Welcome to DeepForest documentation!

DeepForest is a python package for predicting individual tree crowns from RGB imagery. Source code is available here: (https://github.com/weecology/DeepForest.git).

Contents:

• What is DeepForest?
• What’s new in DeepForest 1.0.0?
  • How does deepforest work?
  • Demo
  • License
  • Why DeepForest?
  • Feedback
  • Citation
• Installation
  • conda/mamba CPU
  • conda/mamba GPU
  • Source Installation
  • GPU support
• Getting started
  • Prebuilt models
  • Sample data
  • Prediction
    • Predict a single image
    • Predict a tile
    • Predict a set of annotations
    • Projecting predictions
    • Customizing box appearance for predictions
  • Training
    • Video walkthrough of colab
  • Reducing tile size
    • Negative samples
    • Model checkpoints
    • New Augmentations
  • Evaluation
    • Negative Samples
    • Saving and loading models
  • Multi-class models
  • Issues
• Config
  • Dataloaders
    • workers
    • devices
    • accelerator
    • batch_size
    • nms_thresh
    • score_thresh
  • Train
    • csv_file
    • root_dir
    • lr
    • Epochs
    • fast_dev_run
    • preload_images
  • Validation
    • csv_file
    • root_dir
    • val_accuracy_interval
• Evaluation
  • Evaluating tiles
• Using DeepForest from R
  • Installation
    • Basic Installation
    • Advanced Installation for Python Users
  • Getting Started
    • Load the current release model
    • Predict a single image
    • Predict a tile
    • Predict a set of annotations
    • Training
    • Evaluation
    • Saving & Loading Models
• FAQ
  • Exception: RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0
  • I cannot reload a saved multi-class model using a checkpoint.
  • Weakly referenced objects
    • Saving
    • Training
  • How do I reduce double counting in overlapping images?
  • Issues
• How do I make the predictions better?
  • Check patch size
  • IoU threshold
  • Annotate local training data
  • Issues
• Extending the deepforest module
• Contributor Code of Conduct
  • Our Pledge
  • Our Standards
  • Our Responsibilities
  • Scope
  • Enforcement
  • Attribution
• Bird Detector
  • Predict a folder of images and create a shapefile of annotations for each image
  • Annotating new images
  • Multi-species models
  • Citation
• DeepForest Change Log
• deepforest package
  • Subpackages
    • deepforest.data package
  • Submodules
  • deepforest.IoU module
    • compute_IoU()
    • create_rtree_from_poly()
  • deepforest.callbacks module
    • images_callback
  • deepforest.dataset module
    • TreeDataset
    • get_transform()
  • deepforest.evaluate module
    • compute_class_recall()
    • evaluate()
    • evaluate_image()
  • deepforest.main module
    • deepforest
  • deepforest.model module
    • create_anchor_generator()
    • create_model()
    • load_backbone()
  • deepforest.predict module
    • across_class_nms()
    • predict_file()
    • predict_image()
    • predict_tile()
    • soft_nms()
  • deepforest.preprocess module
    • compute_windows()
    • image_name_from_path()
    • preprocess_image()
    • save_crop()
    • select_annotations()
    • split_raster()
  • deepforest.utilities module
    • DownloadProgressBar
    • annotations_to_shapefile()
    • boxes_to_shapefile()
    • check_file()
    • check_image()
    • collate_fn()
    • project_boxes()
    • read_config()
    • round_with_floats()
    • shapefile_to_annotations()
    • use_bird_release()
    • use_release()
    • xml_to_annotations()
  • deepforest.visualize module
    • format_boxes()
    • label_to_color()
    • plot_prediction_and_targets()
    • plot_prediction_dataframe()
    • plot_predictions()
    • view_dataset()
  • Module contents
    • get_data()
• Authors
  • Primary Authors
  • Other Contributors
• DeepForest
  • deepforest package
    • Subpackages
    • Submodules
    • deepforest.IoU module
    • deepforest.callbacks module
    • deepforest.dataset module
    • deepforest.evaluate module
    • deepforest.main module
    • deepforest.model module
    • deepforest.predict module
    • deepforest.preprocess module
    • deepforest.utilities module
    • deepforest.visualize module
    • Module contents
• Software & Research Using DeepForest
  • Software
  • Research
    • 2023
    • 2022
    • 2021
    • 2020
    • 2019
• Developer’s guide
  • Getting started
  • Testing
    • Running tests locally
    • Testing Conda Deepforest build
    • Conda staged recipe update
  • Documentation

Indices and tables

• Index

• Module Index

• Search Page