November 28, 2019

354 words 2 mins read



Tensorflow Faster R-CNN for Windows/Linux and Python 3 (3.5/3.6/3.7)

repo name dBeker/Faster-RCNN-TensorFlow-Python3
repo link
language Python
size (curr.) 3487 kB
stars (curr.) 406
created 2017-06-09
license MIT License


Tensorflow Faster R-CNN for Windows and Linux by using Python 3

This is the branch to compile Faster R-CNN on Windows and Linux. It is heavily inspired by the great work done here and here. I have not implemented anything new but I fixed the implementations for Windows, Linux and Python 3.

Currently, this repository supports Python 3.5, 3.6 and 3.7. Thanks to @morpheusthewhite

PLEASE BE AWARE: I do not have time or intention to fix all the issues for this branch as I do not use it commercially. I created this branch just for fun. If you want to make any commitment, it is more than welcome. Tensorflow has already released an object detection api. Please refer to it.

If you find a solution to an existing issue in the code, please send a PR for it.

Also, instead of trying to deal with Tensorflow, use Chainer. It is ready to be used with all the common models & . I can reply all of your questions about Chainer

How To Use This Branch

  1. Install tensorflow, preferably GPU version. Follow instructions. If you do not install GPU version, you need to comment out all the GPU calls inside code and replace them with relavent CPU ones.

  2. Checkout this branch

  3. Install python packages (cython, python-opencv, easydict) by running
    pip install -r requirements.txt
    (if you are using an environment manager system such as conda you should follow its instruction)

  4. Go to ./data/coco/PythonAPI
    Run python build_ext --inplace
    Run python build_ext install
    Go to ./lib/utils and run python build_ext --inplace

  5. Follow these instructions to download PyCoco database. I will be glad if you can contribute with a batch script to automatically download and fetch. The final structure has to look like

  6. Download pre-trained VGG16 from here and place it as data\imagenet_weights\vgg16.ckpt.
    For rest of the models, please check here

  7. Run

Notify me if there is any issue found.

comments powered by Disqus