本文整理汇总了Python中thunder.rdds.fileio.imagesloader.ImagesLoader.fromStack方法的典型用法代码示例。如果您正苦于以下问题：Python ImagesLoader.fromStack方法的具体用法？Python ImagesLoader.fromStack怎么用？Python ImagesLoader.fromStack使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类thunder.rdds.fileio.imagesloader.ImagesLoader的用法示例。
在下文中一共展示了ImagesLoader.fromStack方法的8个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: loadImages
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
def loadImages(self, datapath, dims=None, inputformat='stack', dtype='int16', startidx=None, stopidx=None):
"""
Loads an Images object from data stored as a binary image stack, tif, tif-stack, or png files.
Supports single files or multiple files, stored on a local file system, a networked file sytem
(mounted and available on all nodes), or Amazon S3. HDFS is not currently supported for image file data.
Parameters
----------
datapath: string
Path to data files or directory, specified as either a local filesystem path or in a URI-like format,
including scheme. A datapath argument may include a single '*' wildcard character in the filename. Examples
of valid datapaths include 'a/local/relative/directory/*.stack", "s3n:///my-s3-bucket/data/mydatafile.tif",
"/mnt/my/absolute/data/directory/", or "file:///mnt/another/data/directory/".
dims: tuple of positive int, optional (but required if inputformat is 'stack')
Dimensions of input image data, similar to a numpy 'shape' parameter, for instance (1024, 1024, 48). Binary
stack data will be interpreted as coming from a multidimensional array of the specified dimensions. Stack
data should be stored in row-major order (Fortran or Matlab convention) rather than column-major order (C
or python/numpy convention), where the first dimension corresponds to that which is changing most rapidly
on disk. So for instance given dims of (x, y, z), the coordinates of the data in a binary stack file
should be ordered as [(x0, y0, z0), (x1, y0, zo), ..., (xN, y0, z0), (x0, y1, z0), (x1, y1, z0), ...,
(xN, yM, z0), (x0, y0, z1), ..., (xN, yM, zP)].
If inputformat is 'png', 'tif', or'tif-stack', the dims parameter (if any) will be ignored; data dimensions
will instead be read out from the image file headers.
inputformat: {'stack', 'png', 'tif', 'tif-stack'}. optional, default 'stack'
Expected format of the input data. 'stack' indicates flat files of raw binary data. 'png' or 'tif' indicate
two-dimensional image files of the corresponding formats. 'tif-stack' indicates a sequence of multipage tif
files, with each page of the tif corresponding to a separate z-plane.
For all formats, separate files are interpreted as distinct time points, with ordering given by
lexicographic sorting of file names.
This method assumes that stack data consists of signed 16-bit integers in native byte order. Data types of
image file data will be as specified in the file headers.
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string. If inputformat is
'tif-stack', the dtype parameter (if any) will be ignored; data type will instead be read out from the
tif headers.
startidx: nonnegative int, optional
startidx and stopidx are convenience parameters to allow only a subset of input files to be read in. These
parameters give the starting index (inclusive) and final index (exclusive) of the data files to be used
after lexicographically sorting all input data files matching the datapath argument. For example,
startidx=None (the default) and stopidx=10 will cause only the first 10 data files in datapath to be read
in; startidx=2 and stopidx=3 will cause only the third file (zero-based index of 2) to be read in. startidx
and stopidx use the python slice indexing convention (zero-based indexing with an exclusive final position).
stopidx: nonnegative int, optional
See startidx.
Returns
-------
data: thunder.rdds.Images
A newly-created Images object, wrapping an RDD of <int index, numpy array> key-value pairs.
"""
checkparams(inputformat, ['stack', 'png', 'tif', 'tif-stack'])
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputformat.lower() == 'stack':
data = loader.fromStack(datapath, dims, dtype=dtype, startidx=startidx, stopidx=stopidx)
elif inputformat.lower() == 'tif':
data = loader.fromTif(datapath, startidx=startidx, stopidx=stopidx)
elif inputformat.lower() == 'tif-stack':
data = loader.fromMultipageTif(datapath, startidx=startidx, stopidx=stopidx)
else:
data = loader.fromPng(datapath)
return data示例2: convertImagesToSeries
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
#.........这里部分代码省略.........
