def __init__(self,
netParams,
device,
optimizer,
testSet,
classification=False):
self.netParams = netParams
self.testLoader = DataLoader(dataset=testSet,
batch_size=8,
shuffle=False,
num_workers=4)
self.device = device
self.optimizer = optimizer
error = snn.loss(self.netParams).to(self.device)
self.criterion = Criterion(error,
netParams['training']['error']['type'])
self.theta = netParams['neuron']['theta']
self.classification = classification
def __init__(self,
netParams,
device,
optimizer,
trainingSet,
classification=False,
collect_weights=False):
self.netParams = netParams
self.trainLoader = DataLoader(dataset=trainingSet,
batch_size=8,
shuffle=False,
num_workers=4)
self.device = device
self.optimizer = optimizer
error = snn.loss(self.netParams).to(self.device)
self.criterion = Criterion(error,
netParams['training']['error']['type'])
self.classification = classification
self.weightCollector = WeightCollector() if collect_weights else None
if not os.path.exists(os.path.join(path, member)):
zip_file.extract(member, path)
else:
print('extraction path already exist',
os.path.join(path, member))
# extract_dataset()
device = torch.device("cuda" if USE_CUDA else "cpu")
#Create network instance.
net = Network(netParams).to(device)
# Create snn loss instance.
error = snn.loss(netParams).to(device)
# Define optimizer module.
optimizer = torch.optim.Adam(net.parameters(), lr=0.01, amsgrad=True)
# Dataset and dataLoader instances.
trainingSet = nmnistDataset(datasetPath=netParams['training']['path']['in'],
sampleFile=netParams['training']['path']['train'],
samplingTime=netParams['simulation']['Ts'],
sampleLength=netParams['simulation']['tSample'])
trainLoader = DataLoader(dataset=trainingSet,
batch_size=8,
shuffle=False,
num_workers=4)
testingSet = nmnistDataset(datasetPath=netParams['training']['path']['in'],