def run(args):
train, test = util.get_dataset(args.dataset)
names = ['all-one (standard)', 'linear']
colors = [vz.colors.all_one_lg, vz.colors.linear_lg]
models = [
BinaryNet.BinaryConvNet(10, cg.uniform, 'all'),
BinaryNet.BinaryConvNet(10, cg.linear, 'slow_exp'),
]
comp_ratios = np.linspace(0.1, 1.0, 20)
acc_dict = {}
ratios_dict = {}
for name, model in zip(names, models):
util.load_or_train_model(model, train, test, args)
acc_dict[name] = util.sweep_idp(model, test, comp_ratios, args)
ratios_dict[name] = [100. * cr for cr in comp_ratios]
filename = "BinaryNet_{}".format(args.dataset)
vz.plot(ratios_dict,
acc_dict,
names,
filename,
colors=colors,
folder=args.figure_path,
ext=args.ext,
title='BinaryNet (MNIST)',
xlabel='IDP (%)',
ylabel='Classification Accuracy (%)',
ylim=(90, 100))
def run(args):
train, test = util.get_dataset(args.dataset)
colors = [vz.colors.all_one_lg, vz.colors.linear_lg]
names = ['all-one', 'harmonic', 'linear', 'half_one']
colors = [
vz.colors.all_one_lg, vz.colors.harmonic_lg, vz.colors.linear_lg,
vz.colors.half_one_lg
]
models = [
MLP.MLP(10, cg.uniform),
MLP.MLP(10, cg.harmonic),
MLP.MLP(10, cg.linear),
MLP.MLP(10, cg.uniform_exp),
]
comp_ratios = np.linspace(0.1, 1.0, 20)
acc_dict = {}
ratios_dict = {}
for name, model in zip(names, models):
util.load_or_train_model(model, train, test, args)
acc_dict[name] = util.sweep_idp(model, test, comp_ratios, args)
ratios_dict[name] = [100. * cr for cr in comp_ratios]
filename = "MLP_coef_comparison_{}".format(args.dataset)
vz.plot(ratios_dict,
acc_dict,
names,
filename,
colors=colors,
folder=args.figure_path,
ext=args.ext,
xlabel='IDP (%)',
ylabel='Classification Accuracy (%)',
title='MLP (MNIST)',
legend_loc='lower right',
ylim=(85, 100))
comp_f='id',
act='ternary',
coeffs_generator=linear_seq),
net.ApproxNet(nclass,
*large_settings,
m=2,
comp_f='id',
act='ternary',
coeffs_generator=linear_seq),
]
acc_dict = {}
ratios_dict = {}
for name, model in zip(names, models):
acc_dict[name] = []
ratios_dict[name] = []
util.load_or_train_model(model, train, test, args)
for cr in comp_ratios:
acc = util.get_approx_acc(model, test, comp_ratio=cr)
acc_dict[name].append(acc)
ratios_dict[name].append(100. * cr)
filename = "activ_comparison_{}".format(args.dataset)
visualize.plot(ratios_dict,
acc_dict,
names,
filename,
colors=colors,
folder=args.figure_path,
ext=args.ext,
xlabel='Dot Product Component (%)',
ylabel='Classification Accuracy (%)')