def make_network2(input_shape=INPUT_SHAPE):
return (NeuralNetwork()
.input(input_shape)
.conv([5, 5, 12]) # <== doubled
.max_pool()
.relu()
.conv([5, 5, 32]) # <== doubled
.max_pool()
.relu()
.flatten()
.dense(240) # <== doubled
.relu()
.dense(N_CLASSES))
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network2(), make_adam(1.0e-3))
learning_curve = train_evaluate(pipeline)
session.save('checkpoint/network2.ckpt')
show_learning_curve(learning_curve)
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network2())
session.load('checkpoint/network2.ckpt')
pred = pipeline.predict(X_valid)
cm = confusion_matrix(y_valid, pred)
plot_confusion_matrix(cm)
print_confusion_matrix(cm)
'''X_new = np.array(glob.glob('images/*.ppm'))
new_images = [plt.imread(path) for path in X_new]
for result in sorted(results, key=lambda x: -x[2]):
print('{:>2} {:<50} {:6.2f}% {:>4}'.format(*result, sum(y_train==result[0])))
accuracies.append(result[2])
print('-'*50)
print('Accuracy: Mean: {:.3f} Std: {:.3f}'.format(np.mean(accuracies), np.std(accuracies)))
def make_network3(input_shape=INPUT_SHAPE):
return (NeuralNetwork()
.input(input_shape)
.conv([5, 5, 24]) # <== doubled
.max_pool()
.relu()
.conv([5, 5, 64]) # <== doubled
.max_pool()
.relu()
.flatten()
.dense(480) # <== doubled
.relu()
.dense(N_CLASSES))
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network3(), make_adam(0.5e-3))
learning_curve = train_evaluate(pipeline,epochs=100)
session.save('checkpoint/network3_e_100_lr_0.5e-3.ckpt')
show_learning_curve(learning_curve)
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network3())
session.load('checkpoint/network3_e_100_lr_0.5e-3.ckpt')
pred = pipeline.predict(X_valid)
cm = confusion_matrix(y_valid, pred)
plot_confusion_matrix(cm)
print_confusion_matrix(cm)
sum(y_train == result[0])))
accuracies.append(result[2])
print('-' * 50)
print('Accuracy: Mean: {:.3f} Std: {:.3f}'.format(np.mean(accuracies),
np.std(accuracies)))
def make_network5(input_shape=INPUT_SHAPE):
return (NeuralNetwork().input(input_shape).conv(
[5, 5, 24]).max_pool().elu() # <== ELU
.conv([5, 5, 64]).max_pool().elu() # <== ELU
.flatten().dense(480).elu() # <== ELU
.dense(N_CLASSES))
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network5(),
make_adam(0.5e-3))
learning_curve = train_evaluate(pipeline, epochs=20)
session.save('checkpoint/network5.ckpt')
show_learning_curve(learning_curve)
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network5())
session.load('checkpoint/network5.ckpt')
pred = pipeline.predict(X_valid)
cm = confusion_matrix(y_valid, pred)
plot_confusion_matrix(cm)
print_confusion_matrix(cm)
accuracies = []
for result in sorted(results, key=lambda x: -x[2]):
print('{:>2} {:<50} {:6.2f}% {:>4}'.format(*result,
sum(y_train == result[0])))
accuracies.append(result[2])
print('-' * 50)
print('Accuracy: Mean: {:.3f} Std: {:.3f}'.format(np.mean(accuracies),
np.std(accuracies)))
def make_network3(input_shape=INPUT_SHAPE):
return (NeuralNetwork().input(input_shape).conv([5, 5, 24]) # <== doubled
.max_pool().relu().conv([5, 5, 64]) # <== doubled
.max_pool().relu().flatten().dense(480) # <== doubled
.relu().dense(N_CLASSES))
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network3(),
make_adam(1.0e-3))
learning_curve = train_evaluate(pipeline, epochs=20)
session.save('checkpoint/network3_epochs20.ckpt')
show_learning_curve(learning_curve)
with Session() as session:
pipeline = build_pipeline(preprocessors, session, make_network3())
session.load('checkpoint/network3_epochs100.ckpt')
pred = pipeline.predict(X_valid)
cm = confusion_matrix(y_valid, pred)
plot_confusion_matrix(cm)
print_confusion_matrix(cm)