Releases: AlexeyAB/darknet
YOLOv4
YOLOv4 pre-release
YOLOv4
YOLOv4 consists of: https://arxiv.org/abs/2004.10934
- Backbone: CSPDarknet53
- Neck: SPP, PAN
- Head: YOLOv3
Download:
-
cfg-file: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.cfg
-
weights-file: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.weights
-
pre-trained weights-file for training: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.conv.137
Accuracy (AP) / Speed (FPS):
YOLOv4 (416x416 batch=1 FP16) - 32 FPS on Jetson Xavier AGX by using tkDNN+TensorRT: https://github.com/ceccocats/tkDNN
Size | Darknet FPS (avg) | tkDNN TensorRT FP32 FPS | tkDNN TensorRT FP16 FPS | tkDNN TensorRT FP16 batch=4 FPS | Speedup |
---|---|---|---|---|---|
320 | 100.6 | 116 | 202 | 423 | 4.2x |
416 | 82.5 | 103 | 162 | 284 | 3.5x |
512 | 69.7 | 91 | 134 | 206 | 2.9x |
680 | 53.6 | 62 | 100 | 150 | 2.8x |
Yolo v3 optimal
Features:
- fusion blocks: FPN, PAN, ASFF, BiFPN
- network modules: ResNet, CPS, SPP, RFB
- network architecture search: CSPResNext50, CSPDarknet53, SpineNet49, EfficientNetB0, MixNet-M
- activations: SWISH, MISH
- other features: weighted-[shortcut], Sigmoid scaling (Scale-sensitivity), Label smoothing, Optimal hyper parameters, Dynamic mini batch size for random shapes, Squeeze-and-excitation, Grouped convolution, MixConv (grouped [route]), Elastic-module
- data augmentation: MixUp, CutMix, Mosaic
- losses: MSE, GIoU, CIoU, DIoU
- detection layers: [yolo] (fixed iou_thresh), [Gaussian_yolo]
- detection on video (sequence of frames) - layers: [crnn] (convolutional-RNN), [conv_lstm] (Convolutional LSTM)
Darknet for Windows & Linux:
Darknet for Windows & Linux:
- object detection: Yolo v3, Yolo v2
- classification: ResNet, Darknet, DenseNet
- sequence prediction RNN-layers: rnn, crnn, gru, lstm
- Tensor Cores are used
Tested for Training and Prediction.
-
There are attached compiled binary files of Darknet for Windows x64 (559 MB): https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3/darknet.zip
Are used: MSVS 2015, CUDA 10.0, cuDNN 7.4.2, OpenCV 3.4.0, GPU CC 3.0 & 7.5
May be requiredvc_redist.x64.exe
file 13.9 MB (Visual C++ Redistributable for MSVS2015 ): https://www.microsoft.com/en-us/download/confirmation.aspx?id=48145&6B49FDFB-8E5B-4B07-BC31-15695C5A2143=1
Tested Yolo v3 for training and detection on Windows and Linux
Can be used for training and detection Yolo v3 and v2 on Windows and Linux.
Added several performance improvements.
It supports mixed-precision training/detection using Tensor Cores on GPU Volta - set CUDNN_HALF=1
in the Makefile
Tested Yolo v2 for training and detection on Windows and Linux
Yolo_v2_tested Update Readme.md