All Projects → HiKapok → Caffe_Rotate_Pool

HiKapok / Caffe_Rotate_Pool

Licence: Apache-2.0 License
Rotate RoI Align and Rotate Position Sensitive RoI Align Operation in Caffe

Programming Languages

Cuda
1817 projects
C++
36643 projects - #6 most used programming language

Projects that are alternatives of or similar to Caffe Rotate Pool

RoIAlign-RoIPool-pytorch
C++ extension implementation of RoIAlign & RolPool (both GPU and CPU) for PyTorch
Stars: ✭ 69 (+331.25%)
Mutual labels:  roipooling, roialign
CAM-Python
Class Activation Mapping with Caffe using the Python wrapper pycaffe instead of matlab.
Stars: ✭ 66 (+312.5%)
Mutual labels:  caffe
caffe-mobilenet-v3
Caffe Implementation of MobileNets V3
Stars: ✭ 127 (+693.75%)
Mutual labels:  caffe
FDCNN
The implementation of FDCNN in paper - A Feature Difference Convolutional Neural Network-Based Change Detection Method
Stars: ✭ 54 (+237.5%)
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 (-12.5%)
Mutual labels:  caffe
Face-Attributes-MultiTask-Classification
Use Cafffe to do Face Attributes MultiTask Classification based on CelebA data sets
Stars: ✭ 32 (+100%)
Mutual labels:  caffe
dd performances
DeepDetect performance sheet
Stars: ✭ 92 (+475%)
Mutual labels:  caffe
autodial
AutoDIAL Caffe Implementation
Stars: ✭ 28 (+75%)
Mutual labels:  caffe
kernelized correlation filters gpu
Real-time visual object tracking using correlations filters and deep learning
Stars: ✭ 27 (+68.75%)
Mutual labels:  caffe
XLearning-GPU
qihoo360 xlearning with GPU support; AI on Hadoop
Stars: ✭ 22 (+37.5%)
Mutual labels:  caffe
caffe-yolo-9000
caffe-yolo-9000
Stars: ✭ 49 (+206.25%)
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 (-12.5%)
Mutual labels:  caffe
all-classifiers-2019
A collection of computer vision projects for Acute Lymphoblastic Leukemia classification/early detection.
Stars: ✭ 24 (+50%)
Mutual labels:  caffe
nettutorial
Deep learning tutorial
Stars: ✭ 27 (+68.75%)
Mutual labels:  caffe
MobilenetSSD caffe
How to train and verify mobilenet by using voc pascal data in caffe ssd?
Stars: ✭ 25 (+56.25%)
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 (+150%)
Mutual labels:  caffe
Faster rcnn Cplusplus vs2013
faster-rcnn_VS2013with C++
Stars: ✭ 77 (+381.25%)
Mutual labels:  caffe
faster-rcnn-pedestrian-detection
Faster R-CNN for pedestrian detection
Stars: ✭ 31 (+93.75%)
Mutual labels:  caffe
uai-sdk
UCloud AI SDK
Stars: ✭ 34 (+112.5%)
Mutual labels:  caffe
Similarity-Adaptive-Deep-Hashing
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (TPAMI2018)
Stars: ✭ 18 (+12.5%)
Mutual labels:  caffe

Rotate RoI Align Pooling and Rotate Position Sensitive RoI Align Pooling in Caffe

This repository contains codes of two popular Rotate RoI Pooling operation in Caffe, modified from the regular implementation in codes.

Usage

  • You need firstly perform conversion from point-from (x1, y1, x2, y2, x3, y3, x4, y4) of the quadrilaterals to rotate bouding boxes in (x, y, w, h, angle). Please consider the following pseudo codes:

     pt1 = (x1, y1), pt2 = (x2, y2), pt3 = (x3, y3), pt4 = (x4, y4)
    
     edge1 = sqrt((pt1[0] - pt2[0]) ^ 2 + (pt1[1] - pt2[1]) ^ 2)
     edge2 = sqrt((pt2[0] - pt3[0]) ^ 2 + (pt2[1] - pt3[1]) ^ 2)
    
     width = min(edge1, edge2)
     height = max(edge1, edge2)
     
     if edge1 > edge2:
     	angle = 90.0 if pt1[0] - pt2[0] == 0 else -arctan((pt1[1] - pt2[1]) / (pt1[0] - pt2[0])) / pi * 180
     elif edge2 >= edge1:
     	angle = 90.0 if pt2[0] - pt3[0] == 0 else -arctan((pt2[1] - pt3[1]) / (pt2[0] - pt3[0])) / pi * 180
     while angle < -45.0:
     	angle = angle + 180
    
     x = (pt1[0] + pt3[0]) / 2.0
     y = (pt1[1] + pt3[1]) / 2.0
  • Now you can add these operation in caffe.proto and rebuild the library, then call with params similar as the regular ones

Apache License, Version 2.0

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].