Convert Figma logo to code with AI

AlexeyAB logodarknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

21,700
7,957
21,700
5,450
View on GitHub

Top Related Projects

ultralytics's avatar

yolov5

49,537

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

tensorflow's avatar

models

77,006

Models and examples built with TensorFlow

facebookresearch's avatar

detectron2

29,935

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

matterport's avatar

Mask_RCNN

24,600

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

pjreddie's avatar

darknet

25,692

Convolutional Neural Networks

WongKinYiu's avatar

yolov7

13,305

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Quick Overview

AlexeyAB/darknet is an open-source neural network framework written in C and CUDA. It's a fork of the original Darknet project, with additional features and improvements. This repository is particularly known for its implementation of YOLO (You Only Look Once), a real-time object detection system.

Pros

  • High performance and speed, especially with GPU acceleration
  • Supports both Windows and Linux operating systems
  • Extensive documentation and active community support
  • Includes pre-trained models for various tasks, including object detection and image classification

Cons

  • Steep learning curve for beginners due to its C-based implementation
  • Limited support for high-level APIs compared to some other deep learning frameworks
  • Requires manual compilation and setup, which can be challenging for some users
  • Some features may not be as polished or well-maintained as those in more popular frameworks

Code Examples

  1. Loading a pre-trained YOLO model and performing object detection:
#include "darknet.h"

int main() {
    char *cfg = "cfg/yolov4.cfg";
    char *weights = "yolov4.weights";
    char *filename = "data/dog.jpg";
    
    network *net = load_network(cfg, weights, 0);
    image im = load_image_color(filename, 0, 0);
    image sized = letterbox_image(im, net->w, net->h);
    
    layer l = net->layers[net->n - 1];
    float *X = sized.data;
    network_predict(net, X);
    
    int nboxes = 0;
    detection *dets = get_network_boxes(net, im.w, im.h, 0.5, 0.5, 0, 1, &nboxes);
    
    draw_detections(im, dets, nboxes, 0.5, "predictions.jpg");
    free_detections(dets, nboxes);
    free_image(im);
    free_image(sized);
    free_network(net);
    
    return 0;
}
  1. Training a custom YOLO model:
#include "darknet.h"

int main() {
    char *cfg = "cfg/yolov4-custom.cfg";
    char *weights = "yolov4.conv.137";
    char *train_images = "data/train.txt";
    
    char *backup_directory = "backup/";
    
    srand(time(0));
    char *base = basecfg(cfg);
    printf("%s\n", base);
    float avg_loss = -1;
    network *net = load_network(cfg, weights, 0);
    printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net->learning_rate, net->momentum, net->decay);
    
    int imgs = net->batch * net->subdivisions;
    int i = *net->seen / imgs;
    data train, buffer;
    
    list *plist = get_paths(train_images);
    char **paths = (char **)list_to_array(plist);
    
    load_args args = {0};
    args.w = net->w;
    args.h = net->h;
    args.paths = paths;
    args.n = imgs;
    args.m = plist->size;
    args.d = &buffer;
    args.type = DETECTION_DATA;
    
    pthread_t load_thread = load_data_in_thread(args);
    clock_t time;
    
    while(get_current_batch(net) < net->max_batches) {
        i += 1;
        time = clock();
        pthread_join(load_thread, 0);
        train = buffer;
        load_thread = load_data_in_thread(args);
        
        printf("Loaded: %lf seconds\n", sec(clock()-time));
        time = clock();
        float loss = train_network(net, train);
        
        if (avg_loss < 0) avg

Competitor Comparisons

ultralytics logo

yolov5

49,537

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Pros of YOLOv5

  • Easier to use and more accessible, with better documentation and tutorials
  • Faster training and inference times on modern hardware
  • More active development and frequent updates

Cons of YOLOv5

  • Less flexible for custom architectures and modifications
  • Smaller community and fewer third-party contributions
  • Limited support for older YOLO versions

Code Comparison

Darknet (C):

layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int padding, ACTIVATION activation, int batch_normalize, int binary, int xnor, int adam)
{
    layer l = {0};
    l.type = CONVOLUTIONAL;
    // ... (additional initialization)
    return l;
}

YOLOv5 (Python):

class Conv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
tensorflow logo

models

77,006

Models and examples built with TensorFlow

Pros of TensorFlow Models

  • Broader scope with implementations of various ML models beyond object detection
  • Better integration with TensorFlow ecosystem and tools
  • More extensive documentation and community support

Cons of TensorFlow Models

  • Steeper learning curve for beginners
  • Potentially slower inference speed compared to Darknet's optimized C implementation
  • More complex setup and configuration process

Code Comparison

Darknet (C):

image im = load_image("data/dog.jpg", 0, 0, 0);
network *net = load_network("cfg/yolov3.cfg", "yolov3.weights", 0);
detection *dets = get_network_boxes(net, im.w, im.h, 0.5, 0.5, 0, 1, &nboxes);

TensorFlow Models (Python):

image = tf.io.read_file("data/dog.jpg")
image = tf.image.decode_jpeg(image, channels=3)
input_tensor = tf.expand_dims(image, 0)
detections = detect_fn(input_tensor)

Both repositories offer object detection capabilities, but they cater to different user needs. Darknet focuses on speed and efficiency, making it suitable for real-time applications. TensorFlow Models provides a more comprehensive suite of machine learning tools and better integration with the TensorFlow ecosystem, but may require more setup and configuration.

facebookresearch logo

detectron2

29,935

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Pros of Detectron2

  • Built on PyTorch, offering more flexibility and easier integration with other deep learning projects
  • Extensive documentation and active community support
  • Modular design allows for easier customization and extension of models

