def evaluator(x_train, y_train, x_val, y_val, experiment_path="", **kwargs):
# Define model
model = Sequential(loss="cross_entropy")
model.add(
Dense(nodes=10, input_dim=x_train.shape[0], weight_initialization="fixed"))
model.add(Activation("softmax"))
# Fit model
model.fit(X=x_train, Y=y_train, X_val=x_val, Y_val=y_val, **kwargs)
model.plot_training_progress(show=False, save=True, name="figures/" + dict_to_string(kwargs))
model.save(experiment_path + "/" + dict_to_string(kwargs))
# Minimizing value: validation accuracy
val_acc = model.get_classification_metrics(x_val, y_val)[0] # Get accuracy
result = {"value": val_acc, "model": model} # Save score and model
return result
def evaluator(l2_reg):
# Define model
model = Sequential(loss=CrossEntropy(), metric=Accuracy())
model.add(Dense(nodes=800, input_dim=x_train.shape[0]))
model.add(Relu())
model.add(Dense(nodes=10, input_dim=800))
model.add(Softmax())
ns = 800
# Define callbacks
mt = MetricTracker() # Stores training evolution info
lrs = LearningRateScheduler(evolution="cyclic",
lr_min=1e-3,
lr_max=1e-1,
ns=ns) # Modifies lr while training
callbacks = [mt, lrs]
# Fit model
iterations = 4 * ns
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
iterations=iterations,
l2_reg=l2_reg,
shuffle_minibatch=True,
callbacks=callbacks)
model.save("models/yes_dropout_test")
# Test model
val_acc = model.get_metric_loss(x_val, y_val)[0]
test_acc = model.get_metric_loss(x_test, y_test)[0]
subtitle = "L2 param: " + str(l2_reg) + ", Test acc: " + str(test_acc)
mt.plot_training_progress(show=True,
save=True,
name="figures/l2reg_optimization/" + str(l2_reg),
subtitle=subtitle)
print("Val accuracy:", val_acc)
print("Test accuracy:", test_acc)
return val_acc
k1 = 6 # First kernel y size
n2 = 20 # Filters of second Conv2D
k2 = 4 # Second kernel y size
# Define model
model = Sequential(loss=CrossEntropy(class_count=None), metric=Accuracy())
model.add(
Conv2D(num_filters=n1,
kernel_shape=(d, k1),
input_shape=x_train.shape[:-1]))
model.add(Relu())
model.add(Conv2D(num_filters=n2, kernel_shape=(1, k2)))
model.add(Relu())
model.add(Flatten())
model.add(Dense(nodes=y_train.shape[0]))
model.add(Softmax())
# Fit model
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
epochs=500,
lr=1e-3,
momentum=0.8,
l2_reg=0.001,
compensate=True,
callbacks=callbacks)
model.save("models/names_best")
mt.plot_training_progress(save=True, name="figures/names_best")
# y_pred_prob = model.predict(x_train)
def evaluator(x_train, y_train, x_val, y_val, experiment_name="", **kwargs):
print(kwargs)
# Saving directories
figure_file = "figures/" + experiment_name + "/" + dict_to_string(kwargs)
model_file = "models/" + experiment_name + "/" + dict_to_string(kwargs)
mt = MetricTracker() # Stores training evolution info (losses and metrics)
# Define model
d = x_train.shape[0]
n1 = kwargs["n1"] # Filters of first Conv2D
k1 = kwargs["k1"] # First kernel y size
n2 = kwargs["n2"] # Filters of second Conv2D
k2 = kwargs["k2"] # Second kernel y size
batch_size = kwargs["batch_size"]
try:
# Define model
model = Sequential(loss=CrossEntropy(class_count=None),
metric=Accuracy())
model.add(
Conv2D(num_filters=n1,
kernel_shape=(d, k1),
input_shape=x_train.shape[:-1]))
model.add(Relu())
model.add(Conv2D(num_filters=n2, kernel_shape=(1, k2)))
model.add(Relu())
model.add(Flatten())
model.add(Dense(nodes=y_train.shape[0]))
model.add(Softmax())
# Fit model
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=batch_size,
epochs=1000,
lr=1e-2,
momentum=0.8,
l2_reg=0.001,
compensate=True,
callbacks=[mt])
except Exception as e:
print(e)
return -1 # If configuration impossible
model.save(model_file)
# Write results
n1 = str(n1)
n2 = str(n2)
k1 = str(k1)
k2 = str(k2)
batch_size = str(batch_size)
subtitle = "n1:" + n1 + ", n2:" + n2 + ", k1:" + k1 + ", k2:" + k1 +\
", batch_size:" + batch_size
mt.plot_training_progress(show=False,
save=True,
name=figure_file,
subtitle=subtitle)
# Maximizing value: validation accuracy
return model.val_metric
lrs = LearningRateScheduler(evolution="cyclic",
lr_min=1e-3,
lr_max=1e-1,
ns=ns) # Modifies lr while training