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image formats. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
blockSize: string or positive int, optional, default "150M"
Requested size of blocks (e.g "64M", "512k", "2G"). If shuffle=True, can also be a
tuple of int specifying the number of pixels or splits per dimension. Indirectly
controls the number of Spark partitions, with one partition per block.
blockSizeUnits: string, either "pixels" or "splits", default "pixels"
Units for interpreting a tuple passed as blockSize when shuffle=True.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
shuffle: boolean, optional, default = True
Controls whether the conversion from Images to Series formats will use of a Spark shuffle-based method.
overwrite: boolean, optional, default False
If true, the directory specified by outputDirPath will be deleted (recursively) if it
already exists. (Use with caution.)
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if not overwrite:
raiseErrorIfPathExists(outputDirPath, awsCredentialsOverride=self._credentials)
overwrite = True # prevent additional downstream checks for this path
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath, dims, ext=ext, dtype=dtype, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions,
confFilename=confFilename)
else:
# 'tif' or 'tif-stack'
images = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
if renumber:
images = images.renumber()
images.toBlocks(blockSize, units=blockSizeUnits).saveAsBinarySeries(outputDirPath, overwrite=overwrite)
else:
from thunder.rdds.fileio.seriesloader import SeriesLoader
if nplanes is not None:
raise NotImplementedError("nplanes is not supported with shuffle=False")
if npartitions is not None:
raise NotImplementedError("npartitions is not supported with shuffle=False")
loader = SeriesLoader(self._sc)
if inputFormat.lower() == 'stack':
loader.saveFromStack(dataPath, outputDirPath, dims, ext=ext, dtype=dtype,
blockSize=blockSize, overwrite=overwrite, startIdx=startIdx,
stopIdx=stopIdx, recursive=recursive)
else:
# 'tif' or 'tif-stack'
loader.saveFromTif(dataPath, outputDirPath, ext=ext, blockSize=blockSize,
startIdx=startIdx, stopIdx=stopIdx, overwrite=overwrite,
recursive=recursive)示例3: convertImagesToSeries
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
def convertImagesToSeries(self, datapath, outputdirpath, dims=None, inputformat='stack',
dtype='int16', blocksize="150M", startidx=None, stopidx=None,
shuffle=False, overwrite=False):
"""
Write out Images data as Series data, saved in a flat binary format.
The resulting Series data files may subsequently be read in using the loadSeries() method. The Series data
object that results will be equivalent to that which would be generated by loadImagesAsSeries(). It is expected
that loading Series data directly from the series flat binary format, using loadSeries(), will be faster than
converting image data to a Series object through loadImagesAsSeries().
Parameters
----------
datapath: string
Path to data files or directory, specified as either a local filesystem path or in a URI-like format,
including scheme. A datapath argument may include a single '*' wildcard character in the filename. Examples
of valid datapaths include 'a/local/relative/directory/*.stack", "s3n:///my-s3-bucket/data/mydatafile.tif",
"/mnt/my/absolute/data/directory/", or "file:///mnt/another/data/directory/".
outputdirpath: string
Path to a directory into which to write Series file output. An outputdir argument may be either a path
on the local file system or a URI-like format, as in datapath. Examples of valid outputdirpaths include
"a/relative/directory/", "s3n:///my-s3-bucket/data/myoutput/", or "file:///mnt/a/new/directory/". If the
directory specified by outputdirpath already exists and the 'overwrite' parameter is False, this method
will throw a ValueError. If the directory exists and 'overwrite' is True, the existing directory and all
its contents will be deleted and overwritten.
dims: tuple of positive int, optional (but required if inputformat is 'stack')
Dimensions of input image data, for instance (1024, 1024, 48). Binary stack data will be interpreted as
coming from a multidimensional array of the specified dimensions.