Cons of Detectron2

  • Steeper learning curve for beginners due to its more complex architecture
  • Requires more computational resources for training and inference

Code Comparison

Darknet (C):

layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int padding, ACTIVATION activation, int batch_normalize, int binary, int xnor)
{
    layer l = {0};
    l.type = CONVOLUTIONAL;
    // ... (additional initialization)
    return l;
}

Detectron2 (Python):

class Conv2d(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, bias)
    
    def forward(self, x):
        return self.conv(x)
matterport logo

Mask_RCNN

24,600

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Pros of Mask_RCNN

  • Built on TensorFlow and Keras, offering easier integration with other deep learning projects
  • Specifically designed for instance segmentation tasks, providing pixel-level object detection
  • Includes pre-trained models on the COCO dataset, enabling quick start for various applications

Cons of Mask_RCNN

  • Generally slower inference speed compared to Darknet's YOLO-based models
  • Limited to instance segmentation tasks, while Darknet supports various object detection architectures
  • Requires more computational resources for training and inference

Code Comparison

Mask_RCNN (Python):

import mrcnn.model as modellib
model = modellib.MaskRCNN(mode="inference", config=config, model_dir=MODEL_DIR)
model.load_weights(WEIGHTS_PATH, by_name=True)
results = model.detect([image], verbose=1)

Darknet (C):

network *net = load_network("cfg/yolov3.cfg", "yolov3.weights", 0);
image im = load_image_color(input_image, 0, 0);
detection *dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes);
pjreddie logo

darknet

25,692

Convolutional Neural Networks

Pros of darknet (pjreddie)

  • Original implementation by the creator of YOLO
  • Simpler codebase, easier to understand for beginners
  • Lightweight and faster for basic YOLO implementations

Cons of darknet (pjreddie)

  • No longer actively maintained
  • Lacks support for newer YOLO versions and features
  • Limited GPU support and optimization

Code Comparison

darknet (pjreddie):

void forward_network(network *net)
{
    network orig = *net;
    net->input = net->layers[0].output;  
    net->truth = 0;
    for(i = 1; i < net->n; ++i){
        layer l = net->layers[i];
        l.forward(l, net);
        net->input = l.output;
        if(l.truth) net->truth = l.output;
    }
    *net = orig;
}

darknet (AlexeyAB):

void forward_network(network *net)
{
    network orig = *net;
    net->input = net->layers[0].output;  
    net->truth = 0;
    for(i = 1; i < net->n; ++i){
        layer l = net->layers[i];
        if(l.delta){
            fill_cpu(l.outputs * l.batch, 0, l.delta, 1);
        }
        l.forward(l, net);
        net->input = l.output;
        if(l.truth) net->truth = l.output;
    }
    calc_network_cost(net);
    *net = orig;
}

The AlexeyAB version includes additional features like delta initialization and network cost calculation, reflecting its more comprehensive and optimized implementation.

WongKinYiu logo

yolov7

13,305

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Pros of YOLOv7

  • Improved performance and accuracy over previous YOLO versions
  • Includes advanced features like compound scaling and re-parameterization
  • Offers pre-trained models for various tasks and datasets

Cons of YOLOv7

  • Less extensive documentation compared to Darknet
  • Narrower focus on YOLO architecture, while Darknet supports multiple models
  • Newer project with potentially less community support and resources

Code Comparison

YOLOv7:

from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import check_img_size, non_max_suppression, scale_coords

model = attempt_load(weights, map_location=device)

Darknet:

network *net = load_network(cfgfile, weightfile, 0);
image im = load_image_color(filename, 0, 0);
detection *dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes);

YOLOv7 uses Python with PyTorch, while Darknet is implemented in C. YOLOv7's code is more abstracted and easier to use for most developers, but Darknet offers lower-level control and potentially better performance for advanced users.

Convert Figma logo designs to code with AI

Visual Copilot

Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.

Try Visual Copilot

README

Yolo v4, v3 and v2 for Windows and Linux

(neural networks for object detection)

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

YOLOv7 is more accurate and faster than YOLOv5 by 120% FPS, than YOLOX by 180% FPS, than Dual-Swin-T by 1200% FPS, than ConvNext by 550% FPS, than SWIN-L by 500% FPS, than PPYOLOE-X by 150% FPS.

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100, batch=1.

  • YOLOv7-e6 (55.9% AP, 56 FPS V100 b=1) by +500% FPS faster than SWIN-L C-M-RCNN (53.9% AP, 9.2 FPS A100 b=1)
  • YOLOv7-e6 (55.9% AP, 56 FPS V100 b=1) by +550% FPS faster than ConvNeXt-XL C-M-RCNN (55.2% AP, 8.6 FPS A100 b=1)
  • YOLOv7-w6 (54.6% AP, 84 FPS V100 b=1) by +120% FPS faster than YOLOv5-X6-r6.1 (55.0% AP, 38 FPS V100 b=1)
  • YOLOv7-w6 (54.6% AP, 84 FPS V100 b=1) by +1200% FPS faster than Dual-Swin-T C-M-RCNN (53.6% AP, 6.5 FPS V100 b=1)
  • YOLOv7x (52.9% AP, 114 FPS V100 b=1) by +150% FPS faster than PPYOLOE-X (51.9% AP, 45 FPS V100 b=1)
  • YOLOv7 (51.2% AP, 161 FPS V100 b=1) by +180% FPS faster than YOLOX-X (51.1% AP, 58 FPS V100 b=1)

more5

image

More details in articles on medium:

Manual: https://github.com/AlexeyAB/darknet/wiki

Discussion:

About Darknet framework: http://pjreddie.com/darknet/

Darknet Continuous Integration CircleCI Contributors License: Unlicense DOI arxiv.org arxiv.org colab colab

Darknet Logo

scaled_yolov4 AP50:95 - FPS (Tesla V100) Paper: https://arxiv.org/abs/2011.08036

modern_gpus AP50:95 / AP50 - FPS (Tesla V100) Paper: https://arxiv.org/abs/2004.10934

tkDNN-TensorRT accelerates YOLOv4 ~2x times for batch=1 and 3x-4x times for batch=4.

