GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → karta0807913 → caffe-yolo-9000

karta0807913 / caffe-yolo-9000

Licence: other
caffe-yolo-9000

Programming Languages

C++
36643 projects - #6 most used programming language
python
139335 projects - #7 most used programming language
Cuda
1817 projects
CMake
9771 projects
matlab
3953 projects
Makefile
30231 projects

Labels

caffecaffe-yolo-9000

Projects that are alternatives of or similar to caffe-yolo-9000

theWorldInSafety
Surveillance System Against Violence
Stars: ✭ 31 (-36.73%)
Mutual labels:  caffe
How to write cuda extensions in pytorch
How to write cuda kernels or c functions in pytorch, especially for former caffe users.
Stars: ✭ 51 (+4.08%)
Mutual labels:  caffe
nettutorial
Deep learning tutorial
Stars: ✭ 27 (-44.9%)
Mutual labels:  caffe
EmotionChallenge
Source code for 1st winner of face micro-emotion competition, FG 2017.
Stars: ✭ 37 (-24.49%)
Mutual labels:  caffe
facial-landmarks
Facial landmarks detection with OpenCV, Dlib, DNN
Stars: ✭ 25 (-48.98%)
Mutual labels:  caffe
darknet2caffe
Conversion of yolo from DarkNet to Caffe
Stars: ✭ 25 (-48.98%)
Mutual labels:  caffe
superpixelRefinement
Superpixel-based Refinement for Object Proposal Generation (ICPR 2020)
Stars: ✭ 24 (-51.02%)
Mutual labels:  caffe
SSD Tracker
Counting people, dog and bicycle using SSD detection and tracking.
Stars: ✭ 17 (-65.31%)
Mutual labels:  caffe
ddrl
Deep Developmental Reinforcement Learning
Stars: ✭ 27 (-44.9%)
Mutual labels:  caffe
caffe-mobilenet-v3
Caffe Implementation of MobileNets V3
Stars: ✭ 127 (+159.18%)
Mutual labels:  caffe
nsfw api
Python REST API to detect images with adult content
Stars: ✭ 71 (+44.9%)
Mutual labels:  caffe
caffe
Caffe: a Fast framework for deep learning. Custom version with built-in sparse inputs, segmentation, object detection, class weights, and custom layers
Stars: ✭ 36 (-26.53%)
Mutual labels:  caffe
dd performances
DeepDetect performance sheet
Stars: ✭ 92 (+87.76%)
Mutual labels:  caffe
Caffe-installation-Raspberry-Pi-3
No description or website provided.
Stars: ✭ 23 (-53.06%)
Mutual labels:  caffe
TensorRT-LPR
车牌识别，基于HyperLPR实现，修改模型调用方法，使用caffe+tensorRT实现GPU加速，修改了车牌检测模型
Stars: ✭ 14 (-71.43%)
Mutual labels:  caffe
adversarial-attacks
Code for our CVPR 2018 paper, "On the Robustness of Semantic Segmentation Models to Adversarial Attacks"
Stars: ✭ 90 (+83.67%)
Mutual labels:  caffe
R2CNN
caffe re-implementation of R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
Stars: ✭ 80 (+63.27%)
Mutual labels:  caffe
Faster rcnn Cplusplus vs2013
faster-rcnn_VS2013with C++
Stars: ✭ 77 (+57.14%)
Mutual labels:  caffe
vqa-soft
Accompanying code for "A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models" CVPR 2017 VQA workshop paper.
Stars: ✭ 14 (-71.43%)
Mutual labels:  caffe
caffe
This fork of BVLC/Caffe is dedicated to supporting Cambricon deep learning processor and improving performance of this deep learning framework when running on Machine Learning Unit(MLU).
Stars: ✭ 40 (-18.37%)
Mutual labels:  caffe
View All Similar Projects ➔

CAFFE for YOLO-9000

Reference

YOLO9000: Better, Faster, Stronger

https://arxiv.org/abs/1612.08242

https://pjreddie.com/darknet/yolo/

https://github.com/yeahkun/caffe-yolo

Usage

Data preparation

  ln -s /your/path/to/VOCdevkit/ .
  python data/yolo/get_list.py
  cd data/yolo
  # change related path in script convert.sh
  ./convert.sh

Train

  cd examples/yolo
  # change related path in script train.sh and darknet.prototxt
  ./train.sh

Test

weight

https://drive.google.com/open?id=0Bx1yEotM0mQeM3ZPRmhFSHAydUE

binaryproto

https://drive.google.com/open?id=0Bx1yEotM0mQeTE9XYWJjazZTLUE

some image

http://imgur.com/a/mXhat

  cd build/example/yolo_9000_test/
  ./netforward ../../../examples/yolo/darknet_deploy.prototxt path/to/voc_model_iter_30000.caffemode path/to/voc_train.binaryproto test_list > output.txt

test list is a txt file llike

  /VOCdevkit/VOC2007/JPEGImages/000001.jpg
  /VOCdevkit/VOC2007/JPEGImages/000002.jpg
  /VOCdevkit/VOC2007/JPEGImages/000003.jpg
  ...

it will output <label,x,y,w,h> per image

TODO

world tree reorg layer Image Net Pretrain

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].