# author: David Hurwitz
# started: 8/17/19
#
from NN_formatted_data import OneNNData, NUM_PIXELS_1D
from NN_misc import PIXEL_LEN
import random
import numpy as np
AtomRadiusSqr = PIXEL_LEN * PIXEL_LEN
NumAtoms = 40
MidSlice = round(NUM_PIXELS_1D / 2)
# make an empty OneNNData
data = OneNNData()
for ii in range(100):
# get NumAtoms random coordinates. these are the true coordinates.
atomPositions = data.GetRandomPositions2(NumAtoms, AtomRadiusSqr)
atomTypes = ['C'] * NumAtoms
# calculate the density map for atomPositions and put it on the NN output.
data.MakeMap(atomPositions,
atomTypes,
False,
AtomRadiusSqr,
ClearData=True)
# calculate the Patterson map from the NN output and put it on the NN input. this is the true Patterson map.
# don't need to save the density map on the NN output any longer.
#-----------------------------------------------------------
# FileListTrain = "sim_files_000_to_029.txt" # 000_to_004 or 000_to_029
# FileListValidate = "sim_files_030_to_034.txt" # 005_to_009 or 030_to_034
FileListTrain = "sim_files_000_to_000.txt" # 000_to_004 or 000_to_029
FileListValidate = "sim_files_000_to_000.txt" # 005_to_009 or 030_to_034
print("reading the training files listed in: " + CSV_Path + FileListTrain)
allLinesTrain = AllLines()
ReadFilesInList(allLinesTrain, CSV_Path, FileListTrain)
print("reading the validation files list in: " + CSV_Path + FileListValidate)
allLinesValidate = AllLines()
ReadFilesInList(allLinesValidate, CSV_Path, FileListValidate)
#-------------------------------------------------------------------------------
# make a OneNNData to get array sizes for the NN
#-------------------------------------------------------------------------------
data = OneNNData()
inShape = data.InData.shape
outShape = data.OutData.shape
#-------------------------------------------------------------------------------
# make the Keras Functional API model.
#-------------------------------------------------------------------------------
input = Input(shape=data.InData.shape)
L01a = Conv3D(20,
5,
activation='relu',
padding='same',
kernel_initializer='he_normal')(input)
L01b = Conv3D(20,
5,
activation='relu',
allLinesValidate = AllLines()
ReadFilesInList(allLinesValidate, CSV_Path, FileListValidate)
#-----------------------------------------------------------
# read the connection file for this molecule
#-----------------------------------------------------------
ConnectionFile = "C:/Users/david/Documents/newff/results/NN/simulations/mol006_sim000.connections.csv"
print("reading connections file: " + ConnectionFile)
Connections = ProteinConnections(ConnectionFile)
TotalNumConnections = Connections.getTotalNumConnections()
print("check: total num connections = " + str(TotalNumConnections))
#-------------------------------------------------------------------------------
# make a OneNNData to get array sizes for the NN
#-------------------------------------------------------------------------------
data = OneNNData(
SizedForNN=True) # default InData size is larger for extra workspace
inShape = data.InData.shape
outShape = data.OutData.shape
#-------------------------------------------------------------------------------
# make the Keras Functional API model.
#-------------------------------------------------------------------------------
# input shape is: (?, 100, 100, 100, 16)
input = Input(shape=data.InData.shape)
L01 = Conv3D(18,
5,
activation='relu',
padding='same',
kernel_initializer='he_normal')(input)
L02 = Conv3D(18,
5,
# get the batch arrays into a format that is suitable for the NN: [batchsize, nx, ny, nz, numChannels]
(bigInputArray, bigOutputArray) = batchData.makeBigArrays()
print("bigInputArray.shape = ", bigInputArray.shape)
print("bigOutputArray.shape = ", bigOutputArray.shape)
# check that the shape is right for the NN
OneInput = bigInputArray[0]
OneOutput = bigOutputArray[0]
print("OneInput.shape = ", OneInput.shape)
print("OneOutput.shape = ", OneOutput.shape)
# leaving off here
# create this OneNNData object so we can use its member functions
data = OneNNData(SizedForNN=True)
# look at one slice of one output density map at different atom-radii
batchData.getOneItem(0).OutData = bigOutputArray[0]
batchData.getOneItem(0).PrintSlice(2, 50, False)
batchData.getOneItem(0).PrintHistogram(False, 20, 'test data')
batchData.getOneItem(0).ReMakeMap(False, 1.50 * PIXEL_LEN)
(bigInputArray2, bigOutputArray2) = batchData.makeBigArrays()
batchData.getOneItem(0).OutData = bigOutputArray[0]
batchData.getOneItem(0).PrintSlice(2, 50, False)
batchData.getOneItem(0).PrintHistogram(False, 20, 'test data')
batchData.getOneItem(0).ReMakeMap(False, 2.00 * PIXEL_LEN)
(bigInputArray3, bigOutputArray3) = batchData.makeBigArrays()
batchData.getOneItem(0).OutData = bigOutputArray[0]
allLinesValidate = AllLines()
ReadFilesInList(allLinesValidate, CSV_Path, FileListValidate)
#-----------------------------------------------------------
# read the connection file for this molecule
#-----------------------------------------------------------
ConnectionFile = "C:/Users/david/Documents/newff/results/NN/simulations/mol006_sim000.connections.csv"
print("reading connections file: " + ConnectionFile)
Connections = ProteinConnections(ConnectionFile)
TotalNumConnections = Connections.getTotalNumConnections()
print("check: total num connections = " + str(TotalNumConnections))
