def ex_2_2(input1, target1, input2, target2):
## TODO
scores = []
scores_train = []
classifiers = []
for i in range(10):
classifier = MLPClassifier(hidden_layer_sizes=(20, ),
solver="adam",
max_iter=1000,
activation="tanh",
random_state=i)
classifier.fit(input1, target1[:, 0])
scores.append(classifier.score(input2, target2[:, 0]))
classifiers.append(classifier)
scores_train.append(classifier.score(input1, target1[:, 0]))
conf_mat = confusion_matrix(target2[:, 0],
classifiers[np.argmax(scores)].predict(input2))
plot_histogram_of_acc(scores_train, scores)
#plot_histogram_of_acc(classifiers[np.argmax(scores)], classifier.score(input2, target2[:, 0]))
#plot_histogram_of_acc(classifier.score(input1, target1[:,0]), classifier.score(input2, target2[:,0]))
predected_target = classifier.predict(input2)
misclassified_images = []
for i in range(len(target2[:, 0])):
if target2[:, 0][i] != predected_target[i]:
misclassified_images.append(input2[i])
for i in range(len(misclassified_images)):
plot_image(misclassified_images[i])
pass
def ex_2_2(input1, target1, input2, target2):
individualTarget1 = target1[:, 0]
individualTarget2 = target2[:, 0]
classifiers = []
training_scores = []
test_scores = []
for i in range(10):
classifiers.append(MLPClassifier(activation='tanh', hidden_layer_sizes=20, max_iter=1000, random_state=i))
for mlp in classifiers:
mlp.fit(input1, individualTarget1)
training_scores.append(mlp.score(input1, individualTarget1))
test_scores.append(mlp.score(input2, individualTarget2))
plot_histogram_of_acc(training_scores, test_scores)
best_index = test_scores.index(max(test_scores))
best_prediction = classifiers[best_index].predict(input2)
cnf_matrix = confusion_matrix(individualTarget2, best_prediction)
print(cnf_matrix)
misclassified_images = []
for i, pred in enumerate(best_prediction):
if pred != individualTarget2[i]:
misclassified_images.append(i)
plot_images(input2, misclassified_images)
def ex_2_2(input1, target1, input2, target2):
"""
Solution for exercise 2.2
:param input1: The input from dataset1
:param target1: The target from dataset1
:param input2: The input from dataset2
:param target2: The target from dataset2
:return:
"""
#declaring variables used for MLPClassifier
hidden_layers = 20
solver_mode = 'adam'
activation_mode = 'tanh'
max_iter = 1000
max_accuracy = 0.0
train_accuracy = []
test_accuracy = []
cfn = []
m = 0
for m in range(10):
cf = MLPClassifier(hidden_layer_sizes=(hidden_layers, ),
activation=activation_mode,
solver=solver_mode,
random_state=m,
max_iter=max_iter)
cf.fit(input1, target1[:, 0])
train_accuracy.append(cf.score(input1, target1[:, 0]))
current_test_accuracy = cf.score(input2, target2[:, 0])
test_accuracy.append(current_test_accuracy)
plot_histogram_of_acc(train_accuracy[m], test_accuracy[m])
if current_test_accuracy > max_accuracy:
cfn = confusion_matrix(target2[:, 0], cf.predict(input2))
max_accuracy = current_test_accuracy
print(cfn)
#plot_histogram_of_acc(train_accuracy, test_accuracy)
#plot_random_images(input2)
pass
def ex_2_2(input1, target1, input2, target2):
"""
Solution for exercise 2.2
:param input1: The input from dataset1
:param target1: The target from dataset1
:param input2: The input from dataset2
:param target2: The target from dataset2
:return:
"""
n = 10
train_acc = np.zeros(n)
test_acc = np.zeros(n)
pred_test = np.zeros((n, 564))
coefs = np.zeros((n, 960, 20))
#print(min(target1[:,0]), max(target1[:,0]))
# we have 20 person
for i in range(n):
classifier = MLPClassifier(hidden_layer_sizes=(20, ),
activation='tanh',
solver='adam',
max_iter=5000,
random_state=i)
classifier.fit(input1, target1[:, 0])
pred_test[i] = classifier.predict(input2)
coefs[i] = classifier.coefs_[0]
train_acc[i] = classifier.score(input1, target1[:, 0])
test_acc[i] = classifier.score(input2, target2[:, 0])
error = pred_test[1] - target2[:, 0]
for j in range(len(error)):
if (error[j] != 0):
print(j)
plot_random_images(np.row_stack((input2[175, :], input2[184, :])))
plot_random_images(np.row_stack((input2[210, :], input2[134, :])))
plot_random_images(np.row_stack((input2[223, :], input2[177, :])))
plot_random_images(np.row_stack((input2[179, :], input2[186, :])))
plot_histogram_of_acc(train_acc, test_acc)
# best network with seed i=1
confmat = confusion_matrix(target2[:, 0], pred_test[1])
print(confmat)
pass
def main():
data = load_data()
target1, input1, target2, input2 = \
data['target1'], normalize(data['input1']), data['target2'], normalize(data['input2'])