# callbacks = [mt, bms, lrs]
callbacks = [mt, lrs]
# Fit model
iterations = 4 * ns
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
iterations=iterations,
momentum=0.89,
l2_reg=1e-5,
shuffle_minibatch=True,
callbacks=callbacks)
model.save("models/yes_dropout_test")
# Test model
# best_model = bms.get_best_model()
# test_acc, test_loss = best_model.get_metric_loss(x_test, y_test)
# subtitle = "No Dropout, Test acc: " + test_acc
subtitle = ""
mt.plot_training_progress(show=True,
save=True,
name="figures/test_dropout_test",
subtitle=subtitle)
# print("Test accuracy:", test_acc)
model.add(Flatten())
model.add(Dense(nodes=200))
model.add(Relu())
model.add(Dense(nodes=10))
model.add(Softmax())
# for filt in model.layers[0].filters:
# print(filt)
# y_pred_prob = model.predict(x_train)
# print(y_pred_prob)
# Fit model
# model.load("models/cifar_test_2")
# mt.load("models/tracker")
model.fit(X=x_train, Y=y_train, X_val=x_val, Y_val=y_val,
batch_size=100, epochs=20, momentum=0.9, l2_reg=0.003, callbacks=callbacks)
model.save("models/cifar_test_3")
# model.layers[0].show_filters()
# for filt in model.layers[0].filters:
# print(filt)
# print(model.layers[0].biases)
mt.plot_training_progress()
# y_pred_prob = model.predict(x_train)
# # # model.pred
# print(y_train)
# print(np.round(y_pred_prob, decimals=2))
# Preprocessing
mean_x = np.mean(x_train)
std_x = np.std(x_train)
x_train = (x_train - mean_x) / std_x
x_val = (x_val - mean_x) / std_x
x_test = (x_test - mean_x) / std_x
# Define model
model = Sequential(loss=CrossEntropy())
model.add(Dense(nodes=10, input_dim=x_train.shape[0]))
model.add(Softmax())
# Fit model
# model.load("models/mlp_test")
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
epochs=40,
lr=0.001,
momentum=0.0,
l2_reg=0.0,
shuffle_minibatch=False)
model.plot_training_progress(save=True, name="figures/mlp_test")
model.save("models/mlp_test")
# Test model
test_acc, test_loss = model.get_classification_metrics(x_test, y_test)
print("Test accuracy:", test_acc)
model.add(Softmax())
# for filt in model.layers[0].filters:
# print(filt)
# y_pred_prob = model.predict(x_train)
# print(y_pred_prob)
# Fit model
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
epochs=200,
lr=1e-2,
momentum=0.5,
callbacks=callbacks)
model.save("models/mnist_test_conv_2")
# model.layers[0].show_filters()
# for filt in model.layers[0].filters:
# print(filt)
# print(model.layers[0].biases)
mt.plot_training_progress()
y_pred_prob = model.predict(x_train)
# # # model.pred
# print(y_train)
# print(np.round(y_pred_prob, decimals=2))
x_train = (x_train - mean_x) / std_x
x_val = (x_val - mean_x) / std_x
x_test = (x_test - mean_x) / std_x
# Define model
model = Sequential(loss=CrossEntropy())
model.add(Dense(nodes=50, input_dim=x_train.shape[0]))
model.add(Relu())
model.add(Dense(nodes=10, input_dim=50))
model.add(Softmax())
# Fit model
x_train = x_train[:, 0:100]
y_train = y_train[:, 0:100]
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
epochs=200,
lr=0.001,
momentum=0.0,
l2_reg=0.0,
shuffle_minibatch=False,
save_path="models/mlp_overfit_test")
model.plot_training_progress(save=True, name="figures/mlp_overfit_test")
model.save("models/mlp_overfit_test")
# Test model
test_acc, test_loss = model.get_classification_metrics(x_test, y_test)
print("Test accuracy:", test_acc)
mt = MetricTracker() # Stores training evolution info
lrs = LearningRateScheduler(evolution="cyclic",
lr_min=1e-5,
lr_max=1e-1,
ns=ns) # Modifies lr while training
callbacks = [mt, lrs]
# Fit model
iterations = 6 * ns
model.fit(X=x_train,
Y=y_train,
X_val=x_val,
Y_val=y_val,
batch_size=100,
iterations=iterations,
l2_reg=10**-1.85,
shuffle_minibatch=True,
callbacks=callbacks)
model.save("models/l2reg_optimization_good")
# Test model
val_acc = model.get_metric_loss(x_val, y_val)[0]
test_acc = model.get_metric_loss(x_test, y_test)[0]
subtitle = "Test acc: " + str(test_acc)
mt.plot_training_progress(show=True,
save=True,
name="figures/l2reg_optimization/good",
subtitle=subtitle)
print("Val accuracy:", val_acc)
print("Test accuracy:", test_acc)