input = F.relu(torch.add(input, -minimum))
input = F.relu(torch.add(torch.neg(input), maximum-minimum))
input = torch.add(torch.neg(input), maximum)
return input
def quant(input):
input = torch.round(input / (2 ** (-args.aprec))) * (2 ** (-args.aprec))
return input
# Load checkpoint.
if args.mode == 0:
print('==> Resuming from checkpoint..')
assert os.path.isdir('checkpoint'), 'Error: no checkpoint directory found!'
checkpoint = torch.load('./checkpoint/'+args.network)
net = checkpoint['net']
params = utils.paramsGet(net)
tmp = (params.data != 0).sum()
print(tmp.item()/params.size()[0])
elif args.mode == 1:
checkpoint = torch.load('./checkpoint/ckpt_20190802_half_clean_B3.t0')
ckpt = torch.load('./checkpoint/ckpt_20190802_half_clean_B2.t0')
net = checkpoint['net']
net2 = ckpt['net']
if args.resume:
print('==> Resuming from checkpoint..')
best_acc = checkpoint['acc']
else:
best_acc = 0
elif args.mode == 2:
def evalMetric(net, net_origin):
params_net = utils.paramsGet(net)
params_net_origin = utils.paramsGet(net_origin)
print(params_net.size())
print(params_net_origin.size())