GeForce RTX 2080 Ti

Network SizeDarknet, FPS (avg)tkDNN TensorRT FP32, FPStkDNN TensorRT FP16, FPSOpenCV FP16, FPStkDNN TensorRT FP16 batch=4, FPSOpenCV FP16 batch=4, FPStkDNN Speedup
3201001162021834234304.3x
416821031621592842943.6x
51269911341382062163.1x
60853621031151501502.8x
Tiny 416443609790773177413533.5x
Tiny 416 CPU Core i7 7700HQ3.4--42-3912x

Youtube video of results

Yolo v4Scaled Yolo v4

Others: https://www.youtube.com/user/pjreddie/videos

How to evaluate AP of YOLOv4 on the MS COCO evaluation server

  1. Download and unzip test-dev2017 dataset from MS COCO server: http://images.cocodataset.org/zips/test2017.zip
  2. Download list of images for Detection tasks and replace the paths with yours: https://raw.githubusercontent.com/AlexeyAB/darknet/master/scripts/testdev2017.txt
  3. Download yolov4.weights file 245 MB: yolov4.weights (Google-drive mirror yolov4.weights )
  4. Content of the file cfg/coco.data should be
classes= 80
train  = <replace with your path>/trainvalno5k.txt
valid = <replace with your path>/testdev2017.txt
names = data/coco.names
backup = backup
eval=coco
  1. Create /results/ folder near with ./darknet executable file
  2. Run validation: ./darknet detector valid cfg/coco.data cfg/yolov4.cfg yolov4.weights
  3. Rename the file /results/coco_results.json to detections_test-dev2017_yolov4_results.json and compress it to detections_test-dev2017_yolov4_results.zip
  4. Submit file detections_test-dev2017_yolov4_results.zip to the MS COCO evaluation server for the test-dev2019 (bbox)

How to evaluate FPS of YOLOv4 on GPU

  1. Compile Darknet with GPU=1 CUDNN=1 CUDNN_HALF=1 OPENCV=1 in the Makefile
  2. Download yolov4.weights file 245 MB: yolov4.weights (Google-drive mirror yolov4.weights )
  3. Get any .avi/.mp4 video file (preferably not more than 1920x1080 to avoid bottlenecks in CPU performance)
  4. Run one of two commands and look at the AVG FPS:
  • include video_capturing + NMS + drawing_bboxes: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -dont_show -ext_output
  • exclude video_capturing + NMS + drawing_bboxes: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -benchmark

Pre-trained models

There are weights-file for different cfg-files (trained for MS COCO dataset):

FPS on RTX 2070 (R) and Tesla V100 (V):

CLICK ME - Yolo v3 models
CLICK ME - Yolo v2 models

Put it near compiled: darknet.exe

You can get cfg-files by path: darknet/cfg/

Requirements for Windows, Linux and macOS

Yolo v4 in other frameworks

Datasets

  • MS COCO: use ./scripts/get_coco_dataset.sh to get labeled MS COCO detection dataset
  • OpenImages: use python ./scripts/get_openimages_dataset.py for labeling train detection dataset
  • Pascal VOC: use python ./scripts/voc_label.py for labeling Train/Test/Val detection datasets
  • ILSVRC2012 (ImageNet classification): use ./scripts/get_imagenet_train.sh (also imagenet_label.sh for labeling valid set)
  • German/Belgium/Russian/LISA/MASTIF Traffic Sign Datasets for Detection - use this parser: https://github.com/angeligareta/Datasets2Darknet#detection-task
  • List of other datasets: https://github.com/AlexeyAB/darknet/tree/master/scripts#datasets

Improvements in this repository

  • developed State-of-the-Art object detector YOLOv4
  • added State-of-Art models: CSP, PRN, EfficientNet
  • added layers: [conv_lstm], [scale_channels] SE/ASFF/BiFPN, [local_avgpool], [sam], [Gaussian_yolo], [reorg3d] (fixed [reorg]), fixed [batchnorm]
  • added the ability for training recurrent models (with layers conv-lstm[conv_lstm]/conv-rnn[crnn]) for accurate detection on video
  • added data augmentation: [net] mixup=1 cutmix=1 mosaic=1 blur=1. Added activations: SWISH, MISH, NORM_CHAN, NORM_CHAN_SOFTMAX
  • added the ability for training with GPU-processing using CPU-RAM to increase the mini_batch_size and increase accuracy (instead of batch-norm sync)
  • improved binary neural network performance 2x-4x times for Detection on CPU and GPU if you trained your own weights by using this XNOR-net model (bit-1 inference) : https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov3-tiny_xnor.cfg
  • improved neural network performance ~7% by fusing 2 layers into 1: Convolutional + Batch-norm
  • improved performance: Detection 2x times, on GPU Volta/Turing (Tesla V100, GeForce RTX, ...) using Tensor Cores if CUDNN_HALF defined in the Makefile or darknet.sln
  • improved performance ~1.2x times on FullHD, ~2x times on 4K, for detection on the video (file/stream) using darknet detector demo...
  • improved performance 3.5 X times of data augmentation for training (using OpenCV SSE/AVX functions instead of hand-written functions) - removes bottleneck for training on multi-GPU or GPU Volta
  • improved performance of detection and training on Intel CPU with AVX (Yolo v3 ~85%)
  • optimized memory allocation during network resizing when random=1
  • optimized GPU initialization for detection - we use batch=1 initially instead of re-init with batch=1
  • added correct calculation of mAP, F1, IoU, Precision-Recall using command darknet detector map...
  • added drawing of chart of average-Loss and accuracy-mAP (-map flag) during training
  • run ./darknet detector demo ... -json_port 8070 -mjpeg_port 8090 as JSON and MJPEG server to get results online over the network by using your soft or Web-browser
  • added calculation of anchors for training
  • added example of Detection and Tracking objects: https://github.com/AlexeyAB/darknet/blob/master/src/yolo_console_dll.cpp
  • run-time tips and warnings if you use incorrect cfg-file or dataset
  • added support for Windows
  • many other fixes of code...

