aiDoseBooster

aiDoseBooster denoises a single image or an entire tilt series using a previously trained neural network.

aiDoseBooster can be used without a configuration file and all parameters can be provided by command line arguments. For convenience, parameters can also be given using a configuration file with the -u command line argument. Note: If a parameter is passed by file and by command line, the command line overrides the file.

Options are:

CudaDeviceID

The deviceID of the GPU to use.
Argument for command line: -d or –CudaDeviceID
Type: int
Option is mandatory: false
Default value if not set: 0

Input

The file to process.
Argument for command line: -i or –Input
Type: string
Option is mandatory: true

Output

The file to write the result to. If not provided the input file is appended by ‘Denoised’
Argument for command line: -o or –Output
Type: string
Option is mandatory: false
Default value if not set: ’’

Network

The file with the trained network configuration.
Argument for command line: -n or –Network
Type: string
Option is mandatory: true

Scale

The denoised image values are scaled by this factor.
Argument for command line: -s or –Scale
Type: float
Option is mandatory: false
Default value if not set: 1

Offset

The denoised image values are offset by this value (after scaling).
Argument for command line: -off or –Offset
Type: float
Option is mandatory: false
Default value if not set: 0

OutputDataType

The datatype of the aligned image.
Argument for command line: -dt or –OutputDataType
Type: one of [FLOAT, SAME, SHORT, UCHAR, USHORT]
Option is mandatory: false
Default value if not set: SAME
Possible notations:

  • FLOAT: FLOAT, float, Float
  • SAME: SAME, same, Same
  • SHORT: SHORT, short, Short
  • UCHAR: UCHAR, uchar, Uchar, UChar
  • USHORT: USHORT, ushort, Ushort, UShort