#if (not UPDATE) and (isdir(folder)):
# i=1
# oldfolder = folder
# while isdir(folder):
# i+=1
# folder = oldfolder[:-1]+"_"+str(i)+'/'
# print folder
# mkdir(folder)
if update:
stop = raw_input("Loading from folder " + folder +
" : Hit enter to proceed or ctrl+C to cancel")
else:
print "Initializing in folder " + folder
"""Load the train/test split information if update, else split and write out which images are in which dataset"""
trainFs, testFs = getTrainTestSplit(update, folder)
trainL = len(trainFs)
testL = len(testFs)
#if not UPDATE:
# trainFs = ld[:int(numEx*trainTestSplit)]
# testFs = ld[int(numEx*trainTestSplit):]
# with open(folder+"traindata.csv",'wb') as f:
# f.write('\n'.join(trainFs))
# with open(folder+"testdata.csv",'wb') as f:
# f.write('\n'.join(testFs))
#else:
# with open(folder+"traindata.csv",'rb') as f:
# trainFs = f.read().split("\n")
# with open(folder+"testdata.csv",'rb') as f:
# testFs = f.read().split("\n")
batch_size = 32 #how many training examples per batch
chunkSize = 50000 #how much data to ever load at once
testChunkSize = 6000 #how many examples to evaluate per iteration
run = "1"
"""Define the folder where the model will be stored based on the input arguments"""
folder = helperFuncs.defineFolder(False, outType, size, run)
print folder
trainDirect = folder + "tempTrain/"
testDirect = folder + "tempTest/"
#if update:
# stop = raw_input("Loading from folder "+folder+" : Hit enter to proceed or ctrl+C to cancel")
#else:
# print "Initializing in folder "+folder
"""Load the train/test split information if update, else split and write out which images are in which dataset"""
trainFs, testFs = helperFuncs.getTrainTestSplit(False, folder, numEx,
trainTestSplit, ld)
trainL = len(trainFs)
testL = len(testFs)
print "number of examples: ", numEx
print "training examples : ", trainL
print "test examples : ", testL
features, labels = helperFuncs.getTargets(
"justbonds") #get the target vector for each CID
outsize = helperFuncs.getOutSize(features)
"""DEFINE THE MODEL HERE"""
model = Sequential()
model.add(Convolution2D(8, 8, 8, input_shape=(1, size, size)))
print folder
trainDirect = folder+"tempTrain/"
testDirect = folder+"tempTest/"
#if update:
# stop = raw_input("Loading from folder "+folder+" : Hit enter to proceed or ctrl+C to cancel")
#else:
# print "Initializing in folder "+folder
"""Load the train/test split information if update, else split and write out which images are in which dataset"""
if update:
trainFs, testFs = getTrainTestSplit(update,folder)
else:
trainFs, testFs = getTrainTestSplit(update,folder,numEx,trainTestSplit,ld)
trainL = len(trainFs)
testL = len(testFs)
print "number of examples: ", numEx
print "training examples : ", trainL
print "test examples : ", testL
OCRfeatures,labels = getOCRTargets() #get the ECFP vector for each CID
#testAverages(direct,OCRfeatures) # determind the RMSE of guessing the mean
outsize = len(OCRfeatures[OCRfeatures.keys()[0]]) #this it the size of the target (# of OCRfeatures)
"""If we are training a new model, define it"""
"""Define parameters of the run""" batch_size = 32 #how many training examples per batch """Define the folder where the model will be stored based on the input arguments""" folder = helperFuncs.defineFolder(True,outType,size,run) print folder trainDirect = folder+"tempTrain/" trainNP = folder+"tempTrainNP/" testDirect = folder+"tempTest/" testNP = folder+"tempTestNP/" """Load the train/test split information""" trainFs, testFs = helperFuncs.getTrainTestSplit(True,folder) trainL = len(trainFs) testL = len(testFs) features,labels = helperFuncs.getTargets(outType) #get the OCR vector for each CID outsize = len(features[features.keys()[0]]) #this it the size of the target (# of OCRfeatures) means,stds = helperFuncs.getMeansStds(features) """load model""" model = helperFuncs.loadModel(folder+"wholeModel") while not isfile(testNP+"Xtest.h5"):
batch_size = 32 #how many training examples per batch
chunkSize = 50000 #how much data to ever load at once
testChunkSize = 6000 #how many examples to evaluate per iteration
"""Define the folder where the model will be stored based on the input arguments"""
folder = defineFolder(outType, size, lay1size, run, update)
print folder
trainDirect = folder + "tempTrain/"
testDirect = folder + "tempTest/"
#if update:
# stop = raw_input("Loading from folder "+folder+" : Hit enter to proceed or ctrl+C to cancel")
#else:
# print "Initializing in folder "+folder
"""Load the train/test split information if update, else split and write out which images are in which dataset"""
if update:
trainFs, testFs = getTrainTestSplit(update, folder)
else:
trainFs, testFs = getTrainTestSplit(update, folder, numEx, trainTestSplit,
ld)
trainL = len(trainFs)
testL = len(testFs)
print "number of examples: ", numEx
print "training examples : ", trainL
print "test examples : ", testL