The first dimension of the passed dims tuple should be the one that is changing most rapidly
on disk. So for instance given dims of (x, y, z), the coordinates of the data in a binary stack file
should be ordered as [(x0, y0, z0), (x1, y0, z0), ..., (xN, y0, z0), (x0, y1, z0), (x1, y1, z0), ...,
(xN, yM, z0), (x0, y0, z1), ..., (xN, yM, zP)]. This is the opposite convention from that used by numpy,
which by default has the fastest-changing dimension listed last (column-major convention). Thus, if loading
a numpy array `ary`, where `ary.shape == (z, y, x)`, written to disk by `ary.tofile("myarray.stack")`, the
corresponding dims parameter should be (x, y, z).
If inputformat is 'tif-stack', the dims parameter (if any) will be ignored; data dimensions will instead
be read out from the tif file headers.
inputformat: {'stack', 'tif-stack'}. optional, default 'stack'
Expected format of the input data. 'stack' indicates flat files of raw binary data, while 'tif-stack'
indicates a sequence of multipage tif files, with each page of the tif corresponding to a separate z-plane.
For both stacks and tif stacks, separate files are interpreted as distinct time points, with ordering
given by lexicographic sorting of file names.
This method assumes that stack data consists of signed 16-bit integers in native byte order. The lower-level
API method SeriesLoader.saveFromStack() allows alternative data types to be read in.
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string. If inputformat is
'tif-stack', the dtype parameter (if any) will be ignored; data type will instead be read out from the
tif headers.
blocksize: string formatted as e.g. "64M", "512k", "2G", or positive int. optional, default "150M"
Requested size of individual output files in bytes (or kilobytes, megabytes, gigabytes). This parameter
also indirectly controls the number of Spark partitions to be used, with one partition used per block
created.
startidx: nonnegative int, optional
startidx and stopidx are convenience parameters to allow only a subset of input files to be read in. These
parameters give the starting index (inclusive) and final index (exclusive) of the data files to be used
after lexicographically sorting all input data files matching the datapath argument. For example,
startidx=None (the default) and stopidx=10 will cause only the first 10 data files in datapath to be read
in; startidx=2 and stopidx=3 will cause only the third file (zero-based index of 2) to be read in. startidx
and stopidx use the python slice indexing convention (zero-based indexing with an exclusive final position).
stopidx: nonnegative int, optional
See startidx.
shuffle: boolean, optional, default False
Controls whether the conversion from Images to Series formats will make use of a Spark shuffle-based method.
The default at present is not to use a shuffle. The shuffle-based method may lead to higher performance in
some cases, but the default method appears to be more stable with larger data set sizes. This default may
change in future releases.
overwrite: boolean, optional, default False
If true, the directory specified by outputdirpath will first be deleted, along with all its contents, if it
already exists. (Use with caution.) If false, a ValueError will be thrown if outputdirpath is found to
already exist.
"""
checkparams(inputformat, ['stack', 'tif-stack'])
if inputformat.lower() == 'stack' and not dims:
raise ValueError("Dimensions ('dims' parameter) must be specified if loading from binary image stack" +
" ('stack' value for 'inputformat' parameter)")
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputformat.lower() == 'stack':
loader.fromStack(datapath, dims, dtype=dtype, startidx=startidx, stopidx=stopidx)\
.saveAsBinarySeries(outputdirpath, blockSize=blocksize, overwrite=overwrite)
else:
loader.fromMultipageTif(datapath, startidx=startidx, stopidx=stopidx)\
.saveAsBinarySeries(outputdirpath, blockSize=blocksize, overwrite=overwrite)
else:
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc)
if inputformat.lower() == 'stack':
#.........这里部分代码省略.........
示例4: loadImagesAsSeries
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
def loadImagesAsSeries(self, dataPath, dims=None, inputFormat='stack', ext=None, dtype='int16',
blockSize="150M", blockSizeUnits="pixels", startIdx=None, stopIdx=None,
shuffle=True, recursive=False, nplanes=None, npartitions=None,
renumber=False, confFilename='conf.json'):
"""
Load Images data as Series data.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image formats. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
blockSize: string or positive int, optional, default "150M"
Requested size of blocks (e.g "64M", "512k", "2G"). If shuffle=True, can also be a
tuple of int specifying the number of pixels or splits per dimension. Indirectly
controls the number of Spark partitions, with one partition per block.
blockSizeUnits: string, either "pixels" or "splits", default "pixels"
Units for interpreting a tuple passed as blockSize when shuffle=True.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
shuffle: boolean, optional, default = True
Controls whether the conversion from Images to Series formats will use of a Spark shuffle-based method.
