shuffle(ld)
num = 20000
preds = np.zeros((num, s), dtype=np.float)
y = np.zeros((num, s), dtype=np.float)
count = 0
for x in ld[:num]:
CID = x[:x.find(".png")]
y[count, :] = ecfps[CID]
preds[count, :] = means
count += 1
print "RMSE of guessing: ", np.sqrt(mean_squared_error(y, preds))
"""Require an argument specifying whether this is an update or a new model, parse input"""
update, size, lay1size, run = handleArgs(sys.argv)
#if len(sys.argv) <= 1:
# print "needs 'update' or 'new' as first argument"
# sys.exit(1)
#
#if sys.argv[1].lower().strip() == "update":
# UPDATE = True
# if len(sys.argv) < 5:
# print "needs image size, layer size, run # as other inputs"
# sys.exit(1)
# else:
# size = int(sys.argv[2]) #size of the images
# lay1size = int(sys.argv[3]) #size of the first receptive field
# run = "_"+str(sys.argv[4].strip())
# print size, lay1size
#cos = distance.cosine(vec, vec2)
euc = distance.euclidean(vec,vec2)
#row = [k, cos]
row = [k,euc]
tosort.append(row)
data = np.array(tosort)
#sCos = data[np.argsort(data[:,1])]
sEuc = data[np.argsort(data[:,1])]
#c = list(sCos[:,0]).index(cid)
c = list(sEuc[:,0]).index(cid)
return c, sEuc[:10]
"""Require an argument specifying whether this is an update or a new model, parse input"""
size, run, outType = helperFuncs.handleArgs(sys.argv)
"""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"""
shuffle(ld)
num = 20000
preds = np.zeros((num,s),dtype=np.float)
y = np.zeros((num,s),dtype=np.float)
count = 0
for x in ld[:num]:
CID = x[:x.find(".png")]
y[count,:] = OCRfeatures[CID]
preds[count,:] = means
count+=1
print "RMSE of guessing: ", np.sqrt(mean_squared_error(y, preds))
"""Require an argument specifying whether this is an update or a new model, parse input"""
update, size, lay1size, run = handleArgs(sys.argv,size=300)
"""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
preds = np.zeros((num, s), dtype=np.float)
y = np.zeros((num, s), dtype=np.float)
count = 0
for x in ld[:num]:
CID = x[:x.find(".png")]
y[count] = targets[CID]
preds[count] = means
count += 1
print "RMSE of guessing: ", np.sqrt(mean_squared_error(y, preds))
"""*************************************************************************"""
"""*************************************************************************"""
"""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"""
def getRank(cid,vec,allVec):
tosort = []
for k,vec2 in allVec.iteritems():
cos = distance.cosine(vec, vec2)
row = [k, cos]
tosort.append(row)
data = np.array(tosort)
sCos = data[np.argsort(data[:,1])]
c = list(sCos[:,0]).index(cid)
return c, sCos[:10]
"""Require an argument specifying whether this is an update or a new model, parse input"""
size, run, outType = helperFuncs.handleArgs(sys.argv)
"""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"""
y = np.zeros((num,s),dtype=np.float)
count = 0
for x in ld[:num]:
CID = x[:x.find(".png")]
y[count] = targets[CID]
preds[count] = means
count+=1
print "RMSE of guessing: ", np.sqrt(mean_squared_error(y, preds))
"""*************************************************************************"""
"""*************************************************************************"""
"""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
