All Projects → murphypei → faster-rcnn-pedestrian-detection

murphypei / faster-rcnn-pedestrian-detection

Licence: MIT License
Faster R-CNN for pedestrian detection

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language
shell
77523 projects
c
50402 projects - #5 most used programming language
Cuda
1817 projects
matlab
3953 projects

Projects that are alternatives of or similar to faster-rcnn-pedestrian-detection

Unreal caffe
Self Maintained Caffe. In this version Faster-RCNN, RFCN needs layer are fully supported!
Stars: ✭ 38 (+22.58%)
Mutual labels:  caffe, faster-rcnn
Faster Rcnn Cplusplus2
faster-rcnn c++ python model
Stars: ✭ 14 (-54.84%)
Mutual labels:  caffe, faster-rcnn
Py Rfcn Priv
code for py-R-FCN-multiGPU maintained by bupt-priv
Stars: ✭ 153 (+393.55%)
Mutual labels:  caffe, faster-rcnn
Bottom Up Attention
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
Stars: ✭ 989 (+3090.32%)
Mutual labels:  caffe, faster-rcnn
Faster rcnn Cplusplus vs2013
faster-rcnn_VS2013with C++
Stars: ✭ 77 (+148.39%)
Mutual labels:  caffe, faster-rcnn
Caffe Model
Caffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+3958.06%)
Mutual labels:  caffe, faster-rcnn
crowd density segmentation
The code for preparing the training data for crowd counting / segmentation algorithm.
Stars: ✭ 21 (-32.26%)
Mutual labels:  caffe, pedestrian-detection
dd performances
DeepDetect performance sheet
Stars: ✭ 92 (+196.77%)
Mutual labels:  caffe
VisDrone-dataset-python-toolkit
This repository provides a basic Pythonic toolkit for the VisDrone-Dataset (2018).
Stars: ✭ 30 (-3.23%)
Mutual labels:  faster-rcnn
R2CNN
caffe re-implementation of R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
Stars: ✭ 80 (+158.06%)
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 (+64.52%)
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 (+29.03%)
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 (-54.84%)
Mutual labels:  caffe
darknet2caffe
Conversion of yolo from DarkNet to Caffe
Stars: ✭ 25 (-19.35%)
Mutual labels:  caffe
XLearning-GPU
qihoo360 xlearning with GPU support; AI on Hadoop
Stars: ✭ 22 (-29.03%)
Mutual labels:  caffe
Faster-RCNN-Pytorch-Simple
No description or website provided.
Stars: ✭ 24 (-22.58%)
Mutual labels:  faster-rcnn
FDCNN
The implementation of FDCNN in paper - A Feature Difference Convolutional Neural Network-Based Change Detection Method
Stars: ✭ 54 (+74.19%)
Mutual labels:  caffe
caffe-yolo-9000
caffe-yolo-9000
Stars: ✭ 49 (+58.06%)
Mutual labels:  caffe
CFUN
Combining Faster R-CNN and U-net for efficient medical image segmentation
Stars: ✭ 109 (+251.61%)
Mutual labels:  faster-rcnn
pytorch-faster-rcnn
No description or website provided.
Stars: ✭ 45 (+45.16%)
Mutual labels:  faster-rcnn

Pedestrian-RCNN

This code extends py-faster-rcnn by adding:

  • ResNet implementation.
  • Online Hard Example Mining.
  • Caltech Dataset train and test interface.
  • Add RPN tools.

Base

Installation

The installation and useage are same as Faster R-CNN

  1. clone the repository and caffe submodule
  2. build lib and caffe
  3. train your model command like: ./experiments/scripts/faster_rcnn_end2end.sh 0 ResNet50 caltech_reasonable

Notices

For different datasets, the interval frame rate is different, so it need to be changed.

In ./lib/datasets/caltech.py, change the start_frame and frame_rate of insert_frame function.

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].