Stack Overflow
Stack Overflow

Questions tagged [darknet]

This tag refers to the neural net framework created by Joseph Redmon

Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation. You can find the source on GitHub or you can read more about what Darknet can do right here:

454 questions
3
votes
1 answer

parallel GPU execution with multiple darknet models in python

I'm using the darknet repository from https://github.com/pjreddie/darknet Using darknet, I can change my GPU at run-time where my model will run. For example, the following code loads the darknet model weights on GPU 0, and I run prediction on 10…
Zabir Al Nazi
  • 10,298
  • 4
  • 33
  • 60
3
votes
1 answer

What is the real architecture(layers) of YOLOv3?

Recently i'm reading yolov3's paper and code and i found a question. In yolov3 it is darknet-53, which means it has 53 convolutional layers, but when i see this picture and count, i only get 52 convolutional layers. this picture is from it's…
Aaron777
  • 31
  • 1
3
votes
0 answers

YOLOv3 & OpenCV dnn - Inconsistent shape for ConcatLayer in function 'getMemoryShapes'

I'm having trouble loading YOLOv3's into OpenCV's dnn module. I'm following this tutorial but instead of using the full YOLOv3 I'm using Tiny YOLOv3 trained on my own dataset. On line 84 layerOutputs = net.forward(ln) I get the openCV error:…
Andre Fu
  • 400
  • 1
  • 4
  • 16
3
votes
2 answers

Map/graph not appearing when training on darknet?

I am currently training on Darknet YOLO using AlexeyAB's version for linux on the master branch (https://github.com/AlexeyAB/darknet) and the map/graph does not appear in a second, separate window. My makefile is original except that I changed GPU =…
Diana Lee
  • 41
  • 2
  • 8
3
votes
2 answers

How many (classes of) objects can YOLO detect?

On the yolo website, there are weights pretrained on the coco dataset, which consits of 80 objects/classes, (and I think also weight for voc pascal dataset which consist of 20 classes). Are there (out there) some weights that have been trained on a…
Gaetan
  • 577
  • 2
  • 7
  • 20
3
votes
2 answers

How to fix ----- ./darknet: error while loading shared libraries: libcudart.so.10.0: cannot open shared object file: No such file or directory

I'm getting trouble in yolo training in jupyter-notebook with using AWS SageMaker. I wanna darknet-model to start training, but it doesn't work well. I tried these code below, And all codes go well. ! conda install cudatoolkit -y ! conda install…
weekplane
  • 33
  • 1
  • 3
3
votes
2 answers

Darknet Yolov3 Box Coordinates

I want to get bounding box coordinates (as xmin, xmax, ymin, ymax) on darknet YOLOv3 i was tried some methods but when I compile the program after changing codes, I cant see any differences. How can I find the bounding box coordinates of Darknette,…
Emrah Kalfa
  • 31
  • 1
  • 2
3
votes
2 answers

Can we Train YOLOv3 on custom objects with no GPU?

My YOLO model works fine for detecting objects such as bottle, person, cellphone, backpack et cetera. But I want to make my model detect a ring or a bracelet or a helmet (objects which are not in the present in the present yolo model). Without GPU…
user11394181
3
votes
0 answers

YOLO darknet training in R

I installed the package to use YOLO Darknet in R and it works. I follow the steps to detect my custom objects following the indications until the steps 7 "https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects" Now I would…
Laurent
  • 419
  • 4
  • 14
3
votes
1 answer

Should YOLOv3 annotations be done before the resize?

I am about to start annotating my images to train a YOLOv3 model. Before starting I want to make sure that it is okay to create the annotations on the original image. Would the annotations change respectively after I resize my images before…
sugar.darre
  • 33
  • 3
3
votes
2 answers

YOLOv3 SPP and YOLOv3 difference?

I couldn't find any good explanation about YOLOv3 SPP which has better mAP than YOLOv3. The author himself states YOLOv3 SPP as this on his repo: YOLOv3 with spatial pyramid pooling, or something But still I don't really understand it. In…
gameon67
  • 3,981
  • 5
  • 35
  • 61
3
votes
2 answers

How to run the "make" command for YoloV3 Darknet (for Windows)?

After running the ./make.exe command (By using GNUWin32), I get the following error: mkdir -p obj mkdir -p backup A subdirectory or file -p already exists. Error occurred while processing: -p. make: *** [backup] Error 1 After rerunning the…
RedGod
  • 31
  • 2
3
votes
0 answers

Yolo3 on Image-net

Yolo version 3 is amazing new Deep learning neural network with pre-trained configuration and weights. However, the maximum classes it has is only 80 class from COCO dataset. There is another much larger dataset of Imagenet with more than 22,000…
Kardi Teknomo
  • 1,375
  • 16
  • 24
3
votes
0 answers

Detecting sections of text in a document using yolo

I wanted to know if Darknet Yolo or other Object Detection algorithms can be used to pick up sections of text in a document like an IRS 1099 form - which has areas of text that form distinct sections. Can yolo be trained to pick up sections of text…
Prosenjit
  • 31
  • 1
3
votes
1 answer

OpenCv: Using Yolov3

I used the OpenCV Code from https://docs.opencv.org/3.4.1/da/d9d/tutorial_dnn_yolo.html and made it work on my machine with the yolov2 config/weights. When I try to run the program with yolov3 config/weights…
SoullessStone
  • 33
  • 1
  • 4
1 2
3
…
30 31