OCRfeatures, labels = getOCRTargets() #get the ECFP vector for each CID
#testAverages(direct,OCRfeatures) # determind the RMSE of guessing the mean
outsize = len(OCRfeatures[
OCRfeatures.keys()[0]]) #this it the size of the target (# of OCRfeatures)
"""If we are training a new model, define it"""
folder = helperFuncs.defineFolder(False,outType,size,run)
print folder
trainDirect = folder+"tempTrain/"
testDirect = folder+"tempTest/"
#if update:
# stop = raw_input("Loading from folder "+folder+" : Hit enter to proceed or ctrl+C to cancel")
#else:
# print "Initializing in folder "+folder
"""Load the train/test split information if update, else split and write out which images are in which dataset"""
trainFs, testFs = helperFuncs.getTrainTestSplit(False,folder,numEx,trainTestSplit,ld)
trainL = len(trainFs)
testL = len(testFs)
print "number of examples: ", numEx
print "training examples : ", trainL
print "test examples : ", testL
features,labels = helperFuncs.getTargets("ocr") #get the target vector for each CID
outsize = len(features[features.keys()[0]]) #this it the size of the target (# of OCRfeatures)
"""DEFINE THE MODEL HERE"""
model = Sequential()
"""Define parameters of the run"""
imdim = size - 20 #strip 10 pixels buffer from each size
direct = "../data/images" + str(size) + "/" #directory containing the images
ld = listdir(direct) #contents of that directory
numEx = len(ld) #number of images in the directory
shuffle(ld) #shuffle the image list for randomness
outType = "solubility" #what the CNN is predicting
DUMP_WEIGHTS = True #will we dump the weights of conv layers for visualization
trainTestSplit = 0.90 #percentage of data to use as training data
batch_size = 32 #how many training examples per batch
chunkSize = 50000 #how much data to ever load at once
testChunkSize = 5000 #how many examples to evaluate per iteration
"""Define the folder where the model will be stored based on the input arguments"""
folder = helperFuncs.defineFolder(outType, size, lay1size, run)
"""Load the train/test split information if update, else split and write out which images are in which dataset"""
trainFs, testFs = helperFuncs.getTrainTestSplit(update, folder, numEx,
trainTestSplit)
trainL = len(trainFs)
testL = len(testFs)
print "number of examples: ", numEx
print "training examples : ", trainL
print "test examples : ", testL
#batch_size = 32 #how many training examples per batch
#chunkSize = 5000 #how much data to ever load at once
#testChunkSize = 600 #how many examples to evaluate per iteration
numTrainEx = min(trainL, chunkSize)
targets = helperFuncs.getSolubilityTargets(
) #get the solubility value for each CID
outsize = len(
"""Define parameters of the run""" batch_size = 32 #how many training examples per batch """Define the folder where the model will be stored based on the input arguments""" folder = helperFuncs.defineFolder(True,outType,size,run) print folder trainDirect = folder+"tempTrain/" trainNP = folder+"tempTrainNP/" testDirect = folder+"tempTest/" testNP = folder+"tempTestNP/" """Load the train/test split information""" trainFs, testFs = helperFuncs.getTrainTestSplit(True,folder) trainL = len(trainFs) testL = len(testFs) features,labels = helperFuncs.getTargets(outType) #get the OCR vector for each CID outsize = len(features[features.keys()[0]]) #this it the size of the target (# of OCRfeatures) means,stds = helperFuncs.getMeansStds() """load model""" #with open(folder+"bestModel.pickle",'rb') as f: # model = cPickle.load(f) model = helperFuncs.loadModel(folder+"wholeModel")
ld = listdir(direct) #contents of that directory numEx = len(ld) #number of images in the directory shuffle(ld) #shuffle the image list for randomness outType = "solubility" #what the CNN is predicting DUMP_WEIGHTS = True #will we dump the weights of conv layers for visualization trainTestSplit = 0.90 #percentage of data to use as training data batch_size = 32 #how many training examples per batch chunkSize = 50000 #how much data to ever load at once testChunkSize = 5000 #how many examples to evaluate per iteration """Define the folder where the model will be stored based on the input arguments""" folder = helperFuncs.defineFolder(outType,size,lay1size,run) """Load the train/test split information if update, else split and write out which images are in which dataset""" trainFs, testFs = helperFuncs.getTrainTestSplit(update,folder,numEx,trainTestSplit) trainL = len(trainFs) testL = len(testFs) print "number of examples: ", numEx print "training examples : ", trainL print "test examples : ", testL #batch_size = 32 #how many training examples per batch #chunkSize = 5000 #how much data to ever load at once #testChunkSize = 600 #how many examples to evaluate per iteration numTrainEx = min(trainL,chunkSize) targets = helperFuncs.getSolubilityTargets() #get the solubility value for each CID
