def classify(**args):
"""
Main method that prepares dataset, builds model, executes training and displays results.
:param args: keyword arguments passed from cli parser
"""
# only allow print-outs if execution has no repetitions
allow_print = args['repetitions'] == 1
# determine classification targets and parameters to construct datasets properly
cls_target, cls_str = set_classification_targets(args['cls_choice'])
d = prepare_dataset(args['dataset_choice'], cls_target, args['batch_size'])
print('\n\tTask: Classify «{}» using «{}»\n'.format(
cls_str, d['data_str']))
print_dataset_info(d)
# build and train
inputs = Input(shape=(7810, ))
models = [
build_model(i, d['num_classes'], inputs=inputs)
for i in range(args['num_models'])
]
# combine outputs of all models
y = Average()([m.outputs[0] for m in models])
model = Model(inputs, outputs=y, name='multiple')
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
if allow_print:
model.summary()
print('')
plot_model(model, to_file='img/multiple_mlp.png')
model.fit(d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'],
verbose=1,
class_weight=d['class_weights'])
# evaluation model
print('Evaluate ...')
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.evaluate(d['eval_data'], steps=d['test_steps'], verbose=1)
# predict on testset and calculate classification report and confusion matrix for diagnosis
print('Test ...')
pred = model.predict(d['test_data'], steps=d['test_steps'])
if allow_print:
diagnose_output(d['test_labels'], pred.argmax(axis=1),
d['classes_trans'])
return balanced_accuracy_score(d['test_labels'], pred.argmax(axis=1))
def classify(**args):
"""
Main method that prepares dataset, builds model, executes training and displays results.
:param args: keyword arguments passed from cli parser
"""
# only allow print-outs if execution has no repetitions
allow_print = args['repetitions'] == 1
# determine classification targets and parameters to construct datasets properly
cls_target, cls_str = set_classification_targets(args['cls_choice'])
d = prepare_dataset(args['dataset_choice'],
cls_target,
args['batch_size'],
train_shuffle_repeat=False,
categorical_labels=False)
print('\n\tTask: Classify «{}» using «{}» with DecisionTreeClassifier\n'.
format(cls_str, d['data_str']))
print_dataset_info(d)
model = DecisionTreeClassifier(class_weight='balanced')
# empty train data generator into list, then train. Careful with RAM
train_data = [
sample for batch in tqdm(
d['train_data'], total=d['train_steps'], desc='prep_train')
for sample in batch[0]
]
model.fit(train_data, d['train_labels'])
del train_data
# predict on testset and calculate classification report and confusion matrix for diagnosis
test_data = [
sample for batch in tqdm(
d['test_data'], total=d['test_steps'], desc='prep_test')
for sample in batch[0]
]
pred = model.predict(test_data)
del test_data
if allow_print:
# visualise decision tree, from datacamp.com/community/tutorials/decision-tree-classification-python
dot_data = StringIO()
export_graphviz(model,
out_file=dot_data,
filled=True,
rounded=True,
special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
graph.write_pdf('img/decision_tree.pdf')
diagnose_output(d['test_labels'], pred, d['classes_trans'])
return balanced_accuracy_score(d['test_labels'], pred)
def classify(**args):
"""
Main method that prepares dataset, builds model, executes training and displays results.
:param args: keyword arguments passed from cli parser
"""
# only allow print-outs if execution has no repetitions
allow_print = args['repetitions'] == 1
# determine classification targets and parameters to construct datasets properly
cls_target, cls_str = set_classification_targets(args['cls_choice'])
d = prepare_dataset(args['dataset_choice'], cls_target, args['batch_size'],
args['norm_choice'])
print('\n\tTask: Classify «{}» using «{}»\n'.format(
cls_str, d['data_str']))
print_dataset_info(d)
model = build_model(0,
d['num_classes'],
name='baseline_mlp',
new_input=True)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
if allow_print:
model.summary()
print('')
# callback to log data for TensorBoard
# tb_callback = TensorBoard(log_dir='./results', histogram_freq=0, write_graph=True, write_images=True)
# train and evaluate
model.fit(
d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'],
# callbacks=[tb_callback],
verbose=1,
class_weight=d['class_weights'])
model.evaluate(d['eval_data'], steps=d['test_steps'], verbose=1)
# predict on testset and calculate classification report and confusion matrix for diagnosis
pred = model.predict(d['test_data'], steps=d['test_steps'])
if allow_print:
diagnose_output(d['test_labels'], pred.argmax(axis=1),
d['classes_trans'])
return balanced_accuracy_score(d['test_labels'], pred.argmax(axis=1))
def classify(**args):
"""
Main method that prepares dataset, builds model, executes training and displays results.
