python - 使用 gdal.Open 打开内存中的 GDAL 数据集

Question

我有一个仅存在于内存中的 GDAL 数据集 (inmem_ds):

In: gdal.Info(inmem_ds)
Out:
('Driver: NUMPY/Numeric Python Array\n'
 'Files: none associated\n'
 'Size is 500, 500\n'
 'Coordinate System is:\n'
 'PROJCS["WGS 84 / UTM zone 19N",\n'
 '    GEOGCS["WGS 84",\n'
 '        DATUM["WGS_1984",\n'
 '            SPHEROID["WGS 84",6378137,298.257223563,\n'
 '                AUTHORITY["EPSG","7030"]],\n'
 '            AUTHORITY["EPSG","6326"]],\n'
 '        PRIMEM["Greenwich",0,\n'
 '            AUTHORITY["EPSG","8901"]],\n'
 '        UNIT["degree",0.0174532925199433,\n'
 '            AUTHORITY["EPSG","9122"]],\n'
 '        AUTHORITY["EPSG","4326"]],\n'
 '    PROJECTION["Transverse_Mercator"],\n'
 '    PARAMETER["latitude_of_origin",0],\n'
 '    PARAMETER["central_meridian",-69],\n'
 '    PARAMETER["scale_factor",0.9996],\n'
 '    PARAMETER["false_easting",500000],\n'
 '    PARAMETER["false_northing",0],\n'
 '    UNIT["metre",1,\n'
 '        AUTHORITY["EPSG","9001"]],\n'
 '    AXIS["Easting",EAST],\n'
 '    AXIS["Northing",NORTH],\n'
 '    AUTHORITY["EPSG","32619"]]\n'
 'Origin = (617085.000000000000000,-1512585.000000000000000)\n'
 'Pixel Size = (30.000000000000000,-30.000000000000000)\n'
 'Corner Coordinates:\n'
 'Upper Left  (  617085.000,-1512585.000) ( 67d55\' 2.38"W, 13d40\'47.58"S)\n'
 'Lower Left  (  617085.000,-1527585.000) ( 67d55\' 0.13"W, 13d48\'55.77"S)\n'
 'Upper Right (  632085.000,-1512585.000) ( 67d46\'43.12"W, 13d40\'45.26"S)\n'
 'Lower Right (  632085.000,-1527585.000) ( 67d46\'40.59"W, 13d48\'53.42"S)\n'
 'Center      (  624585.000,-1520085.000) ( 67d50\'51.55"W, 13d44\'50.54"S)\n'
 'Band 1 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 2 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 3 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 4 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 5 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 6 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 7 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n'
 'Band 8 Block=500x1 Type=Int16, ColorInterp=Undefined\n'
 '  NoData Value=-9999\n')

现在我想将此数据集直接传递到使用 gdal.Open() 打开其输入数据集的外部 Python 库。所以我需要一个可以传递给 gdal.Open() 的物理文件路径。但我不想将内存中的 GDAL 数据集写入磁盘以节省 IO 时间。

有什么方法可以将内存数据集传递给 gdal.Open() 吗？

我尝试使用 VRT 数据集，但不起作用:

drv = gdal.GetDriverByName("VRT")
vrt = drv.CreateCopy("/mypath/test.vrt", inmem_ds)
type(vrt.ReadAsArray()) # numpy.ndarray -> works

gdal.Open('/mypath/test.vrt') # None, last GDAL error: Exception: Error reading file:  Missing <SourceFilename> element in VRTRasterBand.

保存的 VRT 文件 (mypath/test.vrt) 如下所示:

<VRTDataset rasterXSize="500" rasterYSize="500">
  <SRS>PROJCS["WGS 84 / UTM zone 19N",GEOGCS["WGS 84",DATUM["WGS_1984",SPHEROID["WGS 84",6378137,298.257223563,AUTHORITY["EPSG","7030"]],AUTHORITY["EPSG","6326"]],PRIMEM["Greenwich",0,AUTHORITY["EPSG","8901"]],UNIT["degree",0.0174532925199433,AUTHORITY["EPSG","9122"]],AUTHORITY["EPSG","4326"]],PROJECTION["Transverse_Mercator"],PARAMETER["latitude_of_origin",0],PARAMETER["central_meridian",-69],PARAMETER["scale_factor",0.9996],PARAMETER["false_easting",500000],PARAMETER["false_northing",0],UNIT["metre",1,AUTHORITY["EPSG","9001"]],AXIS["Easting",EAST],AXIS["Northing",NORTH],AUTHORITY["EPSG","32619"]]</SRS>
  <GeoTransform>  6.1708500000000000e+05,  3.0000000000000000e+01,  0.0000000000000000e+00, -1.5125850000000000e+06,  0.0000000000000000e+00, -3.0000000000000000e+01</GeoTransform>
  <VRTRasterBand dataType="Int16" band="1">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>1</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="2">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>2</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="3">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>3</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="4">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>4</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="5">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>5</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="6">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>6</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="7">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>7</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
  <VRTRasterBand dataType="Int16" band="8">
    <NoDataValue>-9999</NoDataValue>
    <SimpleSource>
      <SourceFilename relativeToVRT="0"></SourceFilename>
      <SourceBand>8</SourceBand>
      <SourceProperties RasterXSize="500" RasterYSize="500" DataType="Int16" BlockXSize="500" BlockYSize="1" />
      <SrcRect xOff="0" yOff="0" xSize="500" ySize="500" />
      <DstRect xOff="0" yOff="0" xSize="500" ySize="500" />
    </SimpleSource>
  </VRTRasterBand>
</VRTDataset>

Answer 1

您可以使用 vsimem 前缀将 VRT 写入内存，请注意数据实际上会写入内存，因此 VRT 以外的任何格式都会显着增加内存，具体取决于实际文件大小.

另请注意，即使关闭数据集句柄后，内存中的文件仍然保留。因此，当您使用完它后，您需要自行取消链接，否则它将保留内存。

因此，请跟踪您正在使用的内存中位置，以便您可以正确取消它们的链接。在“取消链接”之前写入现有的 vsimem 位置将不起作用，并保留原始文件。这可能有点麻烦。

要将磁盘上的文件或已打开的数据集输出到内存中的 VRT:

ds = gdal.Translate('/vsimem/inmem.vrt', some_file_or_dataset, format='VRT')
print(ds.ReadAsArray().shape)
ds = None

再次打开:

ds2 = gdal.Open('/vsimem/inmem.vrt')
print(ds2.ReadAsArray().shape)
ds2 = None

从内存中释放文件:

gdal.Unlink('/vsimem/inmem.vrt')

我不完全确定 vsimem 的范围，因此如果您通过“外部”指的是另一个 Python 解释器，它可能无法工作。