clw5180 / monoconx Goto Github PK

This repository is an unofficial implementation of the paper MonoCon for personal study. We will continuously update it for better performance.

This repo benefits from MonoDLE and MonoCon.

This repo is tested on our local environment (python=3.7, cuda=10.1, pytorch=1.5.1), and we recommend you to use anaconda to create a vitural environment:

conda create -n monodle python=3.7

Then, activate the environment:

conda activate mono3d

Install Install PyTorch:

conda install pytorch==1.5.1 torchvision==0.6.1 cudatoolkit=10.1 -c pytorch

and other requirements:

pip install -r requirements.txt

Please download KITTI dataset and organize the data as follows:

#ROOT
  |data/
    |KITTI/
      |ImageSets/ [already provided in this repo]
      |object/			
        |training/
          |calib/
          |image_2/
          |label/
        |testing/
          |calib/
          |image_2/

Move to the workplace and train the network:

 cd #ROOT
 cd experiments/example
 python ../../tools/train_val.py --config kitti_example.yaml

The model will be evaluated automatically if the training completed. If you only want evaluate your trained model (or the provided pretrained model) , you can modify the test part configuration in the .yaml file and use the following command:

python ../../tools/train_val.py --config kitti_example.yaml --e