:param args: keyword arguments passed from cli parser
"""
batch_size = 64
# determine classification targets and parameters to construct datasets properly
cls_target, cls_str = set_classification_targets(args['cls_choice'])
d = prepare_dataset(args['dataset_choice'], cls_target, batch_size)
print('\n\tTask: Classify «{}» using «{}»\n'.format(
cls_str, d['data_str']))
print_dataset_info(d)
model = build_model(0,
d['num_classes'],
name='baseline_mlp',
new_input=True)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
# train and evaluate
model.fit(d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'],
verbose=1,
class_weight=d['class_weights'])
print('Evaluate ...')
model.evaluate(d['eval_data'], steps=d['test_steps'], verbose=1)
# predict on testset and calculate classification report and confusion matrix for diagnosis
print('Test ...')
pred = model.predict(d['test_data'], steps=d['test_steps'])
diagnose_output(d['test_labels'], pred.argmax(axis=1), d['classes_trans'])
def classify(**args):
"""
Main method that prepares dataset, builds model, executes training and displays results.
:param args: keyword arguments passed from cli parser
"""
# only allow print-outs if execution has no repetitions
allow_print = args['repetitions'] == 1
# determine classification targets and parameters to construct datasets properly
cls_target, cls_str = set_classification_targets(args['cls_choice'])
d = prepare_dataset(0, cls_target, args['batch_size'], args['norm_choice'])
print('\n\tTask: Classify «{}» using «{}»'.format(cls_str, d['data_str']))
print_dataset_info(d)
model = build_model(0,
d['num_classes'],
name='baseline_mlp',
new_input=True)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
# train and evaluate - pre-transfer
model.fit(d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'],
verbose=1,
class_weight=d['class_weights'])
print('Evaluate ...')
model.evaluate(d['eval_data'], steps=d['test_steps'], verbose=1)
del d
d = prepare_dataset(
1, # HH12
cls_target,
args['batch_size'],
args['norm_choice'])
print_dataset_info(d)
# make layers untrainable and remove classification layer, then train new last layer on handheld data
for l in model.layers[:-1]:
l.trainable = False
if allow_print:
plot_model(model, to_file='img/transfer_mlp_pre.png')
new_layer = Dense(d['num_classes'],
activation='softmax',
name='dense_transfer')(model.layers[-2].output)
model = Model(inputs=model.inputs,
outputs=new_layer,
name='transfer_model')
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
if allow_print:
model.summary()
print('')
plot_model(model, to_file='img/transfer_mlp_post.png')
# train and evaluate - post-transfer
model.fit(d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'] * 2,
verbose=1,
class_weight=d['class_weights'])
print('Evaluate ...')
model.evaluate(d['eval_data'], steps=d['test_steps'], verbose=1)
# predict on testset and calculate classification report and confusion matrix for diagnosis
print('Test ...')
pred = model.predict(d['test_data'], steps=d['test_steps'])
diagnose_output(
d['test_labels'],
pred.argmax(axis=1),
d['classes_trans'],
show=False,
file_name=
f'heatmap_transfer_{datetime.now().hour}_{datetime.now().minute}')
return balanced_accuracy_score(d['test_labels'], pred.argmax(axis=1))
def classify(**args):
"""
Main method that prepares dataset, builds model, executes training and displays results.
:param args: keyword arguments passed from cli parser
"""
# only allow print-outs if execution has no repetitions
allow_print = args['repetitions'] == 1
# determine classification targets and parameters to construct datasets properly
cls_target, cls_str = set_classification_targets(args['cls_choice'])
d = prepare_dataset(
0, # any synthetic
cls_target,
args['batch_size'])
print('\n\tTask: Classify «{}» using «{}»\n'.format(
cls_str, d['data_str']))
print_dataset_info(d)
model = build_model(1, d['num_classes'], name='concat_mlp', new_input=True)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
if allow_print:
model.summary()
plot_model(model, to_file='img/concat_mlp.png')
# train and evaluate
model.fit(d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'],
verbose=1,
class_weight=d['class_weights'])
model.evaluate(d['eval_data'], steps=d['test_steps'], verbose=1)
del d
# load handheld dataset for evaluation
d = prepare_dataset(
2, # any handheld
cls_target,
args['batch_size'])
print_dataset_info(d)
# build model for handheld data, concatenates the output of the last pre-classification layer of the synthetic network
concat_model = build_model_concat(2, d['num_classes'], concat_model=model)
concat_model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
if allow_print:
concat_model.summary()
plot_model(concat_model, to_file='img/concat_mlp.png')
concat_model.fit(d['train_data'],
steps_per_epoch=d['train_steps'],
epochs=args['epochs'],
verbose=1,
class_weight=d['class_weights'])
# predict on test set and calculate classification report and confusion matrix for diagnosis
pred = model.predict(d['test_data'], steps=d['test_steps'])
if allow_print:
diagnose_output(d['test_labels'], pred.argmax(axis=1),
d['classes_trans'])
return balanced_accuracy_score(d['test_labels'], pred.argmax(axis=1))