xmipp3.protocols.protocol_classify_pca module

class xmipp3.protocols.protocol_classify_pca.XMIPPCOLUMNS(value)[source]

Bases: Enum

An enumeration.

anglePsi = 'anglePsi'
angleRot = 'angleRot'
angleTilt = 'angleTilt'
classCount = 'classCount'
ctfCritFitting = 'ctfCritFitting'
ctfCritMaxFreq = 'ctfCritMaxFreq'
ctfDefocusAngle = 'ctfDefocusAngle'
ctfDefocusU = 'ctfDefocusU'
ctfDefocusV = 'ctfDefocusV'
ctfQ0 = 'ctfQ0'
ctfSphericalAberration = 'ctfSphericalAberration'
ctfVoltage = 'ctfVoltage'
enabled = 'enabled'
flip = 'flip'
image = 'image'
itemId = 'itemId'
micrograph = 'micrograph'
micrographId = 'micrographId'
ref = 'ref'
scoreByGiniCoeff = 'scoreByGiniCoeff'
scoreByVariance = 'scoreByVariance'
shiftX = 'shiftX'
shiftY = 'shiftY'
shiftZ = 'shiftZ'
xcoor = 'xcoor'
ycoor = 'ycoor'
class xmipp3.protocols.protocol_classify_pca.XmippProtClassifyPca(**args)[source]

Bases: ProtClassify2D, XmippProtocol

Classifies a set of images.

CREATE_CLASSES = 0
UPDATE_CLASSES = 1
classification(inputIm, numClass, stfile, mask, sigma)[source]
convertInputStep(input, outputOrig, outputMRC)[source]
createOutputAverages(outputClasses)[source]
createOutputStep()[source]

Store the SetOfClasses2D object resulting from the protocol execution.

pcaTraining(inputIm, resolutionTrain, numTrain)[source]
xmipp3.protocols.protocol_classify_pca.rowToAlignmentEmtable(alignmentRow, alignType)[source]
is2D == True-> matrix is 2D (2D images alignment)

otherwise matrix is 3D (3D volume alignment or projection)

invTransform == True -> for xmipp implies projection

xmipp3.protocols.protocol_classify_pca.updateEnviron(gpuNum)[source]

Create the needed environment for pytorch programs.