input_x, target_y, Winit = T.tensor4("input"), T.vector(
"target", dtype='int32'), init.Normal()
net = ll.InputLayer(input_shape, input_x)
net = ConvLayer(net, 20, 5, W=init.Normal())
net = MaxPool2DLayer(net, 2)
net = ConvLayer(net, 50, 5, W=init.Normal())
net = MaxPool2DLayer(net, 2)
net = ll.DenseLayer(net, 500, W=init.Normal())
net = ll.DenseLayer(net, nclass, W=init.Normal(), nonlinearity=nl.softmax)
return net, input_x, target_y, 1
num_epochs, batch_size, verbose, dataset = 200, 100, 1, 'mnist'
optp = lambda epoch: optpolicy.lr_linear(epoch, 1e-4)
arch = net_lenet5
net = run_experiment(dataset,
num_epochs,
batch_size,
arch,
objectives.sgvlb,
verbose,
optp,
optpolicy.rw_linear,
optimizer='adam',
da=True)
import warnings
from nets import optpolicy
import experiments.utils
from experiments.utils import run_experiment
import numpy as np
import os
from experiments.lenet.lenet import FC_Net, FC_BinDO_Net
from experiments.lenet.lenet import WN_BinDO_Net, WN_Net
import torch
import torch.nn as nn
dataset = 'mnist'
criterion = nn.CrossEntropyLoss().cuda()
num_epochs, batch_size, verbose = 200, 100, 1
optpol_linear = lambda epoch: optpolicy.lr_linear(num_epochs, epoch, 1e-3)
arch = WN_Net
noise_type = None
alpha = None
#alphas = np.logspace(np.log10(0.01), np.log10(3), 8)
noise_magnitude = True
magn_vars = [0.01, 0.05, 0.1, 0.5, 1, 2, 5, 10]
folder_name = 'wn_magn_batch'
filename = 'wn_magn_batch'
trainset_sizes = [100, 500, 1000, 5000, 10000, 50000]
ave_times = 50
if not os.path.exists('./experiments/logs'):
os.mkdir('./experiments/logs')