#-------------------------------------------------------------------------------
# make a OneNNData for general use.
#-------------------------------------------------------------------------------
data = OneNNData(SizedForNN=True)
#-------------------------------------------------------------------------------
# Append 8 extra channels to OneNNData::InData
# Need 4 for EstimateAtomPositionsFromDensityMapsSuperAccurate
# Need 8 for EstimateAtomPositionsFromDensityMapsSuperDuperAccurate
#-------------------------------------------------------------------------------
np_1d = NUM_PIXELS_1D
ExtraSpace = np.zeros(shape=(np_1d, np_1d, np_1d, 8), dtype=float32)
data.InData = np.append(data.InData, ExtraSpace, axis=3)
#-------------------------------------------------------------------------------
# make the first NN input for the trajectory
#-------------------------------------------------------------------------------
Batch = OneBatch(BatchSize)
Batch.makeABatch(allLinesValidate,
from numpy import float32 AtomRadius = 1.0 * PIXEL_LEN AtomRadiusSqr = AtomRadius * AtomRadius AtomRadiusCubed = AtomRadius * AtomRadius * AtomRadius molNum = 5 CSV_Path = "C:/Users/david/Documents/newff/results/NN/simulations/mol_05/csv_files/" FileList = "sim_files_000_to_000.txt" # 1 simulation file is in this list # read in all the CSV files that hold the MD simulation data # the data is stored in an AllLines object Lines = AllLines() ReadFilesInList(Lines, CSV_Path, FileList) data = OneNNData() # make empty data arrays #--------------------------------- # test (x, y, z) -> (i, j, k) #--------------------------------- sn = SMALL_NUM ps2 = PIXEL_LEN / 2 ps9 = 9 * PIXEL_LEN / 10 np1 = NUM_PIXELS_1D - 1 np2 = int(NUM_PIXELS_1D / 2) np21 = int(NUM_PIXELS_1D / 2) - 1 # test: (BOX_MIN+sn, BOX_MIN+sn, BOX_MIN+sn) -> (0,0,0) Pos = (BOX_MIN + sn, BOX_MIN + sn, BOX_MIN + sn) (i, j, k) = data.GetPixel(Pos) assert (i == 0 and j == 0 and k == 0)
def __init__(self, numInBatch):
self.trainingExamples = []
for i in range(numInBatch):
aTrainingExample = OneNNData()
self.trainingExamples.append(aTrainingExample)
#-----------------------------------------------------------
# FileListTrain = "sim_files_000_to_029.txt" # 000_to_004 or 000_to_029
# FileListValidate = "sim_files_030_to_034.txt" # 005_to_009 or 030_to_034
FileListTrain = "sim_files_000_to_000.txt" # 000_to_004 or 000_to_029
FileListValidate = "sim_files_030_to_030.txt" # 005_to_009 or 030_to_034
print("reading the training files listed in: " + CSV_Path + FileListTrain)
allLinesTrain = AllLines()
ReadFilesInList(allLinesTrain, CSV_Path, FileListTrain)
print("reading the validation files list in: " + CSV_Path + FileListValidate)
allLinesValidate = AllLines()
ReadFilesInList(allLinesValidate, CSV_Path, FileListValidate)
#-------------------------------------------------------------------------------
# make a OneNNData to get array sizes for the NN
#-------------------------------------------------------------------------------
data = OneNNData()
inShape = data.InData.shape
outShape = data.OutData.shape
#-------------------------------------------------------------------------------
# make the Keras Functional API model.
#-------------------------------------------------------------------------------
input = Input(shape=data.InData.shape)
L01a = Conv3D(20,
5,
activation='relu',
padding='same',
kernel_initializer='he_normal')(input)
L01b = Conv3D(20,
5,
activation='relu',
(j, dir[0], dir[1], dir[2], mag))
aLine1 = aLine2
#-----------------------------------------------------------
# read the connection file for this molecule
#-----------------------------------------------------------
ConnectionFile = "C:/Users/david/Documents/newff/results/NN/simulations/mol006_sim000.connections.csv"
print("reading connections file: " + ConnectionFile)
Connections = ProteinConnections(ConnectionFile)
TotalNumConnections = Connections.getTotalNumConnections()
print("check: total num connections = " + str(TotalNumConnections))
#-------------------------------------------------------------------------------
# make a OneNNData to get array sizes for the NN
#-------------------------------------------------------------------------------
data = OneNNData(
SizedForNN=True) # default InData size is larger for extra workspace
inShape = data.InData.shape
outShape = data.OutData.shape
#-------------------------------------------------------------------------------
# make a batch of formatted data for validation
#-------------------------------------------------------------------------------
validationBatch = OneBatch(ValidationBatchSize)
validationBatch.makeABatch(allLinesValidate,
Connections,
InRadiusSqr,
OutRadiusSqr,
doRotation=True,
batchType='validation',
timeStepInterval=TimeStepInterval)
(bigInputValidationArray,