And added manual - How to train Yolo v4-v2 (to detect your custom objects)

Also, you might be interested in using a simplified repository where is implemented INT8-quantization (+30% speedup and -1% mAP reduced): https://github.com/AlexeyAB/yolo2_light

How to use on the command line

If you use build.ps1 script or the makefile (Linux only) you will find darknet in the root directory.

If you use the deprecated Visual Studio solutions, you will find darknet in the directory \build\darknet\x64.

If you customize build with CMake GUI, darknet executable will be installed in your preferred folder.

  • Yolo v4 COCO - image: ./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -thresh 0.25
  • Output coordinates of objects: ./darknet detector test cfg/coco.data yolov4.cfg yolov4.weights -ext_output dog.jpg
  • Yolo v4 COCO - video: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights -ext_output test.mp4
  • Yolo v4 COCO - WebCam 0: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights -c 0
  • Yolo v4 COCO for net-videocam - Smart WebCam: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights http://192.168.0.80:8080/video?dummy=param.mjpg
  • Yolo v4 - save result videofile res.avi: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -out_filename res.avi
  • Yolo v3 Tiny COCO - video: ./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights test.mp4
  • JSON and MJPEG server that allows multiple connections from your soft or Web-browser ip-address:8070 and 8090: ./darknet detector demo ./cfg/coco.data ./cfg/yolov3.cfg ./yolov3.weights test50.mp4 -json_port 8070 -mjpeg_port 8090 -ext_output
  • Yolo v3 Tiny on GPU #1: ./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights -i 1 test.mp4
  • Alternative method Yolo v3 COCO - image: ./darknet detect cfg/yolov4.cfg yolov4.weights -i 0 -thresh 0.25
  • Train on Amazon EC2, to see mAP & Loss-chart using URL like: http://ec2-35-160-228-91.us-west-2.compute.amazonaws.com:8090 in the Chrome/Firefox (Darknet should be compiled with OpenCV): ./darknet detector train cfg/coco.data yolov4.cfg yolov4.conv.137 -dont_show -mjpeg_port 8090 -map
  • 186 MB Yolo9000 - image: ./darknet detector test cfg/combine9k.data cfg/yolo9000.cfg yolo9000.weights
  • Remember to put data/9k.tree and data/coco9k.map under the same folder of your app if you use the cpp api to build an app
  • To process a list of images data/train.txt and save results of detection to result.json file use: ./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -ext_output -dont_show -out result.json < data/train.txt
  • To process a list of images data/train.txt and save results of detection to result.txt use: ./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -dont_show -ext_output < data/train.txt > result.txt
  • To process a video and output results to a json file use: darknet.exe detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights file.mp4 -dont_show -json_file_output results.json
  • Pseudo-labelling - to process a list of images data/new_train.txt and save results of detection in Yolo training format for each image as label <image_name>.txt (in this way you can increase the amount of training data) use: ./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -thresh 0.25 -dont_show -save_labels < data/new_train.txt
  • To calculate anchors: ./darknet detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -height 416
  • To check accuracy mAP@IoU=50: ./darknet detector map data/obj.data yolo-obj.cfg backup\yolo-obj_7000.weights
  • To check accuracy mAP@IoU=75: ./darknet detector map data/obj.data yolo-obj.cfg backup\yolo-obj_7000.weights -iou_thresh 0.75
For using network video-camera mjpeg-stream with any Android smartphone

  1. Download for Android phone mjpeg-stream soft: IP Webcam / Smart WebCam

  2. Connect your Android phone to the computer by WiFi (through a WiFi-router) or USB

  3. Start Smart WebCam on your phone

  4. Replace the address below, shown in the phone application (Smart WebCam) and launch:

  • Yolo v4 COCO-model: ./darknet detector demo data/coco.data yolov4.cfg yolov4.weights http://192.168.0.80:8080/video?dummy=param.mjpg -i 0

How to compile on Linux/macOS (using CMake)

The CMakeLists.txt will attempt to find installed optional dependencies like CUDA, cudnn, ZED and build against those. It will also create a shared object library file to use darknet for code development.

To update CMake on Ubuntu, it's better to follow guide here: https://apt.kitware.com/ or https://cmake.org/download/

git clone https://github.com/AlexeyAB/darknet
cd darknet
mkdir build_release
cd build_release
cmake ..
cmake --build . --target install --parallel 8

Using also PowerShell

Install: Cmake, CUDA, cuDNN How to install dependencies

Install powershell for your OS (Linux or MacOS) (guide here).

Open PowerShell type these commands

git clone https://github.com/AlexeyAB/darknet
cd darknet
./build.ps1 -UseVCPKG -EnableOPENCV -EnableCUDA -EnableCUDNN
  • remove options like -EnableCUDA or -EnableCUDNN if you are not interested into
  • remove option -UseVCPKG if you plan to manually provide OpenCV library to darknet or if you do not want to enable OpenCV integration
  • add option -EnableOPENCV_CUDA if you want to build OpenCV with CUDA support - very slow to build! (requires -UseVCPKG)

If you open the build.ps1 script at the beginning you will find all available switches.

