Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LQDM

Installation

Create a new conda environment, and install the dependencies:

conda create -n lqdm
conda activate lqdm
conda install python pytorch torchvision -c pytorch -y
python3 -m pip install -r requirements.txt

Data

Download the data and model checkpoint from here. Create a new directory datasets/ from the project root, and place the ZIP file inside. Create a new directory checkpoints/ from the project root, and place the checkpoint file inside.

Running the code

Training

python3 main.py fit -c configs/lqds.yaml --trainer.devices 4 --data.batch_size 4 --data.path
data/

This will train the model from scratch using the dataset from the config. Replace with the number of GPUs and the batch size based on available memory.

Validation

python3 main.py validate -c configs/lqds.yaml --trainer.devices 1 --data.batch_size 4 --data.path data/ --model.ckpt_path checkpoints/model.ckpt

This will evaluate metrics for a trained model checkpoint.

About

Data and code for "Learning to Segment Liquids in Real-world Images" (IROS 2026)

Resources

Stars

Watchers

Forks

Contributors

Languages