Documentation
This section collects technical notes and usage guides for StarNet and DeepSNR: command-line references, input behavior, data-quality guidance, and workflow examples.
StarNet command-line tool reference
This page describes the current StarNet command-line options, example commands, supported inputs, and output behavior.
Running options
USAGE:
starnet2 [-ehqu] [--version] [-i <string>] [-m <string>]
[-n <string>] [-o <string>] [-s <int>] [-w <string>]
Options:
-i <string>, --input <string>
Input image filename. Supported sample depths: 8-bit and 16-bit integer.
-o <string>, --output <string>
Output image filename. TIF/PNG default to 16-bit unless --eight is used.
-m <string>, --mask <string>
Optional mask output filename. Disabled unless provided. TIF/PNG default
to 16-bit unless --eight is used.
-n <string>, --unscreen <string>
Unscreen star-layer output filename. TIF/PNG default to 16-bit unless
--eight is used.
-w <string>, --weights <string>
Override path to the model checkpoint. Normally omit this option.
-s <int>, --stride <int>
Stride value. Must be even and between 2 and 512.
-u, --upsample
Use intermediate 2x upsampling.
-q, --quiet
Run quietly with no terminal output.
-e, --eight
Write TIF and PNG starless, mask, and unscreen outputs as 8-bit instead
of the default 16-bit.
--, --ignore_rest
Ignores the rest of the labeled arguments following this flag.
--version
Displays version information and exits.
-h, --help
Displays usage information and exits.
CLI interface for StarNet2 w/ ONNX Runtime backend.
StarNet2 v2.5.0 Example commands
- Write a starless image
starnet2 --input input.tif --output starless.tif- Write a starless image and subtractive star mask
starnet2 --input input.tif --output starless.tif --mask starmask.tif- Write a starless image and unscreen star layer
starnet2 --input input.tif --output starless.tif --unscreen stars.tif- Use 2× upsampling for a difficult image
starnet2 --input input.tif --output starless.tif --upsample- Write all StarNet outputs in one run
starnet2 --input input.tif --output starless.tif --mask starmask.tif --unscreen stars.tif- Force 8-bit TIFF or PNG output
starnet2 --input input.tif --output starless.png --eight
Inputs and outputs
- File formats
- The image reader accepts common OpenCV-readable formats including TIFF, PNG, JPEG, and BMP.
- Bit depth
- 8-bit and 16-bit integer inputs are supported. 16-bit TIFF/PNG input is preserved and normalized as 16-bit. Unsupported input depths, including 32-bit floating-point images, are rejected; convert them to 16-bit integer before running the tool.
- Color and grayscale
- RGB/color and grayscale inputs are accepted. Images with alpha channels or other channel counts are rejected.
- Image size
- Images must be at least 512 × 512 pixels in normal mode.
- Default output depth
- TIFF and PNG outputs are written as 16-bit integer images by default.
--eight- Use this only when you intentionally want 8-bit TIFF or PNG output. It applies to starless, mask, and unscreen outputs.
StarNet-specific options
--mask,-m- Writes an optional mask output. Use it when the workflow needs a mask rather than only a starless image.
--unscreen,-n- Writes an unscreen star-layer output. This is independent from
--mask; either, both, or neither optional output can be requested. --upsample,-u- Uses intermediate 2× upsampling. Use it for tight stars or difficult structures; expect higher runtime cost.
- Short option clustering
- Short boolean switches can be combined. For example,
-equis equivalent to-e -q -u. Options that take values, such as-i,-o,-m,-n,-w, and-s, must be provided separately.