How to compile on Linux (using make)

Just do make in the darknet directory. (You can try to compile and run it on Google Colab in cloud link (press «Open in Playground» button at the top-left corner) and watch the video link ) Before make, you can set such options in the Makefile: link

  • GPU=1 to build with CUDA to accelerate by using GPU (CUDA should be in /usr/local/cuda)
  • CUDNN=1 to build with cuDNN v5-v7 to accelerate training by using GPU (cuDNN should be in /usr/local/cudnn)
  • CUDNN_HALF=1 to build for Tensor Cores (on Titan V / Tesla V100 / DGX-2 and later) speedup Detection 3x, Training 2x
  • OPENCV=1 to build with OpenCV 4.x/3.x/2.4.x - allows to detect on video files and video streams from network cameras or web-cams
  • DEBUG=1 to build debug version of Yolo
  • OPENMP=1 to build with OpenMP support to accelerate Yolo by using multi-core CPU
  • LIBSO=1 to build a library darknet.so and binary runnable file uselib that uses this library. Or you can try to run so LD_LIBRARY_PATH=./:$LD_LIBRARY_PATH ./uselib test.mp4 How to use this SO-library from your own code - you can look at C++ example: https://github.com/AlexeyAB/darknet/blob/master/src/yolo_console_dll.cpp or use in such a way: LD_LIBRARY_PATH=./:$LD_LIBRARY_PATH ./uselib data/coco.names cfg/yolov4.cfg yolov4.weights test.mp4
  • ZED_CAMERA=1 to build a library with ZED-3D-camera support (should be ZED SDK installed), then run LD_LIBRARY_PATH=./:$LD_LIBRARY_PATH ./uselib data/coco.names cfg/yolov4.cfg yolov4.weights zed_camera
  • You also need to specify for which graphics card the code is generated. This is done by setting ARCH=. If you use a newer version than CUDA 11 you further need to edit line 20 from Makefile and remove -gencode arch=compute_30,code=sm_30 \ as Kepler GPU support was dropped in CUDA 11. You can also drop the general ARCH= and just uncomment ARCH= for your graphics card.

How to compile on Windows (using CMake)

Requires:

In Windows:

  • Start (button) -> All programs -> CMake -> CMake (gui) ->

  • look at image In CMake: Enter input path to the darknet Source, and output path to the Binaries -> Configure (button) -> Optional platform for generator: x64 -> Finish -> Generate -> Open Project ->

  • in MS Visual Studio: Select: x64 and Release -> Build -> Build solution

  • find the executable file darknet.exe in the output path to the binaries you specified

x64 and Release

How to compile on Windows (using vcpkg)

This is the recommended approach to build Darknet on Windows.

  1. Install Visual Studio 2017 or 2019. In case you need to download it, please go here: Visual Studio Community. Remember to install English language pack, this is mandatory for vcpkg!

  2. Install CUDA enabling VS Integration during installation.

  3. Open Powershell (Start -> All programs -> Windows Powershell) and type these commands:

Set-ExecutionPolicy unrestricted -Scope CurrentUser -Force
git clone https://github.com/AlexeyAB/darknet
cd darknet
.\build.ps1 -UseVCPKG -EnableOPENCV -EnableCUDA -EnableCUDNN

(add option -EnableOPENCV_CUDA if you want to build OpenCV with CUDA support - very slow to build! - or remove options like -EnableCUDA or -EnableCUDNN if you are not interested in them). If you open the build.ps1 script at the beginning you will find all available switches.

How to train with multi-GPU

  1. Train it first on 1 GPU for like 1000 iterations: darknet.exe detector train cfg/coco.data cfg/yolov4.cfg yolov4.conv.137

  2. Then stop and by using partially-trained model /backup/yolov4_1000.weights run training with multigpu (up to 4 GPUs): darknet.exe detector train cfg/coco.data cfg/yolov4.cfg /backup/yolov4_1000.weights -gpus 0,1,2,3

If you get a Nan, then for some datasets better to decrease learning rate, for 4 GPUs set learning_rate = 0,00065 (i.e. learning_rate = 0.00261 / GPUs). In this case also increase 4x times burn_in = in your cfg-file. I.e. use burn_in = 4000 instead of 1000.

https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ

How to train (to detect your custom objects)

(to train old Yolo v2 yolov2-voc.cfg, yolov2-tiny-voc.cfg, yolo-voc.cfg, yolo-voc.2.0.cfg, ... click by the link)

Training Yolo v4 (and v3):

  1. For training cfg/yolov4-custom.cfg download the pre-trained weights-file (162 MB): yolov4.conv.137 (Google drive mirror yolov4.conv.137 )
  2. Create file yolo-obj.cfg with the same content as in yolov4-custom.cfg (or copy yolov4-custom.cfg to yolo-obj.cfg) and:

So if classes=1 then should be filters=18. If classes=2 then write filters=21. (Do not write in the cfg-file: filters=(classes + 5)x3)

(Generally filters depends on the classes, coords and number of masks, i.e. filters=(classes + coords + 1)*<number of mask>, where mask is indices of anchors. If mask is absence, then filters=(classes + coords + 1)*num)

So for example, for 2 objects, your file yolo-obj.cfg should differ from yolov4-custom.cfg in such lines in each of 3 [yolo]-layers:

[convolutional]
filters=21

[region]
classes=2
  1. Create file obj.names in the directory build\darknet\x64\data\, with objects names - each in new line
  2. Create file obj.data in the directory build\darknet\x64\data\, containing (where classes = number of objects):
classes = 2
train  = data/train.txt
valid  = data/test.txt
names = data/obj.names
backup = backup/
  1. Put image-files (.jpg) of your objects in the directory build\darknet\x64\data\obj\
  2. You should label each object on images from your dataset. Use this visual GUI-software for marking bounded boxes of objects and generating annotation files for Yolo v2 & v3: https://github.com/AlexeyAB/Yolo_mark

