Skip to content
Other

Everglades bird behavior classifier

aerial imagery model

2 min readupdated

This model analyzes aerial photos from Everglades National Park to tell what a wading bird is doing: nesting or roosting. Built on the DeepForest library (an ecosystem imagery analysis tool) with an ImageNet ResNet-50 architecture (a computer vision model), it processes 100x100-pixel bird crops extracted by a detector. It is a useful tool for ornithologists and ecologists monitoring bird colonies from aerial surveys.

Key features

  • Tailored to Everglades species: trained on survey data covering white ibises, wood storks, and other wading birds.
  • High accuracy: reaches an overall Accuracy of 0.93 on the validation set.
  • Easy integration: works as a CropModel add-on paired with the DeepForest bird detector.
  • Balanced training: uses data augmentation, class balancing, and 224-pixel crop windows.

What you can do

  • Classify birds in aerial photos: automatically sort detected birds into nesting and roosting groups.
  • Analyze colonies: process aerial imagery from wildlife reserves to monitor wetland bird populations.
  • Extend ecological pipelines: pair the model with the weecology/everglades-bird-airplane detector.

Example

from deepforest import main
from deepforest.model import CropModel

detector = main.deepforest()
detector.load_model("weecology/everglades-bird-airplane")
crop_model = CropModel.load_model("weecology/everglades-airplane-roosting-classifier")
crop_model.config["cropmodel"]["expand"] = 25
birds = detector.predict_tile(path="DSC_2226.JPG", patch_size=800)
Read moreDetails
Metrics: Accuracy 0.93, mean per-class Recall 0.86
Architecture: DeepForest CropModel (ImageNet ResNet-50)
Limitations: data collected from a single camera type during one season in 2022
Dataset: 4,853 birds across 11 Everglades colonies
Discuss Telegram 0 23

Will it run?

Runs in F32

Fits without quantisation.

  • F32weights 0.1 GB · ready files0.6 GB
  • BF16weights 0.0 GB0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · F32 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # weecology/everglades-airplane-roosting-classifier
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download weecology/everglades-airplane-roosting-classifier --local-dir ~/models/everglades-airplane-roosting-classifier
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of everglades-airplane-roosting-classifier (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

weecology/everglades-airplane-roosting-classifier
Author
weecology
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

230

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments