Add pytorch darknet to caffe code and demo script

README.md

@@ -80,56 +80,6 @@ If load success , you can see the image window like this
 
 ![alt tag](00002.jpg)
 
-### Vehicle Dection 
-
-[![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/oagXgyQHuNA/0.jpg)](https://www.youtube.com/watch?v=oagXgyQHuNA)
-
-#### CLASS NAME
-
-```
-char* CLASSES2[6] = { "__background__","bicycle", "car", "motorbike", "person","cones" };
-```
-
-[model](models/vehicle)
-
-## Maintenance
-
-I'll appreciate  if you can help me to 
-
-1. Miragrate to [modivius neural compute stick](https://github.com/eric612/YoloV2-MobileNet-NCS)
-2. Mobilenet upgrade to v2 or model tunning
-
-## Caffe 
-
-[![Build Status](https://travis-ci.org/BVLC/caffe.svg?branch=master)](https://travis-ci.org/BVLC/caffe)
-[![License](https://img.shields.io/badge/license-BSD-blue.svg)](LICENSE)
-
-Caffe is a deep learning framework made with expression, speed, and modularity in mind.
-It is developed by Berkeley AI Research ([BAIR](http://bair.berkeley.edu))/The Berkeley Vision and Learning Center (BVLC) and community contributors.
-
-Check out the [project site](http://caffe.berkeleyvision.org) for all the details like
-
-- [DIY Deep Learning for Vision with Caffe](https://docs.google.com/presentation/d/1UeKXVgRvvxg9OUdh_UiC5G71UMscNPlvArsWER41PsU/edit#slide=id.p)
-- [Tutorial Documentation](http://caffe.berkeleyvision.org/tutorial/)
-- [BAIR reference models](http://caffe.berkeleyvision.org/model_zoo.html) and the [community model zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo)
-- [Installation instructions](http://caffe.berkeleyvision.org/installation.html)
-
-and step-by-step examples.
-
-## Custom distributions
-
- - [Intel Caffe](https://github.com/BVLC/caffe/tree/intel) (Optimized for CPU and support for multi-node), in particular Xeon processors (HSW, BDW, SKX, Xeon Phi).
-- [OpenCL Caffe](https://github.com/BVLC/caffe/tree/opencl) e.g. for AMD or Intel devices.
-- [Windows Caffe](https://github.com/BVLC/caffe/tree/windows)
-
-## Community
-
-[![Join the chat at https://gitter.im/BVLC/caffe](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/BVLC/caffe?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
-
-Please join the [caffe-users group](https://groups.google.com/forum/#!forum/caffe-users) or [gitter chat](https://gitter.im/BVLC/caffe) to ask questions and talk about methods and models.
-Framework development discussions and thorough bug reports are collected on [Issues](https://github.com/BVLC/caffe/issues).
-
-Happy brewing!
 
 ## License and Citation
 

demo_darknet_yolov3.sh

@@ -0,0 +1 @@
+./examples/ssd/ssd_detect models/darknet_yolov3/yolov3.prototxt models/darknet_yolov3/yolov3.caffemodel -file_type image -wait_time 1500 -mean_value 0.0,0.0,0.0 -normalize_value 0.0039215 -confidence_threshold 0.2

examples/ssd/ssd_detect.cpp

@@ -34,8 +34,30 @@
 //char* CLASSES[6] = { "__background__",
 //"bicyle", "car", "motorbike", "person","cones"
 //};
-char* CLASSES[5] = { "__background__",
-"big car","car", "motorbike","person"
+//char* CLASSES[5] = { "__background__",
+//"big car","car", "motorbike","person"
+//};
+char* CLASSES[81] = { "__background__",
+"person", "bicycle", "car", "motorcycle",
+"airplane", "bus", "train", "truck", "boat",
+"traffic light", "fire hydrant", "stop sign", "parking meter",
+"bench", "bird", "cat",
+"dog", "horse", "sheep", "cow" 
+"elephant", "bear", "zebra", "giraffe" ,
+"backpack", "umbrella", "handbag", "tie" ,
+"suitcase", "frisbee", "skis", "snowboard" ,
+"sports ball", "kite", "baseball bat", "baseball glove" ,
+"skateboard", "surfboard", "tennis racket", "bottle" ,
+"wine glass", "cup", "fork", "knife" ,
+"spoon", "bowl", "banana", "apple" ,
+"sandwich", "orange", "broccoli", "carrot" ,
+"hot dog", "pizza", "donut", "cake" ,
+"chair", "sofa", "potted plant", "bed" ,
+"dining table", "toilet", "tv", "laptop" ,
+"mouse", "remote", "keyboard", "cell phone" ,
+"microwave", "oven", "toaster", "sink" ,
+"refrigerator", "book", "clock", "vase" ,
+"scissors", "teddy bear", "hair drier", "toothbrush" ,
 };
 #else
 char* CLASSES[21] = { "__background__",

models/darknet_yolov3/README.md

@@ -0,0 +1,29 @@
+# Pytorch darknet to caffe 
+
+Modify from [pytorch-caffe-darknet-convert](https://github.com/marvis/pytorch-caffe-darknet-convert),[object_detetction_tools](https://github.com/BingzheWu/object_detetction_tools)
+
+## Modified items :
+
+1. yolov3 output layer
+2. when pooling layer stide =1 , size =2 , assign size = 1
+3. upsample layer 
+
+## Usage : 
+
+1. Download weights from original darknet web
+2. Unmark custom_class in examples\ssd\ssd_detect.cpp
+3. Remake project
+
+```
+> python darknet2caffe.py yolov3.cfg yolov3.weights yolov3.prototxt yolov3.caffemodel
+> cd $caffe_root
+> sh demo_darknet_yolov3.sh
+```
+
+
+## To do list :
+
+1. verify accuracy and compare result
+2. retrain
+
+I'm not sure the result was same as darknet now , contribution is welcome