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
Returns
-------
data: thunder.rdds.Series
A Series object, wrapping an RDD, with (n-tuples of ints) : (numpy array) pairs.
Keys will be n-tuples of int, with n given by dimensionality of the images, and correspond
to indexes into the image arrays. Value will have length equal to the number of image files.
With each image contributing one point to this value array, with ordering given by
the lexicographic ordering of image file names.
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath, dims, dtype=dtype, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions,
confFilename=confFilename)
else:
# tif / tif stack
images = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
if renumber:
images = images.renumber()
#.........这里部分代码省略.........
示例5: loadImages
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
def loadImages(self, dataPath, dims=None, dtype=None, inputFormat='stack', ext=None,
startIdx=None, stopIdx=None, recursive=False, nplanes=None, npartitions=None,
renumber=False, confFilename='conf.json'):
"""
Loads an Images object from data stored as a binary image stack, tif, or png files.
Supports single files or multiple files, stored on a local file system, a networked file sytem
(mounted and available on all nodes), or Amazon S3. HDFS is not currently supported for image file data.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image format. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype, optional, default = 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
Returns
-------
data: thunder.rdds.Images
An Images object, wrapping an RDD of with (int) : (numpy array) pairs
"""
checkParams(inputFormat, ['stack', 'png', 'tif', 'tif-stack'])
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
# Checking StartIdx is smaller or equal to StopIdx
if startIdx is not None and stopIdx is not None and startIdx > stopIdx:
raise Exception("Error. startIdx {} is larger than stopIdx {}".inputFormat(startIdx, stopIdx))
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if inputFormat.lower() == 'stack':
data = loader.fromStack(dataPath, dims=dims, dtype=dtype, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions,
confFilename=confFilename)
elif inputFormat.lower().startswith('tif'):
data = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx, recursive=recursive,
nplanes=nplanes, npartitions=npartitions)
else:
if nplanes:
raise NotImplementedError("nplanes argument is not supported for png files")
data = loader.fromPng(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx, recursive=recursive,
npartitions=npartitions)
if not renumber:
return data
else:
return data.renumber()示例6: loadImagesAsSeries
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
def loadImagesAsSeries(self, datapath, dims=None, inputformat='stack', blockSize="150M",
startidx=None, stopidx=None, shuffle=False):
"""
Load Images data as Series data.
Parameters
----------
datapath: string
Path to data files or directory, specified as either a local filesystem path or in a URI-like format,
including scheme. A datapath argument may include a single '*' wildcard character in the filename. Examples
of valid datapaths include 'a/local/relative/directory/*.stack", "s3n:///my-s3-bucket/data/mydatafile.tif",
"/mnt/my/absolute/data/directory/", or "file:///mnt/another/data/directory/".
dims: tuple of positive int, optional (but required if inputformat is 'stack')
Dimensions of input image data, similar to a numpy 'shape' parameter, for instance (1024, 1024, 48). Binary
stack data will be interpreted as coming from a multidimensional array of the specified dimensions. Stack
data should be stored in row-major order (Fortran or Matlab convention) rather than column-major order (C
or python/numpy convention), where the first dimension corresponds to that which is changing most rapidly
on disk. So for instance given dims of (x, y, z), the coordinates of the data in a binary stack file
should be ordered as [(x0, y0, z0), (x1, y0, zo), ..., (xN, y0, z0), (x0, y1, z0), (x1, y1, z0), ...,
(xN, yM, z0), (x0, y0, z1), ..., (xN, yM, zP)].
If inputformat is 'tif-stack', the dims parameter (if any) will be ignored; data dimensions will instead
be read out from the tif file headers.
inputformat: {'stack', 'tif-stack'}. optional, default 'stack'
Expected format of the input data. 'stack' indicates flat files of raw binary data, while 'tif-stack'
indicates a sequence of multipage tif files, with each page of the tif corresponding to a separate z-plane.
