def train(self):
outputPrefix=self.readField(self.config,self.name,"output_directory")
outputDir=os.path.join(outputPrefix,self.name)
if not os.path.exists(outputDir):
os.makedirs(outputDir)
showFreq = int(self.readField(self.config, self.name, "show_freq"))
if showFreq > 0:
visDir = os.path.join(outputDir,'vis')
if not os.path.exists(visDir):
os.mkdir(visDir)
#do normalization for images if they are not normalized before
normalize=self.str2bool(self.readField(self.config, self.name, "normalize"))
trainDataSize=int(self.readField(self.config, self.name, "train_size"))
numBatch = trainDataSize / self.batchsize
trainDataPath = self.readField(self.config, self.name, "train_data")
if self.readField(self.config,self.name,"extract_reps")=="True":
trainRepsPath=self.readField(self.config, self.name, "train_reps")
else:
trainRepsPath=None
trainDataLoader=DataHandler(trainDataPath, trainRepsPath, self.vDim, self.hDim, self.batchsize,numBatch, normalize)
evalFreq=int(self.readField(self.config,self.name,'eval_freq'))
if evalFreq!=0:
qsize=int(self.readField(self.config, self.name, "query_size"))
evalPath=self.readField(self.config,self.name,"validation_data")
labelPath=self.readField(self.config,self.name,"label")
queryPath=self.readField(self.config, self.name, "query")
label=np.load(labelPath)
eval=Evaluator(queryPath,label ,os.path.join(outputDir,'perf'), self.name, query_size=qsize,verbose=self.verbose)
validation_data=gp.garray(np.load(evalPath))
if normalize:
validation_data=trainDataLoader.doNormalization(validation_data)
maxEpoch = int(self.readField(self.config, self.name, "max_epoch"))
nCommon, nMetric, title=self.getDisplayFields()
if self.verbose:
print title
for epoch in range(maxEpoch):
perf=np.zeros( nMetric)
trainDataLoader.reset()
for i in range(numBatch):
batch = trainDataLoader.getOneBatch()
curr = self.trainOneBatch(batch, epoch, computeStat=True)
perf=self.aggregatePerf(perf, curr)
if showFreq != 0 and (1+epoch) % showFreq == 0:
validation_code=self.getReps(validation_data)
np.save(os.path.join(visDir, '%dvis' % (1+epoch)), validation_code)
if evalFreq !=0 and (1+epoch) % evalFreq ==0:
validation_code=self.getReps(validation_data)
eval.evalSingleModal(validation_code,epoch,self.name+'V')
validation_code=None
if self.verbose:
self.printEpochInfo(epoch,perf,nCommon)
if self.readField(self.config,self.name,"checkpoint")=="True":
self.doCheckpoint(outputDir)
if self.readField(self.config,self.name,"extract_reps")=="True":
if evalFreq!=0:
validation_reps_path=self.readField(self.config, self.name, "validation_reps")
self.extractValidationReps(validation_data, validation_reps_path)
self.extractTrainReps(trainDataLoader, numBatch)
self.saveConfig(outputDir)
def train(self):
outputPrefix = self.readField(self.config, self.name,
"output_directory")
outputDir = os.path.join(outputPrefix, self.name)
if not os.path.exists(outputDir):
os.makedirs(outputDir)
showFreq = int(self.readField(self.config, self.name, "show_freq"))
if showFreq > 0:
visDir = os.path.join(outputDir, 'vis')
if not os.path.exists(visDir):
os.mkdir(visDir)
#do normalization for images if they are not normalized before
normalize = self.str2bool(
self.readField(self.config, self.name, "normalize"))
trainDataSize = int(
self.readField(self.config, self.name, "train_size"))
numBatch = trainDataSize / self.batchsize
trainDataPath = self.readField(self.config, self.name, "train_data")
if self.readField(self.config, self.name, "extract_reps") == "True":
trainRepsPath = self.readField(self.config, self.name,
"train_reps")
else:
trainRepsPath = None
trainDataLoader = DataHandler(trainDataPath, trainRepsPath, self.vDim,
self.hDim, self.batchsize, numBatch,
normalize)
evalFreq = int(self.readField(self.config, self.name, 'eval_freq'))
if evalFreq != 0:
qsize = int(self.readField(self.config, self.name, "query_size"))
evalPath = self.readField(self.config, self.name,
"validation_data")
labelPath = self.readField(self.config, self.name, "label")
queryPath = self.readField(self.config, self.name, "query")
label = np.load(labelPath)
eval = Evaluator(queryPath,
label,
os.path.join(outputDir, 'perf'),
self.name,
query_size=qsize,
verbose=self.verbose)
validation_data = gp.garray(np.load(evalPath))
if normalize:
validation_data = trainDataLoader.doNormalization(
validation_data)
maxEpoch = int(self.readField(self.config, self.name, "max_epoch"))
nCommon, nMetric, title = self.getDisplayFields()
if self.verbose:
print title
for epoch in range(maxEpoch):
perf = np.zeros(nMetric)
