"""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"""
print "loading model"
if not update:
model = Sequential()
model.add(Convolution2D(16, 1, lay1size, lay1size, border_mode='full'))
model.add(Activation('relu'))
model.add(MaxPooling2D(poolsize=(2,2)))
model.add(Convolution2D(32, 16, lay1size, lay1size, border_mode='full'))
model.add(Activation('relu'))
#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"""
print "loading model"
if not update:
model = Sequential()
model.add(Convolution2D(16, 1, lay1size, lay1size, border_mode='full'))
model.add(Activation('relu'))
model.add(MaxPooling2D(poolsize=(2, 2)))
model.add(Convolution2D(32, 16, lay1size, lay1size, border_mode='full'))
model.add(Activation('relu'))
def getSize(folder):
fold = folder[folder[-1].rfind("/") + 1:]
fold = fold[:fold.find("_")]
print fold
fold = fold[fold.rfind("/") + 1:]
print fold
return fold
with open(sys.argv[1] + "wholeModel.pickle", 'rb') as f:
model = cPickle.load(f)
size = int(getSize(sys.argv[1]))
imdim = size
#OCRfeatures, labels = getOCRScaledTargets()
OCRTargets, labels = getOCRTargets()
means, stds = getMeansStds()
if True:
ld = listdir("/home/test/usan/")
images = np.zeros((1, 1, imdim, imdim), dtype=np.float)
for x in ld:
print x
try:
CID = x
print "reading in"
image = io.imread("/home/test/usan/" + x, as_grey=True)
image = minusOnes(image)
print "numpying"
image = np.array(image)
#image = convertIt(image)
def getSize(folder):
fold = folder[folder[-1].rfind("/")+1:]
fold = fold[:fold.find("_")]
print fold
fold = fold[fold.rfind("/")+1:]
print fold
return fold
with open(sys.argv[1]+"wholeModel.pickle",'rb') as f:
model = cPickle.load(f)
size = int(getSize(sys.argv[1]))
imdim = size
#OCRfeatures, labels = getOCRScaledTargets()
OCRTargets, labels = getOCRTargets()
means,stds = getMeansStds()
if True:
ld = listdir("/home/test/usan/")
images = np.zeros((1,1,imdim,imdim),dtype=np.float)
for x in ld:
print x
try:
CID = x
print "reading in"
image = io.imread("/home/test/usan/"+x,as_grey=True)
image = minusOnes(image)
print "numpying"
image = np.array(image)
