Skip to content
Other

DCAP: Landslide Segmentation Checkpoints

1 min readupdated

The model implements the Detail–Context Adaptive Structured Pruning approach for precise detection and segmentation of landslides using satellite or multi-channel data. The release features two ensemble builds: Dense ResUNet and DCAP70, each utilizing probability averaging across three seeds. It accepts specialized 21-channel reflectance and change features as input. The solution is designed for researchers and specialists in remote sensing and geological hazard analysis.

Key features

  • Includes Dense ResUNet and DCAP70 checkpoints for precise analysis
  • Utilizes a three-member ensemble with predicted probability averaging
  • Processes complex 21-channel reflectance and change input data
  • Distributed under the permissive MIT license with full reproduction instructions

What you can do

  • Evaluate model performance using the official project CLI tool
  • Integrate the checkpoints into remote sensing data processing pipelines
  • Benchmark the Dense ResUNet and DCAP70 ensembles on custom datasets
  • Reproduce the results following the official repository guide

Example

hf download ghimiredhikura/DCAP --include "*.pt" --include MODEL_NOTICES.txt --local-dir downloads/models
python -m dcap models install --source downloads/models
Read moreDetails
Architecture: Dense ResUNet and DCAP70
Input data: 21-channel reflectance and change features
Ensembles: Probability averaging of three seed models
License: MIT
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 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 · BF16 — 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.

    # ghimiredhikura/DCAP
    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 ghimiredhikura/DCAP --local-dir ~/models/DCAP
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to DCAP
  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 DCAP (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

ghimiredhikura/DCAP
Author
ghimiredhikura
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

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

Comments