All Projects → lwplw → darknet2caffe

lwplw / darknet2caffe

Licence: other
Conversion of yolo from DarkNet to Caffe

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to darknet2caffe

Mobilenet Yolo
A caffe implementation of MobileNet-YOLO detection network
Stars: ✭ 825 (+3200%)
Mutual labels:  caffe, yolo, darknet
Pytorch Caffe Darknet Convert
convert between pytorch, caffe prototxt/weights and darknet cfg/weights
Stars: ✭ 867 (+3368%)
Mutual labels:  caffe, yolo, darknet
Darknet2caffe
Convert Darknet model to Caffe's
Stars: ✭ 46 (+84%)
Mutual labels:  caffe, conversion, darknet
OpenCV-Flask
🐛 🐛 Opencv视频流传输到网页浏览器并做目标检测 🐛 🐛
Stars: ✭ 35 (+40%)
Mutual labels:  yolo, darknet
object-tracking
Multiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (+256%)
Mutual labels:  yolo, darknet
vehicle-rear
Vehicle-Rear: A New Dataset to Explore Feature Fusion For Vehicle Identification Using Convolutional Neural Networks
Stars: ✭ 99 (+296%)
Mutual labels:  yolo, darknet
darknet-nnpack
Darknet with NNPACK
Stars: ✭ 302 (+1108%)
Mutual labels:  yolo, darknet
pnn
pnn is Darknet compatible neural nets inference engine implemented in Rust.
Stars: ✭ 17 (-32%)
Mutual labels:  yolo, darknet
darknet-vis
Visualize YOLO feature map in prediction for easily checking your model performance
Stars: ✭ 68 (+172%)
Mutual labels:  yolo, darknet
darknet ros
Robotics Operating System Package for Yolo v3 based on darknet with optimized tracking using Kalman Filter and Optical Flow.
Stars: ✭ 51 (+104%)
Mutual labels:  yolo, darknet
Tracking-with-darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 522 (+1988%)
Mutual labels:  yolo, darknet
DarkPlate
License plate parsing using Darknet and YOLO
Stars: ✭ 36 (+44%)
Mutual labels:  yolo, darknet
yolor
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
Stars: ✭ 1,867 (+7368%)
Mutual labels:  yolo, darknet
darknet
php ffi darknet
Stars: ✭ 21 (-16%)
Mutual labels:  yolo, darknet
caffe weight converter
Caffe-to-Keras weight converter. Can also export weights as Numpy arrays for further processing.
Stars: ✭ 68 (+172%)
Mutual labels:  caffe, conversion
DroNet
DroNet: Efficient convolutional neural network detector for Real-Time UAV applications
Stars: ✭ 54 (+116%)
Mutual labels:  yolo, darknet
JSON2YOLO
Convert JSON annotations into YOLO format.
Stars: ✭ 222 (+788%)
Mutual labels:  yolo, darknet
ffcnn
ffcnn is a cnn neural network inference framework, written in 600 lines C language.
Stars: ✭ 50 (+100%)
Mutual labels:  yolo, darknet
lightDenseYOLO
A real-time object detection app based on lightDenseYOLO Our lightDenseYOLO is the combination of two components: lightDenseNet as the CNN feature extractor and YOLO v2 as the detection module
Stars: ✭ 20 (-20%)
Mutual labels:  yolo, darknet
Caffe Yolov3 Windows
A windows caffe implementation of YOLO detection network
Stars: ✭ 210 (+740%)
Mutual labels:  caffe, yolo

Darknet2Caffe

DarkNet下训练的yolo的.cfg文件和.weights文件转换为Caffe的.prototxt文件和.caffemodel文件

根目录执行命令:

python darknet2caffe.py yolov2_tiny_3.cfg yolov2_tiny_3.weights yolov2_tiny_3.prototxt yolov2_tiny_3.caffemodel

其中:

  1. yolov2_tiny_3.cfg --------- 模型结构文件,这里是一个3个类别的目标检测模型

  2. yolov2_tiny_3.weights ----- 训练好的模型权重文件

  3. yolov2_tiny_3.prototxt ---- 待生成的Caffe框架下的模型结构文件

  4. yolov2_tiny_3.caffemodel -- 待生成的Caffe框架下的模型权重文件

注:

  1. 上面我准备好的4个文件下载链接:链接: https://pan.baidu.com/s/1di7UxmJkUmkN3vgvlJOVFQ 提取码: ckd2

  2. 修改darknet2caffe.py中的Caffe路径(路径为Caffe的根目录,从官方GitHub下载并正常安装,可参考:https://blog.csdn.net/lwplwf/article/details/82415620)

  3. 修改yolov2_tiny_3.prototxt文件(和Caffe下region层的实现有关)

将第一层

input: "data"
input_dim: 1
input_dim: 3
input_dim: 416
input_dim: 416

修改为:

layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 3 dim: 416 dim: 416 } }
}

Reference:

https://github.com/marvis/pytorch-caffe-darknet-convert

https://github.com/lwplw/caffe_yolov2

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].