def main():
__model = MLP(in_dim=400, hidden_dim=HIDDEN_DIM, out_dim=800)
print("\tTraining {}...".format(__model.__str__().split("(")[0]))
optim = torch.optim.Adam(__model.parameters(), lr=LEARNING_RATE)
train(__model, optim, X_train, y_train, 128)
mse = test(__model, X_test, y_test).mean().item()
print(mse)
def main():
save_dir = './results/'
models = [
MLP(
num_layers=NUM_LAYERS,
in_dim=2,
hidden_dim=HIDDEN_DIM,
out_dim=1,
activation='relu6',
),
MLP(
num_layers=NUM_LAYERS,
in_dim=2,
hidden_dim=HIDDEN_DIM,
out_dim=1,
activation='none',
),
NAC(
num_layers=NUM_LAYERS,
in_dim=2,
hidden_dim=HIDDEN_DIM,
out_dim=1,
),
NALU(
num_layers=NUM_LAYERS,
in_dim=2,
hidden_dim=HIDDEN_DIM,
out_dim=1
),
]
results = {}
for fn_str, fn in ARITHMETIC_FUNCTIONS.items():
print('[*] Testing function: {}'.format(fn_str))
results[fn_str] = []
# dataset
X_train, y_train, X_test, y_test = generate_data(
num_train=500, num_test=50,
dim=100, num_sum=5, fn=fn,
support=RANGE,
)
# random model
random_mse = []
for i in range(100):
net = MLP(
num_layers=NUM_LAYERS, in_dim=2,
hidden_dim=HIDDEN_DIM, out_dim=1,
activation='relu6',
)
mse = test(net, X_test, y_test)
random_mse.append(mse.mean().item())
results[fn_str].append(np.mean(random_mse))
# others
for net in models:
print("\tTraining {}...".format(net.__str__().split("(")[0]))
optim = torch.optim.RMSprop(net.parameters(), lr=LEARNING_RATE)
train(net, optim, X_train, y_train, NUM_ITERS)
mse = test(net, X_test, y_test).mean().item()
results[fn_str].append(mse)
with open(save_dir + "interpolation.txt", "w") as f:
f.write("Relu6\tNone\tNAC\tNALU\n")
for k, v in results.items():
rand = results[k][0]
mses = [100.0*x/rand for x in results[k][1:]]
if NORMALIZE:
f.write("{:.3f}\t{:.3f}\t{:.3f}\t{:.3f}\n".format(*mses))
else:
f.write("{:.3f}\t{:.3f}\t{:.3f}\t{:.3f}\n".format(*results[k][1:]))
