xdim = image.shape[1] - wSize + 1
output = []
xran = np.linspace(0,xdim,(xdim/stride))
yran = np.linspace(0,ydim,(ydim/stride))
for y in yran:
for x in xran:
output.append(canvas[y:y+wSize,x:x+wSize])
return np.reshape(np.array(output),(len(output),1,wSize,wSize))
#Process the arguments given (see helperFuncs.py for details)
size, indir, binarize, blur, padding, targetType = helperFuncs.dataProcessorArgs(sys.argv[1:])
targets, labels = helperFuncs.getTargets(targetType)
outsize = helperFuncs.getOutSize(targets)
#wait until the folder exists
while not isdir(indir+"tempTrain/"):
time.sleep(10.)
print "I'm sleeping", isdir(indir), indir, " \r",
if not isdir(indir+"tempTrainNP/"):
mkdir(indir+"tempTrainNP/")
mkdir(indir+"tempTestNP/")
#define folders
trainFolder = indir+"tempTrain/"
trainNPfolder = indir+"tempTrainNP/"
testFolder = indir+"tempTest/"
# 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)))
model.add(Activation('relu'))
model.add(Convolution2D(8, 5, 5))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(3, 3)))
model.add(Dropout(0.25))
model.add(Convolution2D(8, 5, 5))
model.add(Activation('relu'))