def trainSamples(primaryDatasets, primaryClasses, primaryInstances,
helperInstances):
for dataSet in primaryDataSets:
for cls in primaryClasses:
for instance in primaryInstances:
for helperInstance in helperInstances:
# if the number of primary instances are larger than the number of helper
# instances, no need to calculate MMD
if instance > helperInstance:
continue
# get a fixed helper class for a particular dataset and primary class
helperClass = getHelperClass(dataSet, cls)
if helperClass == -1:
continue
print(
'Primary Class: {} Helper Class: {} Primary Instances: {} Helper Instance {}'
.format(cls, helperClass, instance, helperInstance))
primaryFileName = dataSet + '_' + str(cls) + '_' + str(
instance)
helperFileName = dataSet + '_' + str(
helperClass) + '_' + str(helperInstance)
dataFolder = rootDir + str(dataSet)
x = loadDataset(dataSet, cls, instance)
y = loadDataset(dataSet, helperClass, helperInstance)
primaryTrainLoader = torch.utils.data.DataLoader(
x,
batch_size=batchSize,
shuffle=True,
num_workers=4,
drop_last=True)
helperTrainLoader = torch.utils.data.DataLoader(
y,
batch_size=batchSize,
shuffle=True,
num_workers=4,
drop_last=True)
numOutputChannels = getChannels(dataSet)
epochs = getEpochs(dataSet, instance)
print epochs
train(primaryFileName,
helperFileName,
primaryTrainLoader,
helperTrainLoader,
instance,
numOutputChannels,
epochs=epochs)
def trainSamples(primaryDataSet, helperDataSet, primaryClasses,
primaryInstances, helperInstances):
for cls in primaryClasses:
for instance in primaryInstances:
for helperInstance in helperInstances:
# if the number of primary instances are larger than the number of helper
# instances, no need to calculate MMD
if instance > helperInstance:
continue
# the primary class is same as helper class in this case
helperClass = cls
print(
'Primary Class: {} Helper Class: {} Primary Instances: {} Helper Instance {}'
.format(cls, helperClass, instance, helperInstance))
primaryFileName = primaryDataSet + '_' + str(cls) + '_' + str(
instance)
helperFileName = helperDataSet + '_' + str(
helperClass) + '_' + str(helperInstance)
x = loadDataset(primaryDataSet, cls, instance)
y = loadDataset(helperDataSet, helperClass, helperInstance)
primaryTrainLoader = torch.utils.data.DataLoader(
x,
batch_size=batchSize,
shuffle=True,
num_workers=4,
drop_last=False)
helperTrainLoader = torch.utils.data.DataLoader(
y,
batch_size=batchSize,
shuffle=True,
num_workers=4,
drop_last=True)
numOutputChannels = getChannels(primaryDataSet)
epochs = getEpochs(primaryDataSet, instance)
train(primaryFileName,
helperFileName,
primaryTrainLoader,
helperTrainLoader,
instance,
numOutputChannels,
epochs=epochs)
def trainSamples(primaryDatasets, primaryClasses, primaryInstances,
helperInstances):
for dataSet in primaryDataSets:
for cls in primaryClasses:
for instance in primaryInstances:
for helperInstance in helperInstances:
# if the number of primary instances are larger than the number of helper
# instances, no need to calculate MMD
if instance > helperInstance:
continue
primaryFileName = dataSet + '_' + str(cls) + '_' + str(
instance)
helperFileName = dataSet + '_' + 'all' + '_' + str(
helperInstance)
dataFolder = rootDir + str(dataSet)
x = loadDataset(dataSet, cls, instance, except_=0)
y = loadDataset(dataSet, cls, instance, except_=1)
primaryTrainLoader = torch.utils.data.DataLoader(
x,
batch_size=batchSize,
shuffle=True,
num_workers=4,
drop_last=True)
