with Python 3.6 and Tensorflow r.1.14

This is an updated version of MonoGRNet. The original version is based on Python 2.7 and Tensorflow 1.4. Currently, I am using this Model for my own project and needed to update/adopt the code to Python 3.6 and Tensorflow 1.14. Please check the original Repository under https://github.com/Zengyi-Qin/MonoGRNet

• Ubuntu 18.04
• Python 3.6
• Tensorflow r1.14

Clone this repository

git clone https://github.com/SamGhK/MonoGRNet_python36.git

Download the Kitti Object Detection Dataset (image, calib and label) and place it into data/KittiBox. The folder should be in the following structure:

data
    KittiBox
        training
            calib
            image_2
            label_2
        train.txt
        val.txt

The train-val split train.txt and val.txt are contained in this repository.

Compile the Cython module and download the pretrained model:

python setup.py

Run the training script and specify the GPU to use:

python train.py --gpus 0

The evaluation is done during training. You can adjust the evaluation intervals in hypes/kittiBox.json.

cd visualize && mkdir visualize
python visualize.py

I would like to thank the original Authors for their great job and implementation. MonoGRNet