For both stacks and tif stacks, separate files are interpreted as distinct time points, with ordering
given by lexicographic sorting of file names.
This method assumes that stack data consists of signed 16-bit integers in native byte order.
blocksize: string formatted as e.g. "64M", "512k", "2G", or positive int. optional, default "150M"
Requested size of individual output files in bytes (or kilobytes, megabytes, gigabytes). This parameter
also indirectly controls the number of Spark partitions to be used, with one partition used per block
created.
startidx: nonnegative int, optional
startidx and stopidx are convenience parameters to allow only a subset of input files to be read in. These
parameters give the starting index (inclusive) and final index (exclusive) of the data files to be used
after lexicographically sorting all input data files matching the datapath argument. For example,
startidx=None (the default) and stopidx=10 will cause only the first 10 data files in datapath to be read
in; startidx=2 and stopidx=3 will cause only the third file (zero-based index of 2) to be read in. startidx
and stopidx use the python slice indexing convention (zero-based indexing with an exclusive final position).
stopidx: nonnegative int, optional
See startidx.
shuffle: boolean, optional, default False
Controls whether the conversion from Images to Series formats will make use of a Spark shuffle-based method.
The default at present is not to use a shuffle. The shuffle-based method may lead to higher performance in
some cases, but the default method appears to be more stable with larger data set sizes. This default may
change in future releases.
Returns
-------
data: thunder.rdds.Series
A newly-created Series object, wrapping an RDD of timeseries data generated from the images in datapath.
This RDD will have as keys an n-tuple of int, with n given by the dimensionality of the original images. The
keys will be the zero-based spatial index of the timeseries data in the RDD value. The value will be
a numpy array of length equal to the number of image files loaded. Each loaded image file will contribute
one point to this value array, with ordering as implied by the lexicographic ordering of image file names.
"""
checkparams(inputformat, ['stack', 'tif-stack'])
if inputformat.lower() == 'stack' and not dims:
raise ValueError("Dimensions ('dims' parameter) must be specified if loading from binary image stack" +
" ('stack' value for 'inputformat' parameter)")
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputformat.lower() == 'stack':
return loader.fromStack(datapath, dims, startidx=startidx, stopidx=stopidx)\
.toSeries(blockSize=blockSize)
else:
# tif stack
return loader.fromMultipageTif(datapath, startidx=startidx, stopidx=stopidx)\
.toSeries(blockSize=blockSize)
else:
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc)
if inputformat.lower() == 'stack':
return loader.fromStack(datapath, dims, blockSize=blockSize, startidx=startidx, stopidx=stopidx)
else:
# tif stack
return loader.fromMultipageTif(datapath, blockSize=blockSize,
startidx=startidx, stopidx=stopidx)示例7: loadImages
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
def loadImages(self, dataPath, dims=None, inputFormat='stack', ext=None, dtype='int16',
startIdx=None, stopIdx=None, recursive=False, nplanes=None, npartitions=None,
renumber=False):
"""
Loads an Images object from data stored as a binary image stack, tif, or png files.
Supports single files or multiple files, stored on a local file system, a networked file sytem
(mounted and available on all nodes), or Amazon S3. HDFS is not currently supported for image file data.
Parameters
----------
dataPath: string
Path to data files or directory, specified as either a local filesystem path or in a URI-like format,
including scheme. A dataPath argument may include a single '*' wildcard character in the filename. Examples
of valid dataPaths include 'a/local/relative/directory/*.stack", "s3n:///my-s3-bucket/data/mydatafile.tif",
"/mnt/my/absolute/data/directory/", or "file:///mnt/another/data/directory/".
dims: tuple of positive int, optional (but required if inputFormat is 'stack')
Dimensions of input image data, similar to a numpy 'shape' parameter, for instance (1024, 1024, 48). Binary
stack data will be interpreted as coming from a multidimensional array of the specified dimensions. Stack
data should be stored in row-major order (Fortran or Matlab convention) rather than column-major order (C
or python/numpy convention), where the first dimension corresponds to that which is changing most rapidly
on disk. So for instance given dims of (x, y, z), the coordinates of the data in a binary stack file
should be ordered as [(x0, y0, z0), (x1, y0, zo), ..., (xN, y0, z0), (x0, y1, z0), (x1, y1, z0), ...,
(xN, yM, z0), (x0, y0, z1), ..., (xN, yM, zP)].