It will create .txt-file for each .jpg-image-file - in the same directory and with the same name, but with .txt-extension, and put to file: object number and object coordinates on this image, for each object in new line:

<object-class> <x_center> <y_center> <width> <height>

Where:

  • <object-class> - integer object number from 0 to (classes-1)

  • <x_center> <y_center> <width> <height> - float values relative to width and height of image, it can be equal from (0.0 to 1.0]

  • for example: <x> = <absolute_x> / <image_width> or <height> = <absolute_height> / <image_height>

  • attention: <x_center> <y_center> - are center of rectangle (are not top-left corner)

    For example for img1.jpg you will be created img1.txt containing:

    1 0.716797 0.395833 0.216406 0.147222
0 0.687109 0.379167 0.255469 0.158333
1 0.420312 0.395833 0.140625 0.166667
  1. Create file train.txt in directory build\darknet\x64\data\, with filenames of your images, each filename in new line, with path relative to darknet.exe, for example containing:
data/obj/img1.jpg
data/obj/img2.jpg
data/obj/img3.jpg

  1. Download pre-trained weights for the convolutional layers and put to the directory build\darknet\x64

  2. Start training by using the command line: darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137

    To train on Linux use command: ./darknet detector train data/obj.data yolo-obj.cfg yolov4.conv.137 (just use ./darknet instead of darknet.exe)

    • (file yolo-obj_last.weights will be saved to the build\darknet\x64\backup\ for each 100 iterations)
    • (file yolo-obj_xxxx.weights will be saved to the build\darknet\x64\backup\ for each 1000 iterations)
    • (to disable Loss-Window use darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -dont_show, if you train on computer without monitor like a cloud Amazon EC2)
    • (to see the mAP & Loss-chart during training on remote server without GUI, use command darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -dont_show -mjpeg_port 8090 -map then open URL http://ip-address:8090 in Chrome/Firefox browser)

8.1. For training with mAP (mean average precisions) calculation for each 4 Epochs (set valid=valid.txt or train.txt in obj.data file) and run: darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -map

8.2. One can also set the -mAP_epochs in the training command if less or more frequent mAP calculation is needed. For example in order to calculate mAP for each 2 Epochs run darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -map -mAP_epochs 2

  1. After training is complete - get result yolo-obj_final.weights from path build\darknet\x64\backup\

    • After each 100 iterations you can stop and later start training from this point. For example, after 2000 iterations you can stop training, and later just start training using: darknet.exe detector train data/obj.data yolo-obj.cfg backup\yolo-obj_2000.weights

    (in the original repository https://github.com/pjreddie/darknet the weights-file is saved only once every 10 000 iterations if(iterations > 1000))

    • Also you can get result earlier than all 45000 iterations.

Note: If during training you see nan values for avg (loss) field - then training goes wrong, but if nan is in some other lines - then training goes well.

Note: If you changed width= or height= in your cfg-file, then new width and height must be divisible by 32.

Note: After training use such command for detection: darknet.exe detector test data/obj.data yolo-obj.cfg yolo-obj_8000.weights

Note: if error Out of memory occurs then in .cfg-file you should increase subdivisions=16, 32 or 64: link

How to train tiny-yolo (to detect your custom objects)

Do all the same steps as for the full yolo model as described above. With the exception of:

  • Download file with the first 29-convolutional layers of yolov4-tiny: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.conv.29 (Or get this file from yolov4-tiny.weights file by using command: darknet.exe partial cfg/yolov4-tiny-custom.cfg yolov4-tiny.weights yolov4-tiny.conv.29 29
  • Make your custom model yolov4-tiny-obj.cfg based on cfg/yolov4-tiny-custom.cfg instead of yolov4.cfg
  • Start training: darknet.exe detector train data/obj.data yolov4-tiny-obj.cfg yolov4-tiny.conv.29

For training Yolo based on other models (DenseNet201-Yolo or ResNet50-Yolo), you can download and get pre-trained weights as showed in this file: https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x64/partial.cmd If you made you custom model that isn't based on other models, then you can train it without pre-trained weights, then will be used random initial weights.

When should I stop training

Usually sufficient 2000 iterations for each class(object), but not less than number of training images and not less than 6000 iterations in total. But for a more precise definition of when you should stop training, use the following manual:

  1. During training, you will see varying indicators of error, and you should stop when no longer decreases 0.XXXXXXX avg:

Region Avg IOU: 0.798363, Class: 0.893232, Obj: 0.700808, No Obj: 0.004567, Avg Recall: 1.000000, count: 8 Region Avg IOU: 0.800677, Class: 0.892181, Obj: 0.701590, No Obj: 0.004574, Avg Recall: 1.000000, count: 8

9002: 0.211667, 0.60730 avg, 0.001000 rate, 3.868000 seconds, 576128 images Loaded: 0.000000 seconds

  • 9002 - iteration number (number of batch)

  • 0.60730 avg - average loss (error) - the lower, the better

    When you see that average loss 0.xxxxxx avg no longer decreases at many iterations then you should stop training. The final average loss can be from 0.05 (for a small model and easy dataset) to 3.0 (for a big model and a difficult dataset).

    Or if you train with flag -map then you will see mAP indicator Last accuracy mAP@0.5 = 18.50% in the console - this indicator is better than Loss, so train while mAP increases.