helperTrainLoader = torch.utils.data.DataLoader(
y,
batch_size=batchSize,
shuffle=True,
num_workers=4,
drop_last=True)
numOutputChannels = getChannels(dataSet)
epochs = getEpochs(dataSet, instance)
train(primaryFileName,
helperFileName,
primaryTrainLoader,
helperTrainLoader,
instance,
numOutputChannels,
epochs=epochs)
def test(primaryDataSet, helperDataSet, primaryClass, helperClass, primaryInstances, helperInstances):
'''
Inputs :
dataSets : List : Datasets for which samples are to be genrated
instances : List : Number of instances to be used from original dataset
classes : List : Classes for which samples are to be generated
Output :
File with 1000 compressed images generated by GAN
'''
helperClass = primaryClass
modelFolder = resultDir + 'models/crossDataSetMMDall'+'/'+primaryDataSet+'/'
print (primaryDataSet, helperDataSet, primaryClass, helperClass, primaryInstances, helperInstances, getEpochs(primaryDataSet,primaryInstances)-1)
modelFile = modelFolder + primaryDataSet + '_' + helperDataSet + '_' + \
str(primaryClass) + '_' + str(helperClass) + '_' + \
str(primaryInstances) + '_' + str(helperInstances)+'_'+ \
str(getEpochs(primaryDataSet,primaryInstances)-1)+'.pt'
print ('Generating examples for Dataset: '+primaryDataSet+
' Primary Class: '+str(primaryClass)+
' Helper Class: '+str(helperClass)+
' Primary Instances: '+str(primaryInstances)+
' Helper Instances: '+str(helperInstances)+
' Epochs: '+str(getEpochs(primaryDataSet,primaryInstances)))
numOutputChannels = getChannels(primaryDataSet)
# load the model learnt during training
G = Generator(numInputChannels, numGenFilter, numOutputChannels)
G.load_state_dict(torch.load(modelFile))
genImageConcat = np.empty(1)
iterations = numOfSamples/batchSize
for iteration in range(iterations):
noise = torch.FloatTensor(batchSize,
numInputChannels,
1,
1)
noise.normal_(0,1)
if cuda:
G = G.cuda()
noise = noise.cuda()
noiseVariable = Variable(noise)
genImage = G(noiseVariable)
genImage = genImage.data
genImage = genImage.cpu()
genImage = genImage.numpy()
if iteration==0:
genImageConcat = genImage
else:
genImageConcat = np.concatenate((genImageConcat, genImage),
axis=0)
if iteration==(iterations-1):
# normalize sets image pixels between 0 and 1
genImage = torchvision.utils.make_grid(torch.from_numpy(genImage[:25]), nrow=5, normalize=True)
# mapping between 0 to 1 as required by imshow,
# otherwise the images are stored in the form -1 to 1
# done through normalize=True
genImage = genImage.permute(1,2,0)
genImage = genImage.numpy()
plt.imshow(genImage, cmap='gray')
plotFolder = resultDir+'results'+'/'+'crossDataSetMMDall/samples'+'/'+primaryDataSet+'/'
checkAndCreateFolder(plotFolder)
plotFile = primaryDataSet + '_' + helperDataSet + '_' + \
str(primaryClass) + '_' + 'all' + '_' + \
str(primaryInstances) + '_' + str(helperInstances)
plotPath = plotFolder + plotFile
plt.axis('off')
plt.savefig(plotPath, bbox_inches='tight')
plt.show()
resultFolder = resultDir+'results/crossDataSetMMDall'+'/'+'compressed'+'/'+primaryDataSet+'/'
checkAndCreateFolder(resultFolder)
resultFile = primaryDataSet + '_' + helperDataSet + '_' + \
str(primaryClass) + '_' + 'all' + '_' + \
str(primaryInstances) + '_' + str(helperInstances) + '.npy'
resultPath = resultFolder + resultFile
# save the image in some format
with open(resultPath,'wb+') as fh:
genImageConcat = np.squeeze(genImageConcat)
np_save(fh, genImageConcat, allow_pickle=False)
sync(fh)