If inputFormat is 'png' or 'tif', the dims parameter (if any) will be ignored; data dimensions
will instead be read out from the image file headers.
inputFormat: {'stack', 'png', 'tif'}. optional, default 'stack'
Expected format of the input data. 'stack' indicates flat files of raw binary data. 'png' or 'tif' indicate
image files of the corresponding formats. Each page of a multipage tif file will be interpreted as a
separate z-plane. For all formats, separate files are interpreted as distinct time points, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default None
Extension required on data files to be loaded. By default will be "stack" if inputFormat=="stack", "tif" for
inputFormat=='tif', and 'png' for inputFormat="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string. If inputFormat is
'tif' or 'png', the dtype parameter (if any) will be ignored; data type will instead be read out from the
tif headers.
startIdx: nonnegative int, optional
startIdx and stopIdx are convenience parameters to allow only a subset of input files to be read in. These
parameters give the starting index (inclusive) and final index (exclusive) of the data files to be used
after lexicographically sorting all input data files matching the dataPath argument. For example,
startIdx=None (the default) and stopIdx=10 will cause only the first 10 data files in dataPath to be read
in; startIdx=2 and stopIdx=3 will cause only the third file (zero-based index of 2) to be read in. startIdx
and stopIdx use the python slice indexing convention (zero-based indexing with an exclusive final position).
stopIdx: nonnegative int, optional
See startIdx.
recursive: boolean, default False
If true, will recursively descend directories rooted at dataPath, loading all files in the tree that
have an appropriate extension. Recursive loading is currently only implemented for local filesystems
(not s3).
nplanes: positive integer, default None
If passed, will cause a single image file to be subdivided into multiple records. Every
`nplanes` z-planes (or multipage tif pages) in the file will be taken as a new record, with the
first nplane planes of the first file being record 0, the second nplane planes being record 1, etc,
until the first file is exhausted and record ordering continues with the first nplane planes of the
second file, and so on. With nplanes=None (the default), a single file will be considered as
representing a single record. Keys are calculated assuming that all input files contain the same
number of records; if the number of records per file is not the same across all files,
then `renumber` should be set to True to ensure consistent keys.
npartitions: positive int, optional
If specified, request a certain number of partitions for the underlying Spark RDD. Default is 1
partition per image file.
renumber: boolean, optional, default False
If renumber evaluates to True, then the keys for each record will be explicitly recalculated after
all images are loaded. This should only be necessary at load time when different files contain
different number of records. See Images.renumber().
Returns
-------
data: thunder.rdds.Images
A newly-created Images object, wrapping an RDD of <int index, numpy array> key-value pairs.
"""
checkParams(inputFormat, ['stack', 'png', 'tif', 'tif-stack'])
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if inputFormat.lower() == 'stack':
data = loader.fromStack(dataPath, dims, dtype=dtype, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
elif inputFormat.lower().startswith('tif'):
data = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx, recursive=recursive,
nplanes=nplanes, npartitions=npartitions)
else:
if nplanes:
#.........这里部分代码省略.........
示例8: convertImagesToSeries
# 需要导入模块: from thunder.rdds.fileio.imagesloader import ImagesLoader [as 别名]
# 或者: from thunder.rdds.fileio.imagesloader.ImagesLoader import fromStack [as 别名]
#.........这里部分代码省略.........
blockSize: string formatted as e.g. "64M", "512k", "2G", or positive int, tuple of positive int, or instance of
BlockingStrategy. optional, default "150M"
Requested size of individual output files in bytes (or kilobytes, megabytes, gigabytes). blockSize can also
be an instance of blockingStrategy, or a tuple of int specifying either the number of pixels or of splits
per dimension to apply to the loaded images. Whether a tuple of int is interpreted as pixels or as splits
depends on the value of the blockSizeUnits parameter. This parameter also indirectly controls the number
of Spark partitions to be used, with one partition used per block created.