  1. Once training is stopped, you should take some of last .weights-files from darknet\build\darknet\x64\backup and choose the best of them:

For example, you stopped training after 9000 iterations, but the best result can give one of previous weights (7000, 8000, 9000). It can happen due to over-fitting. Over-fitting - is case when you can detect objects on images from training-dataset, but can't detect objects on any others images. You should get weights from Early Stopping Point:

Over-fitting

To get weights from Early Stopping Point:

2.1. At first, in your file obj.data you must specify the path to the validation dataset valid = valid.txt (format of valid.txt as in train.txt), and if you haven't validation images, just copy data\train.txt to data\valid.txt.

2.2 If training is stopped after 9000 iterations, to validate some of previous weights use this commands:

(If you use another GitHub repository, then use darknet.exe detector recall... instead of darknet.exe detector map...)

  • darknet.exe detector map data/obj.data yolo-obj.cfg backup\yolo-obj_7000.weights
  • darknet.exe detector map data/obj.data yolo-obj.cfg backup\yolo-obj_8000.weights
  • darknet.exe detector map data/obj.data yolo-obj.cfg backup\yolo-obj_9000.weights

And compare last output lines for each weights (7000, 8000, 9000):

Choose weights-file with the highest mAP (mean average precision) or IoU (intersect over union)

For example, bigger mAP gives weights yolo-obj_8000.weights - then use this weights for detection.

Or just train with -map flag:

darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -map

So you will see mAP-chart (red-line) in the Loss-chart Window. mAP will be calculated for each 4 Epochs using valid=valid.txt file that is specified in obj.data file (1 Epoch = images_in_train_txt / batch iterations)

(to change the max x-axis value - change max_batches= parameter to 2000*classes, f.e. max_batches=6000 for 3 classes)

loss_chart_map_chart

Example of custom object detection: darknet.exe detector test data/obj.data yolo-obj.cfg yolo-obj_8000.weights

  • IoU (intersect over union) - average intersect over union of objects and detections for a certain threshold = 0.24

  • mAP (mean average precision) - mean value of average precisions for each class, where average precision is average value of 11 points on PR-curve for each possible threshold (each probability of detection) for the same class (Precision-Recall in terms of PascalVOC, where Precision=TP/(TP+FP) and Recall=TP/(TP+FN) ), page-11: http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc09.pdf

mAP is default metric of precision in the PascalVOC competition, this is the same as AP50 metric in the MS COCO competition. In terms of Wiki, indicators Precision and Recall have a slightly different meaning than in the PascalVOC competition, but IoU always has the same meaning.

precision_recall_iou

Custom object detection

Example of custom object detection: darknet.exe detector test data/obj.data yolo-obj.cfg yolo-obj_8000.weights

Yolo_v2_trainingYolo_v2_training

How to improve object detection

  1. Before training:

  • set flag random=1 in your .cfg-file - it will increase precision by training Yolo for different resolutions: link

  • increase network resolution in your .cfg-file (height=608, width=608 or any value multiple of 32) - it will increase precision

  • check that each object that you want to detect is mandatory labeled in your dataset - no one object in your data set should not be without label. In the most training issues - there are wrong labels in your dataset (got labels by using some conversion script, marked with a third-party tool, ...). Always check your dataset by using: https://github.com/AlexeyAB/Yolo_mark

  • my Loss is very high and mAP is very low, is training wrong? Run training with -show_imgs flag at the end of training command, do you see correct bounded boxes of objects (in windows or in files aug_...jpg)? If no - your training dataset is wrong.

  • for each object which you want to detect - there must be at least 1 similar object in the Training dataset with about the same: shape, side of object, relative size, angle of rotation, tilt, illumination. So desirable that your training dataset include images with objects at different: scales, rotations, lightings, from different sides, on different backgrounds - you should preferably have 2000 different images for each class or more, and you should train 2000*classes iterations or more

  • desirable that your training dataset include images with non-labeled objects that you do not want to detect - negative samples without bounded box (empty .txt files) - use as many images of negative samples as there are images with objects

  • What is the best way to mark objects: label only the visible part of the object, or label the visible and overlapped part of the object, or label a little more than the entire object (with a little gap)? Mark as you like - how would you like it to be detected.

  • for training with a large number of objects in each image, add the parameter max=200 or higher value in the last [yolo]-layer or [region]-layer in your cfg-file (the global maximum number of objects that can be detected by YoloV3 is 0,0615234375*(width*height) where are width and height are parameters from [net] section in cfg-file)

  • for training for small objects (smaller than 16x16 after the image is resized to 416x416) - set layers = 23 instead of https://github.com/AlexeyAB/darknet/blob/6f718c257815a984253346bba8fb7aa756c55090/cfg/yolov4.cfg#L895

  • for training for both small and large objects use modified models:

  • If you train the model to distinguish Left and Right objects as separate classes (left/right hand, left/right-turn on road signs, ...) then for disabling flip data augmentation - add flip=0 here: https://github.com/AlexeyAB/darknet/blob/3d2d0a7c98dbc8923d9ff705b81ff4f7940ea6ff/cfg/yolov3.cfg#L17

  • General rule - your training dataset should include such a set of relative sizes of objects that you want to detect:

    • train_network_width * train_obj_width / train_image_width ~= detection_network_width * detection_obj_width / detection_image_width
    • train_network_height * train_obj_height / train_image_height ~= detection_network_height * detection_obj_height / detection_image_height

    I.e. for each object from Test dataset there must be at least 1 object in the Training dataset with the same class_id and about the same relative size:

    object width in percent from Training dataset ~= object width in percent from Test dataset

    That is, if only objects that occupied 80-90% of the image were present in the training set, then the trained network will not be able to detect objects that occupy 1-10% of the image.

