size = 300 #EDIT ME! #how large the images are
outType = "justbonds" #EDIT ME! #what the CNN is predicting
#imdim = size - 20 #strip 10 pixels buffer from each size
direct = "../data/SDF/" #directory containing the SD files
ld = listdir(direct) #contents of that directory
shuffle(ld) #shuffle the image list for randomness
numEx = len(ld) #number of images in the directory
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 = 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
# depth = 2 #size of the first receptive field
# run = ""
"""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
shuffle(ld) #shuffle the image list for randomness
numEx = len(ld) #number of images in the directory
outType = "ecfp" #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 = 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)
#folder = "../ecfp/"+str(size)+"_"+str(lay1size)+run+"/"
#if not isdir(folder):
# mkdir(folder)
#
#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 +
"""Define parameters of the run"""
imdim = size - 20 #strip 10 pixels buffer from each size
direct = "../data/SDF/" #directory containing the SD files
ld = listdir(direct) #contents of that directory
shuffle(ld) #shuffle the image list for randomness
numEx = len(ld) #number of images in the directory
outType = "OCRfeatures" #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 = 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:
ld = listdir(direct) #contents of that directory
shuffle(ld) #shuffle the image list for randomness
numEx = len(ld) #number of images in the directory
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 = 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)
"""Require an argument specifying whether this is an update or a new model, parse input"""
update, size, lay1size, run = helperFuncs.handleArgs(sys.argv)
"""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)
"""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
