Published February 21, 2024
| Version 2.0.0
Dataset
Open
A Construction Waste Landfill Dataset of Two Districts in Beijing, China from High Resolution Satellite Images
Creators
- 1. huang-lei@emails.bjut.edu.cn
- 2. linshaofu@bjut.edu.cn
- 3. liuxl@bjut.edu.cn
Description
CWLD_model project shows scripts and instructions on how to use this dataset to train a segmentation model. requirements.txt files provide the libraries you need to run your project. The README.md document details the deployment process and features of each module.
You can also visit the GitHub page for scripts and instructions on how to use this dataset for visualizing and plotting basic statistics. The models and the code to execute them are released on https://github.com/huangleinxidimejd/CWLD_Model.
Training details
The model was trained with two GPUs, an Nvidia GeForce RTX 2080Ti, and the following parameters:
- 'train_batch_size': 4,
- 'val_batch_size': 4,
- 'train_crop_size': 512,
- 'val_crop_size': 512,
- 'lr': 0.001, # the learning rate used during training. It determines how quickly the model learns from the data
- 'Epoch Times': 200,
- 'gpu': correct,
- 'weight_decay': 5E-4,
- 'Momentum': 0.9,
- 'print_freq': 100,
- 'predict_step': 5,
usage
- After downloading the dataset from Zenodo, place the train and val files from the Deep Learning Datasets file into the data folder of the CWLD semantic segmentation model.
- Open: CWLD_ Open the root directory in CWLD_model/dataset/ and start training with the WasteSeg_Train.py file. The modelss module provides five convolutional networks, Improved_DeeplabV3_plus, PSPNet, ResNet, SegNet, and UNet, which can be selected and modified accordingly.
- The utils package provides a large number of data processing tools to use.
- The trained model can be predicted from a EvalSeg.py file.
Files
CWLD_model.zip
Files
(530.5 MB)
Name | Size | Download all |
---|---|---|
md5:74d94ffaf2e3b31b15f2cd9fcb8e115b
|
530.5 MB | Preview Download |
Additional details
References
- Torres, Rocio Nahime and Fraternali, Piero. "AerialWaste dataset for landfill discovery in aerial and satellite images." Scientific Data, vol. 10, no.1, p.63, 2023.
- L. Zhou et al., "SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 306-320, 2023, doi: 10.1109/JSTARS.2022.3218958.