  • to speedup training (with decreasing detection accuracy) set param stopbackward=1 for layer-136 in cfg-file

  • each: model of object, side, illumination, scale, each 30 grad of the turn and inclination angles - these are different objects from an internal perspective of the neural network. So the more different objects you want to detect, the more complex network model should be used.

  • to make the detected bounded boxes more accurate, you can add 3 parameters ignore_thresh = .9 iou_normalizer=0.5 iou_loss=giou to each [yolo] layer and train, it will increase mAP@0.9, but decrease mAP@0.5.

  • Only if you are an expert in neural detection networks - recalculate anchors for your dataset for width and height from cfg-file: darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -height 416 then set the same 9 anchors in each of 3 [yolo]-layers in your cfg-file. But you should change indexes of anchors masks= for each [yolo]-layer, so for YOLOv4 the 1st-[yolo]-layer has anchors smaller than 30x30, 2nd smaller than 60x60, 3rd remaining, and vice versa for YOLOv3. Also you should change the filters=(classes + 5)*<number of mask> before each [yolo]-layer. If many of the calculated anchors do not fit under the appropriate layers - then just try using all the default anchors.

  1. After training - for detection:

  • Increase network-resolution by set in your .cfg-file (height=608 and width=608) or (height=832 and width=832) or (any value multiple of 32) - this increases the precision and makes it possible to detect small objects: link

  • it is not necessary to train the network again, just use .weights-file already trained for 416x416 resolution

  • to get even greater accuracy you should train with higher resolution 608x608 or 832x832, note: if error Out of memory occurs then in .cfg-file you should increase subdivisions=16, 32 or 64: link

How to mark bounded boxes of objects and create annotation files

Here you can find repository with GUI-software for marking bounded boxes of objects and generating annotation files for Yolo v2 - v4: https://github.com/AlexeyAB/Yolo_mark

With example of: train.txt, obj.names, obj.data, yolo-obj.cfg, air1-6.txt, bird1-4.txt for 2 classes of objects (air, bird) and train_obj.cmd with example how to train this image-set with Yolo v2 - v4

Different tools for marking objects in images:

  1. in C++: https://github.com/AlexeyAB/Yolo_mark
  2. in Python: https://github.com/tzutalin/labelImg
  3. in Python: https://github.com/Cartucho/OpenLabeling
  4. in C++: https://www.ccoderun.ca/darkmark/
  5. in JavaScript: https://github.com/opencv/cvat
  6. in C++: https://github.com/jveitchmichaelis/deeplabel
  7. in C#: https://github.com/BMW-InnovationLab/BMW-Labeltool-Lite
  8. DL-Annotator for Windows ($30): url
  9. v7labs - the greatest cloud labeling tool ($1.5 per hour): https://www.v7labs.com/

How to use Yolo as DLL and SO libraries

  • on Linux
    • using build.sh or
    • build darknet using cmake or
    • set LIBSO=1 in the Makefile and do make
  • on Windows
    • using build.ps1 or
    • build darknet using cmake or
    • compile build\darknet\yolo_cpp_dll.sln solution or build\darknet\yolo_cpp_dll_no_gpu.sln solution

There are 2 APIs:

  1. To compile Yolo as C++ DLL-file yolo_cpp_dll.dll - open the solution build\darknet\yolo_cpp_dll.sln, set x64 and Release, and do the: Build -> Build yolo_cpp_dll

    • You should have installed CUDA 10.2
    • To use cuDNN do: (right click on project) -> properties -> C/C++ -> Preprocessor -> Preprocessor Definitions, and add at the beginning of line: CUDNN;

  2. To use Yolo as DLL-file in your C++ console application - open the solution build\darknet\yolo_console_dll.sln, set x64 and Release, and do the: Build -> Build yolo_console_dll

    • you can run your console application from Windows Explorer build\darknet\x64\yolo_console_dll.exe use this command: yolo_console_dll.exe data/coco.names yolov4.cfg yolov4.weights test.mp4

    • after launching your console application and entering the image file name - you will see info for each object: <obj_id> <left_x> <top_y> <width> <height> <probability>

    • to use simple OpenCV-GUI you should uncomment line //#define OPENCV in yolo_console_dll.cpp-file: link

    • you can see source code of simple example for detection on the video file: link

yolo_cpp_dll.dll-API: link

struct bbox_t {
    unsigned int x, y, w, h;    // (x,y) - top-left corner, (w, h) - width & height of bounded box
    float prob;                    // confidence - probability that the object was found correctly
    unsigned int obj_id;        // class of object - from range [0, classes-1]
    unsigned int track_id;        // tracking id for video (0 - untracked, 1 - inf - tracked object)
    unsigned int frames_counter;// counter of frames on which the object was detected
};

class Detector {
public:
        Detector(std::string cfg_filename, std::string weight_filename, int gpu_id = 0);
        ~Detector();

        std::vector<bbox_t> detect(std::string image_filename, float thresh = 0.2, bool use_mean = false);
        std::vector<bbox_t> detect(image_t img, float thresh = 0.2, bool use_mean = false);
        static image_t load_image(std::string image_filename);
        static void free_image(image_t m);

#ifdef OPENCV
        std::vector<bbox_t> detect(cv::Mat mat, float thresh = 0.2, bool use_mean = false);
        std::shared_ptr<image_t> mat_to_image_resize(cv::Mat mat) const;
#endif
};

Citation

@misc{bochkovskiy2020yolov4,
      title={YOLOv4: Optimal Speed and Accuracy of Object Detection}, 
      author={Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao},
      year={2020},
      eprint={2004.10934},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@InProceedings{Wang_2021_CVPR,
    author    = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
    title     = {{Scaled-YOLOv4}: Scaling Cross Stage Partial Network},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {13029-13038}
}