haralick-torch
GPU-accelerated Haralick texture extraction for GeoTIFF images using PyTorch.
Installation
GDAL must be installed via precompiled wheels:
https://github.com/cgohlke/geospatial-wheels/releases
pip install GDAL-3.10.1-cp310-cp310-win_amd64.whl
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install haralick-torch
Usage CLI
haralick-torch --input image.tif --out-texture textures.tif --out-pca pca.tif --nir-idx 8 --window 7 --levels 128 --tile 64
Usage API
import torch
from haralick_torch.io import read_nir_as_tensor, write_haralick_geotiff
from haralick_torch.haralick import compute_haralick
from haralick_torch.tiling import process_in_tiles
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
# ---- INPUT
img = "image.tif"
out = "haralick.tif"
nir_band = 4
# ---- IO
nir, ref_ds = read_nir_as_tensor(img, nir_band, DEVICE)
# ---- HARALICK
textures = process_in_tiles(
nir,
compute_haralick,
window=11,
stride=1
)
# ---- SAVE
write_haralick_geotiff(
out,
textures,
list(textures.keys()),
ref_ds
)
Metadata
Release files for haralick-torch 1.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| haralick_torch-1.1.0.tar.gz | 5.5 kB | Without provenance | Details for haralick_torch-1.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| haralick_torch-1.1.0-py3-none-any.whl | Python 3 | none | any | Details for haralick_torch-1.1.0-py3-none-any.whl |
Total release size: 12.4 kB
Release files / haralick_torch-1.1.0.tar.gz
| Download URL | haralick_torch-1.1.0.tar.gz |
|---|---|
| Size | 5.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c5a4eb2c59c876348dbe83c8ffe8d18be20f77fe2b51d91b4d96e35300dc6816
|
|
BLAKE2b-256 checksum How to use checksums |
37fb54cd5b0f8a86fe36667b845bc3ddb47b7c0b9daa9eaee92ff544ee8fc744
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Release files / haralick_torch-1.1.0-py3-none-any.whl
| Download URL | haralick_torch-1.1.0-py3-none-any.whl |
|---|---|
| Size | 6.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
787952dc5e5ad041fdda42bf29ceae66c0bea83c0abfcc04d81f17b6ee41d9b8
|
|
BLAKE2b-256 checksum How to use checksums |
7a651458c67c84d7551fc0c23cde5356442b47d21011f3b4982d7d1f41725caa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Security for haralick-torch 1.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.