def attach(self, model):
self.e2efs_layer = self.get_layer(model.input_shape[1:])
self.model = self.e2efs_layer.add_to_model(
model, input_shape=model.input_shape[1:])
kwargs = model.optimizer.get_config()
if 'sgd' in type(model.optimizer).__name__.lower():
opt = custom_optimizers.E2EFS_SGD(self.e2efs_layer,
th=self.th,
**kwargs)
elif 'adam' in type(model.optimizer).__name__.lower():
opt = custom_optimizers.E2EFS_Adam(self.e2efs_layer,
th=self.th,
**kwargs)
else:
raise Exception(
'Optimizer not supported. Contact the authors if you need it')
self.model.compile(opt, model.loss, model.metrics, model.loss_weights,
model.sample_weight_mode, model.weighted_metrics)
return self
def main():
dataset = load_dataset()
train_data = np.asarray(dataset['train']['data'])
train_labels = dataset['train']['label']
num_classes = len(np.unique(train_labels))
test_data = np.asarray(dataset['test']['data'])
test_labels = dataset['test']['label']
train_labels = to_categorical(train_labels, num_classes=num_classes)
test_labels = to_categorical(test_labels, num_classes=num_classes)
generator = dataset['generator']
fs_generator = dataset['fs_generator']
generator_kwargs = {
'batch_size': batch_size
}
print('reps : ', reps)
name = 'mnist_' + fs_network + '_r_' + str(regularization)
print(name)
model_kwargs = {
'nclasses': num_classes,
'regularization': regularization
}
total_features = int(np.prod(train_data.shape[1:]))
fs_filename = directory + fs_network + '_trained_model.h5'
classifier_filename = directory + classifier_network + '_trained_model.h5'
if not os.path.isdir(directory):
os.makedirs(directory)
if not os.path.exists(fs_filename) and warming_up:
np.random.seed(1001)
tf.set_random_seed(1001)
model = getattr(network_models, fs_network)(input_shape=train_data.shape[1:], **model_kwargs)
print('training_model')
model.fit_generator(
generator.flow(train_data, train_labels, **generator_kwargs),
steps_per_epoch=train_data.shape[0] // batch_size, epochs=110,
callbacks=[
callbacks.LearningRateScheduler(scheduler())
],
validation_data=(test_data, test_labels),
validation_steps=test_data.shape[0] // batch_size,
verbose=verbose
)
model.save(fs_filename)
del model
K.clear_session()
for e2efs_class in e2efs_classes:
nfeats = []
accuracies = []
times = []
cont_seed = 0
for factor in [.05, .1, .25, .5]:
n_features = int(total_features * factor)
n_accuracies = []
n_times = []
for r in range(reps):
print('factor : ', factor, ' , rep : ', r)
np.random.seed(cont_seed)
tf.set_random_seed(cont_seed)
cont_seed += 1
mask = (np.std(train_data, axis=0) > 1e-3).astype(int).flatten()
classifier = load_model(fs_filename) if warming_up else getattr(network_models, fs_network)(input_shape=train_data.shape[1:], **model_kwargs)
e2efs_layer = e2efs_class(n_features, input_shape=train_data.shape[1:], kernel_initializer=initializers.constant(mask))
model = e2efs_layer.add_to_model(classifier, input_shape=train_data.shape[1:])
optimizer = custom_optimizers.E2EFS_Adam(e2efs_layer=e2efs_layer, lr=1e-3) # optimizers.adam(lr=1e-2)
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['acc'])
model.fs_layer = e2efs_layer
model.classifier = classifier
model.summary()
start_time = time.time()
model.fit_generator(
fs_generator.flow(train_data, train_labels, **generator_kwargs),
steps_per_epoch=train_data.shape[0] // batch_size, epochs=20000,
callbacks=[
E2EFSCallback(verbose=verbose)
],
validation_data=(test_data, test_labels),
validation_steps=test_data.shape[0] // batch_size,
verbose=verbose
)
fs_rank = np.argsort(K.eval(model.heatmap))[::-1]
mask = np.zeros(train_data.shape[1:])
mask.flat[fs_rank[:n_features]] = 1.