blockSizeUnits: string, either "pixels" or "splits" (or unique prefix of each, such as "s"), default "pixels"
Specifies units to be used in interpreting a tuple passed as blockSizeSpec when shuffle=True. If a string
or a BlockingStrategy instance is passed as blockSizeSpec, or if shuffle=False, this parameter has no
effect.
startIdx: nonnegative int, optional
startIdx and stopIdx are convenience parameters to allow only a subset of input files to be read in. These
parameters give the starting index (inclusive) and final index (exclusive) of the data files to be used
after lexicographically sorting all input data files matching the dataPath argument. For example,
startIdx=None (the default) and stopIdx=10 will cause only the first 10 data files in dataPath to be read
in; startIdx=2 and stopIdx=3 will cause only the third file (zero-based index of 2) to be read in. startIdx
and stopIdx use the python slice indexing convention (zero-based indexing with an exclusive final position).
stopIdx: nonnegative int, optional
See startIdx.
shuffle: boolean, optional, default True
Controls whether the conversion from Images to Series formats will make use of a Spark shuffle-based method.
overwrite: boolean, optional, default False
If true, the directory specified by outputDirPath will first be deleted, along with all its contents, if it
already exists. (Use with caution.) If false, a ValueError will be thrown if outputDirPath is found to
already exist.
recursive: boolean, default False
If true, will recursively descend directories rooted at dataPath, loading all files in the tree that
have an appropriate extension. Recursive loading is currently only implemented for local filesystems
(not s3), and only with shuffle=True.
nplanes: positive integer, default None
If passed, will cause a single image file to be subdivided into multiple records. Every
`nplanes` z-planes (or multipage tif pages) in the file will be taken as a new record, with the
first nplane planes of the first file being record 0, the second nplane planes being record 1, etc,
until the first file is exhausted and record ordering continues with the first nplane planes of the
second file, and so on. With nplanes=None (the default), a single file will be considered as
representing a single record. Keys are calculated assuming that all input files contain the same
number of records; if the number of records per file is not the same across all files,
then `renumber` should be set to True to ensure consistent keys. nplanes is only supported for
shuffle=True (the default).
npartitions: positive int, optional
If specified, request a certain number of partitions for the underlying Spark RDD. Default is 1
partition per image file. Only applies when shuffle=True.
renumber: boolean, optional, default False
If renumber evaluates to True, then the keys for each record will be explicitly recalculated after
all images are loaded. This should only be necessary at load time when different files contain
different number of records. renumber is only supported for shuffle=True (the default). See
Images.renumber().
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if inputFormat.lower() == 'stack' and not dims:
raise ValueError("Dimensions ('dims' parameter) must be specified if loading from binary image stack" +
" ('stack' value for 'inputFormat' parameter)")
if not overwrite:
raiseErrorIfPathExists(outputDirPath, awsCredentialsOverride=self.awsCredentials)
overwrite = True # prevent additional downstream checks for this path
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath, dims, ext=ext, dtype=dtype, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
else:
# 'tif' or 'tif-stack'
images = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
if renumber:
images = images.renumber()
images.toBlocks(blockSize, units=blockSizeUnits).saveAsBinarySeries(outputDirPath, overwrite=overwrite)
else:
from thunder.rdds.fileio.seriesloader import SeriesLoader
if nplanes is not None:
raise NotImplementedError("nplanes is not supported with shuffle=False")
if npartitions is not None:
raise NotImplementedError("npartitions is not supported with shuffle=False")
loader = SeriesLoader(self._sc)
if inputFormat.lower() == 'stack':
loader.saveFromStack(dataPath, outputDirPath, dims, ext=ext, dtype=dtype,
blockSize=blockSize, overwrite=overwrite, startIdx=startIdx,
stopIdx=stopIdx, recursive=recursive)
else:
# 'tif' or 'tif-stack'
loader.saveFromTif(dataPath, outputDirPath, ext=ext, blockSize=blockSize,
startIdx=startIdx, stopIdx=stopIdx, overwrite=overwrite,
recursive=recursive)