def bbbp_4_layers_100_neurons():
trainer_obj = trainers.BBBP
model_generator = models.get_correct_model(dataset="toy",
trainer=trainer_obj)
model, opts = model_generator.create(input_shape=1,
num_neurons=100,
num_layers=4)
trainer = trainer_obj(model, opts, learning_rate=1e-3)
model, rmse, nll = trainer.train(x_train,
y_train,
x_train,
y_train,
np.array([[1.]]),
iters=iterations,
batch_size=batch_size,
verbose=True)
plot_bbbp(model, os.path.join(save_fig_dir, "bbbp_4_layers_100_neurons"))
def evidence_noreg_4_layers_100_neurons():
trainer_obj = trainers.Evidential
model_generator = models.get_correct_model(dataset="toy",
trainer=trainer_obj)
model, opts = model_generator.create(input_shape=1,
num_neurons=100,
num_layers=4)
trainer = trainer_obj(model,
opts,
learning_rate=5e-3,
lam=0.,
maxi_rate=0.)
model, rmse, nll = trainer.train(x_train,
y_train,
x_train,
y_train,
np.array([[1.]]),
iters=iterations,
batch_size=batch_size,
verbose=True)
plot_ng(model,
os.path.join(save_fig_dir, "evidence_noreg_4_layers_100_neurons"))
def compute_predictions():
RMSE = np.zeros((len(datasets), len(training_schemes), num_trials))
NLL = np.zeros((len(datasets), len(training_schemes), num_trials))
df_pred_uci = pd.DataFrame(
columns=["Dataset", "Method", "Target", "Mu", "Sigma"])
for di, dataset in enumerate(datasets):
for ti, trainer_obj in enumerate(training_schemes):
for n in range(num_trials):
(x_train,
y_train), (x_test,
y_test), y_scale = data_loader.load_dataset(
dataset, return_as_tensor=False)
batch_size = h_params[dataset]["batch_size"]
num_iterations = num_epochs * x_train.shape[0] // batch_size
print("Num of iterations :", num_iterations)
done = False
while not done:
with tf.device(dev):
model_generator = models.get_correct_model(
dataset="toy", trainer=trainer_obj)
model, opts = model_generator.create(
input_shape=x_train.shape[1:])
if method_names[
ti] == "Laplace": #training scheme is likelihood; as its 2nd in list
print("Trainienr lalpace likelihood")
trainer = trainer_obj(
model,
opts,
"laplace",
dataset,
learning_rate=h_params[dataset]
["learning_rate"])
elif method_names[ti] == "Gaussian":
print("Trainienr Gaussian likelihood")
trainer = trainer_obj(
model,
opts,
"gaussian",
dataset,
learning_rate=h_params[dataset]
["learning_rate"])
else:
trainer = trainer_obj(
model,
opts,
dataset,
learning_rate=h_params[dataset]
["learning_rate"])
model, rmse, nll = trainer.train(x_train,
y_train,
x_test,
y_test,
y_scale,
iters=num_iterations,
batch_size=batch_size,
verbose=True)
#Compute on validation data and save predictions
summary_to_add = get_prediction_summary(
dataset, method_names[ti], model, x_test, y_test)
df_pred_uci = df_pred_uci.append(summary_to_add,
ignore_index=True)
del model
tf.keras.backend.clear_session()
done = False if np.isinf(nll) or np.isnan(
nll) else True
print("saving {} {}".format(rmse, nll))
RMSE[di, ti, n] = rmse
NLL[di, ti, n] = nll
RESULTS = np.hstack((RMSE, NLL))
mu = RESULTS.mean(axis=-1)
error = np.std(RESULTS, axis=-1)
print("==========================")
print("[{}]: {} pm {}".format(dataset, mu, error))
print("==========================")
print("TRAINERS: {}\nDATASETS: {}".format(
[trainer.__name__ for trainer in training_schemes], datasets))
print("MEAN: \n{}".format(mu))
print("ERROR: \n{}".format(error))
return df_pred_uci
num_epochs = args.num_epochs
dev = "/cpu:0" # for small datasets/models cpu is faster than gpu
"""" ================================================"""
RMSE = np.zeros((len(datasets), len(training_schemes), num_trials))
NLL = np.zeros((len(datasets), len(training_schemes), num_trials))
for di, dataset in enumerate(datasets):
for ti, trainer_obj in enumerate(training_schemes):
for n in range(num_trials):
(x_train, y_train), (x_test, y_test), y_scale = data_loader.load_dataset(dataset, return_as_tensor=False)
batch_size = h_params[dataset]["batch_size"]
num_iterations = num_epochs * x_train.shape[0]//batch_size
done = False
while not done:
with tf.device(dev):
model_generator = models.get_correct_model(dataset="toy", trainer=trainer_obj)
model, opts = model_generator.create(input_shape=x_train.shape[1:])
trainer = trainer_obj(model, opts, dataset, learning_rate=h_params[dataset]["learning_rate"])
model, rmse, nll = trainer.train(x_train, y_train, x_test, y_test, y_scale, iters=num_iterations, batch_size=batch_size, verbose=True)
del model
tf.keras.backend.clear_session()
done = False if np.isinf(nll) or np.isnan(nll) else True
print("saving {} {}".format(rmse, nll))
RMSE[di, ti, n] = rmse
NLL[di, ti, n] = nll
RESULTS = np.hstack((RMSE, NLL))
mu = RESULTS.mean(axis=-1)
error = np.std(RESULTS, axis=-1)
print("==========================")