## Plot some random images
plot_random_images(input2)
## End plot some random images
## 2.1
## ex_2_1(input2, target2)
## End 2.1
## 2.2
train_acc, test_acc, y_pred, C = ex_2_2(input1, target1, input2, target2)
plot_histogram_of_acc(train_acc, test_acc)
print(C)
def ex_2_2(input1, target1, input2, target2):
"""
Solution for exercise 2.2
:param input1: The input from dataset1
:param target1: The target from dataset1
:param input2: The input from dataset2
:param target2: The target from dataset2
:return:
"""
train = input1
test = input2
target_train = target1[:, 1]
target_test = target2[:, 1]
## TODO
n_hidden_neurons = 20
accu_list_train = np.zeros((10,1))
accu_list_test = np.zeros((10, 1))
# Find the best seed
for seed in range(10):
nn = MLPClassifier(activation='tanh', solver='adam', max_iter=1000, hidden_layer_sizes=(n_hidden_neurons,), random_state=seed)
nn.fit(train, target_train)
accu_list_train[seed] = nn.score(train, target_train)
accu_list_test[seed] = nn.score(test, target_test)
print(accu_list_train)
print(accu_list_test)
# Compute NN weights with the best seed
best_seed = np.argmax(accu_list_train)
best_nn = nn = MLPClassifier(activation='tanh', solver='adam', max_iter=1000, hidden_layer_sizes=(n_hidden_neurons,),random_state=best_seed)
best_nn.fit(train, target_train)
# Evaluate the confusion matrix with best NN
predictions = nn.predict(test)
C = confusion_matrix(target_test, predictions)
print(C)
# Plot results
plot_histogram_of_acc(accu_list_train, accu_list_test)
print(accu_list_test)
# Find misclassified images
comp_array = target_test - predictions
comp_vector2 = np.nonzero(comp_array)
def ex_2_2(input1, target1, input2, target2):
target1 = np.transpose(target1)
target1 = target1[0]
target2 = np.transpose(target2)
target2 = target2[0]
acc_train = np.zeros((10, ))
acc_test = np.zeros((10, ))
max = -1
for i in range(10):
nn = MLPClassifier(random_state=i,
hidden_layer_sizes=(20, ),
activation='tanh',
solver='adam',
max_iter=1000)
model = nn.fit(input1, target1)
acc_train[i] = model.score(input1, target1)
acc_test[i] = model.score(input2, target2)
if acc_test[i] > max:
max = acc_test[i]
y_predict = model.predict(input2)
C = confusion_matrix(target2, y_predict)
k = 0
for i, a in enumerate(target2):
if a != y_predict[i] and k < 20:
plot_image(input2[i])
k = k + 1
hidden_layer_weights = model.coefs_
plot_hidden_layer_weights(hidden_layer_weights[0])
plot_histogram_of_acc(acc_train, acc_test)
print(C)
pass
def ex_2_2(input1, target1, input2, target2):
'''
• Write code to train a feed-forward neural network with 1 hidden layer containing 20 hidden units
for recognising the individuals. Use dataset1 for training, ‘adam’ as the training solver and train for
1000 iterations. Use dataset2 as the test set.
• Repeat the process 10 times starting from a different initial weight vector and plot the histogram
for the resulting accuracy on the training and on the test set (the accuracy is proportion of correctly
classified samples and it is computed with the method score of the classifier).
• Use the best network (with maximal accuracy on the test set) to calculate the confusion matrix for
the test set.
• Plot a few misclassified images.
'''
x_train = input1
y_train = target1[:, 0]
x_test = input2
y_test = target2[:, 0]
seeds = np.array(range(1, 11))
train_accs = []
test_accs = []
max_acc = -1
for index_seed, seed in np.ndenumerate(seeds):
nn = MLPClassifier(solver='adam',
activation='tanh',
max_iter=1000,
hidden_layer_sizes=(20, ),
random_state=seed)
nn.fit(x_train, y_train)
train_acc = accuracy_score(y_train, nn.predict(x_train))
train_accs.append(train_acc)
test_acc = accuracy_score(y_test, nn.predict(x_test))
test_accs.append(test_acc)
if test_acc > max_acc:
max_acc = test_acc
best_nn = nn
plot_histogram_of_acc(train_accs, test_accs)
cm = confusion_matrix(y_test, best_nn.predict(x_test))
prediction = best_nn.predict(x_test)
misclassified = np.where(y_test != prediction)
print(cm)
limit = 8
i = 0
for mc_index in misclassified[0]:
if i < limit:
fig, plts = plt.subplots(1, 2)
plts[0].set_title("Predicted Person " + str(prediction[mc_index]))
plts[0].imshow(input2[prediction[mc_index]].reshape(*IMAGE_DIM).T,
cmap=plt.cm.gray)
plts[0].set_xticks(())
plts[0].set_yticks(())
plts[1].set_title("Should be Person " + str(y_test[mc_index]))
plts[1].imshow(input2[y_test[mc_index]].reshape(*IMAGE_DIM).T,
cmap=plt.cm.gray)
plts[1].set_xticks(())
plts[1].set_yticks(())
plt.show()
i = i + 1
pass