trainDataLoader.reset()
for i in range(numBatch):
batch = trainDataLoader.getOneBatch()
curr = self.trainOneBatch(batch, epoch, computeStat=True)
perf = self.aggregatePerf(perf, curr)
if showFreq != 0 and (1 + epoch) % showFreq == 0:
validation_code = self.getReps(validation_data)
np.save(os.path.join(visDir, '%dvis' % (1 + epoch)),
validation_code)
if evalFreq != 0 and (1 + epoch) % evalFreq == 0:
validation_code = self.getReps(validation_data)
eval.evalSingleModal(validation_code, epoch, self.name + 'V')
validation_code = None
if self.verbose:
self.printEpochInfo(epoch, perf, nCommon)
if self.readField(self.config, self.name, "checkpoint") == "True":
self.doCheckpoint(outputDir)
if self.readField(self.config, self.name, "extract_reps") == "True":
if evalFreq != 0:
validation_reps_path = self.readField(self.config, self.name,
"validation_reps")
self.extractValidationReps(validation_data,
validation_reps_path)
self.extractTrainReps(trainDataLoader, numBatch)
self.saveConfig(outputDir)
def train(self):
outputPrefix = self.readField(self.config, self.name,
"output_directory")
outputDir = os.path.join(outputPrefix, self.name)
if not os.path.exists(outputDir):
os.makedirs(outputDir)
showFreq = int(self.readField(self.config, self.name, "show_freq"))
if showFreq > 0:
visDir = os.path.join(outputDir, 'vis')
if not os.path.exists(visDir):
os.mkdir(visDir)
#do normalization for images if they are not normalized before
normalize = self.str2bool(
self.readField(self.config, self.name, "normalize"))
trainDataSize = int(
self.readField(self.config, self.name, "train_size"))
numBatch = trainDataSize / self.batchsize
if self.readField(self.config, self.name, "extract_reps") == "True":
trainRepsPath = self.readField(self.config, self.name,
"train_reps")
else:
trainRepsPath = None
print trainDataSize
#Ehsan
trainDataPath = (self.readField(self.config, self.name,
'train_data')).split(',')
print trainDataPath
trainDataLoader = [None for x in trainDataPath]
trainDataFiles = len(trainDataPath)
dims = [self.vDim]
if self.config.has_option(self.name, 'train_dims'):
dimsstr = (self.readField(self.config, self.name,
'train_dims')).split(',')
dims = [int(i) for i in dimsstr]
for i in range(trainDataFiles):
trainDataLoader[i] = DataHandler(trainDataPath[i], trainRepsPath,
dims[i], self.hDim,
self.batchsize, numBatch,
normalize)
evalFreq = int(self.readField(self.config, self.name, 'eval_freq'))
if evalFreq != 0:
qsize = int(self.readField(self.config, self.name, "query_size"))
evalPath = self.readField(self.config, self.name,
"validation_data")
labelPath = self.readField(self.config, self.name, "label")
queryPath = self.readField(self.config, self.name, "query")
label = np.load(labelPath)
eval = Evaluator(queryPath,
label,
os.path.join(outputDir, 'perf'),
self.name,
query_size=qsize,
verbose=self.verbose)
validation_data = gp.garray(np.load(evalPath))
if normalize:
validation_data = trainDataLoader.doNormalization(
validation_data)
maxEpoch = int(self.readField(self.config, self.name, "max_epoch"))
nCommon, nMetric, title = self.getDisplayFields()
if self.verbose:
print title
for epoch in range(maxEpoch):
perf = np.zeros(nMetric)
for tl in trainDataLoader:
tl.reset()
for i in range(numBatch):
batches = [None for x in trainDataLoader]
for i in range(len(batches)):
batches[i] = trainDataLoader[i].getOneBatch()
batch = gp.concatenate(tuple(batches), axis=1)
curr = self.trainOneBatch(batch, epoch, computeStat=True)
perf = self.aggregatePerf(perf, curr)
if showFreq != 0 and (1 + epoch) % showFreq == 0:
validation_code = self.getReps(validation_data)
np.save(os.path.join(visDir, '%dvis' % (1 + epoch)),
validation_code)
if evalFreq != 0 and (1 + epoch) % evalFreq == 0:
validation_code = self.getReps(validation_data)
eval.evalSingleModal(validation_code, epoch, self.name + 'V')
validation_code = None
if self.verbose:
self.printEpochInfo(epoch, perf, nCommon)
#Ehsan
try:
keepDL = self.str2bool(
self.readField(self.config, self.name, "keep_dataloader"))
if keepDL:
print 'saving tdl for ', self.name
self.trainDataLoader = trainDataLoader
except:
print 'exception occured'
if self.readField(self.config, self.name, "checkpoint") == "True":
self.doCheckpoint(outputDir)
if self.readField(self.config, self.name, "extract_reps") == "True":
if evalFreq != 0:
validation_reps_path = self.readField(self.config, self.name,
"validation_reps")
self.extractValidationReps(validation_data,
validation_reps_path)
self.extractTrainReps(trainDataLoader, numBatch)
self.saveConfig(outputDir)
