 2021-02-09T06:06:25Z

@vincentgong7 Sir, Can you help me to get only detected object(Licence plate) only from video?

AlexeyAB#7276 this might help

vincentgong7 · 2021-02-10T09:19:22Z

Hi, Sorry I have not yet looked into detecting objects in video using Yolo. Maybe others with such experiences can help. Regards, Vincent X. Gong

…

On Tue, Feb 9, 2021 at 7:07 AM Shubham Shah ***@***.***> wrote: @vincentgong7 <https://github.com/vincentgong7> Sir, Can you help me to get only detected object(Licence plate) only from video? AlexeyAB#7276 <AlexeyAB#7276> this might help — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#723 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABSXEIYNLRSZYBQLVRVACQTS6DGKLANCNFSM4E32P4WQ> .

neomukul · 2021-03-15T02:04:53Z

@mhusseinsh
Here's a python code to save multiple images from a test.txt file.

import os
import glob
os.system
import PIL
import PIL.Image as Image

d = 0
test_Path = r'E:\ANPR\darknet\build\darknet\x64\data\test'
with open((test_Path + '.txt'),'r') as fobj:
for line in fobj:
image_List = [[num for num in line.split()] for line in fobj]
for images in image_List:
commands = ['darknet.exe detector test data/obj.data yolo-obj_test.cfg backup/yolo-obj_4900.weights -dont_show', images[0]]
os.system(' '.join(commands))
predicted_image = Image.open("E:/ANPR/darknet/build/darknet/x64/predictions.jpg")
output = "E:/ANPR/darknet/build/darknet/x64/data/predictedimages/predicted_image%d.jpg"%d
predicted_image.save(output)
d+=1

Did some changes but works good. thankyou....

pabsan-0 · 2021-03-22T08:36:40Z

Hello, I struggled with batch inferring for some time and would like to share my solution. It is a python script to be run after running darknet for predictions so that images will be modified from a log text file. See more inside the very script. It is not perfect but it is quick and easy to use. Cheers!
darknet-yolo-batch-annotation.txt

saktheeswaranswan · 2021-12-10T20:52:09Z

@austinmw Yes. For Yolo v3: ./darknet detector test ./cfg/coco.data ./cfg/yolov3.cfg ./yolov3.weights -dont_show < data/train.txt > result.txt

saktheeswaranswan · 2021-12-10T20:58:00Z

Hi guys I made an python script that runs efficiently with any GPU if you have a big weights file it runs the detection and saves it on excel with time stamp and confidence you can also use live detection and save it in Excel file refer this youtube link please subscribe to appreciate my work I have done it elegantly its. Simple even you don't understand the language just watch the video and try it and you can also do it for images follow me on youtube I can guide you here is the link and code it's given in description for free

https://youtu.be/tKSiEslHVqI

bijuangalees · 2024-03-03T11:41:43Z

how to hide confidence score on predicted image on yolov2?

austinmw closed this as completed Apr 22, 2018

PeterQuinn925 mentioned this issue Aug 15, 2018

prediction class coordinates AlexeyAB/darknet#1411

Open

Run YoloV3 detections on thousands of images and save outputs? #723

Run YoloV3 detections on thousands of images and save outputs? #723

Comments

austinmw commented Apr 21, 2018

AlexeyAB commented Apr 21, 2018

austinmw commented Apr 21, 2018 • edited Loading

AlexeyAB commented Apr 21, 2018

austinmw commented Apr 21, 2018 • edited Loading

AlexeyAB commented Apr 21, 2018

austinmw commented Apr 21, 2018

surajitkundu29 commented Jun 4, 2018

worldmovers commented Jun 7, 2018

austinmw commented Jun 7, 2018 • edited Loading

AlexeyAB commented Jun 7, 2018

mhusseinsh commented Jul 30, 2018

PeterQuinn925 commented Jul 30, 2018 via email

mhusseinsh commented Jul 30, 2018

berinhard commented Aug 25, 2018

Muhammad057 commented Aug 25, 2018

buzdarbalooch commented Nov 9, 2018

buzdarbalooch commented Nov 11, 2018

vikasmishra591 commented Nov 23, 2018

rodrigoap commented Dec 3, 2018

srhtyldz commented Dec 11, 2018

srhtyldz commented Dec 11, 2018

vincentgong7 commented Dec 13, 2018 • edited Loading

Command

Usage

Contact

vincentgong7 commented Dec 13, 2018

vincentgong7 commented Dec 13, 2018

vincentgong7 commented Dec 13, 2018

vincentgong7 commented Dec 13, 2018

Yddeon commented Dec 14, 2018 • edited Loading

./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt

Detail process:

vincentgong7 commented Dec 14, 2018

./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt

Detail process:

vincentgong7 commented Jul 3, 2020 via email

RoshniKoli commented Jul 3, 2020

vincentgong7 commented Jul 3, 2020 via email

RoshniKoli commented Jul 4, 2020

vincentgong7 commented Jul 4, 2020 via email

neheteakshay commented Jul 5, 2020

RoshniKoli commented Jul 5, 2020

vincentgong7 commented Jul 5, 2020 via email

vincentgong7 commented Jul 5, 2020 via email

peijason commented Jul 22, 2020 • edited Loading

murari2401 commented Jul 31, 2020 • edited Loading

vincentgong7 commented Jul 31, 2020 via email

murari2401 commented Aug 2, 2020

Fetulhak commented Nov 1, 2020

panban-ux commented Nov 9, 2020

vincentgong7 commented Nov 9, 2020 via email

panban-ux commented Nov 9, 2020 • edited Loading

panban-ux commented Nov 11, 2020

pentanol2 commented Dec 11, 2020

paulaceccon commented Dec 18, 2020

rk8650 commented Dec 20, 2020 • edited Loading

paulaceccon commented Dec 21, 2020

shubham-shahh commented Feb 9, 2021

shubham-shahh commented Feb 9, 2021

vincentgong7 commented Feb 10, 2021 via email

neomukul commented Mar 15, 2021

pabsan-0 commented Mar 22, 2021 • edited Loading

saktheeswaranswan commented Dec 10, 2021

saktheeswaranswan commented Dec 10, 2021

bijuangalees commented Mar 3, 2024

austinmw commented Apr 21, 2018 •

edited

Loading

austinmw commented Apr 21, 2018 •

edited

Loading

austinmw commented Jun 7, 2018 •

edited

Loading

vincentgong7 commented Dec 13, 2018 •

edited

Loading

Yddeon commented Dec 14, 2018 •

edited

Loading

`./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt`

`./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt`

peijason commented Jul 22, 2020 •

edited

Loading

murari2401 commented Jul 31, 2020 •

edited

Loading

panban-ux commented Nov 9, 2020 •

edited

Loading

rk8650 commented Dec 20, 2020 •

edited

Loading

pabsan-0 commented Mar 22, 2021 •

edited

Loading