# mask = K.eval(model.fs_kernel).reshape(train_data.shape[1:])
n_times.append(time.time() - start_time)
print('nnz : ', np.count_nonzero(mask))
del model
K.clear_session()
model = load_model(classifier_filename) if warming_up else getattr(network_models, classifier_network)(
input_shape=train_data.shape[1:], **model_kwargs)
optimizer = optimizers.Adam(lr=1e-2) # optimizers.adam(lr=1e-2)
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['acc'])
model.fit_generator(
generator.flow(mask * train_data, train_labels, **generator_kwargs),
steps_per_epoch=train_data.shape[0] // batch_size, epochs=80,
callbacks=[
callbacks.LearningRateScheduler(scheduler()),
],
validation_data=(mask * test_data, test_labels),
validation_steps=test_data.shape[0] // batch_size,
verbose=verbose
)
n_accuracies.append(model.evaluate(mask * test_data, test_labels, verbose=0)[-1])
del model
K.clear_session()
print(
'n_features : ', n_features, ', acc : ', n_accuracies, ', time : ', n_times
)
accuracies.append(n_accuracies)
nfeats.append(n_features)
times.append(n_times)
output_filename = directory + fs_network + '_' + classifier_network + '_' + e2efs_class.__name__ + \
'_results_warming_' + str(warming_up) + '.json'
try:
with open(output_filename) as outfile:
info_data = json.load(outfile)
except:
info_data = {}
if name not in info_data:
info_data[name] = []
info_data[name].append(
{
'regularization': regularization,
'reps': reps,
'classification': {
'n_features': nfeats,
'accuracy': accuracies,
'times': times
}
}
)
with open(output_filename, 'w') as outfile:
json.dump(info_data, outfile)
def main():
dataset = load_dataset()
for network_name in network_names:
train_data = np.asarray(dataset['train']['data'])
train_labels = dataset['train']['label']
num_classes = len(np.unique(train_labels))
test_data = np.asarray(dataset['test']['data'])
test_labels = dataset['test']['label']
train_labels = to_categorical(train_labels, num_classes=num_classes)
test_labels = to_categorical(test_labels, num_classes=num_classes)
generator = dataset['generator']
generator_fs = dataset['generator_fs']
generator_kwargs = {
'batch_size': batch_size
}
print('reps : ', reps)
name = 'fashion_mnist_' + network_name + '_r_' + str(regularization)
print(name)
model_kwargs = {
'nclasses': num_classes,
'regularization': regularization
}
total_features = int(np.prod(train_data.shape[1:]))
model_filename = directory + network_name + '_trained_model.h5'
if not os.path.isdir(directory):
os.makedirs(directory)
if not os.path.exists(model_filename) and warming_up:
np.random.seed(1001)
tf.set_random_seed(1001)
model = getattr(network_models, network_name)(input_shape=train_data.shape[1:], **model_kwargs)
print('training_model')
model.fit_generator(
generator.flow(train_data, train_labels, **generator_kwargs),
steps_per_epoch=train_data.shape[0] // batch_size, epochs=80,
callbacks=[
callbacks.LearningRateScheduler(scheduler())
],
validation_data=(test_data, test_labels),
validation_steps=test_data.shape[0] // batch_size,
verbose=verbose
)
model.save(model_filename)
del model
K.clear_session()
for e2efs_class in e2efs_classes:
nfeats = []
accuracies = []
times = []
cont_seed = 0
for r in range(reps):
temp_filename = temp_directory + network_name + '_' + e2efs_class.__name__ + \
'_e2efs_heatmap_iter_' + str(r) + '.npy'
if os.path.exists(temp_filename):
heatmap = np.load(temp_filename)
else:
heatmap = np.zeros(np.prod(train_data.shape[1:]))
start_time = time.time()
for fs_r in range(fs_reps):
print('rep : ', fs_r)
np.random.seed(cont_seed)
tf.set_random_seed(cont_seed)
cont_seed += 1
classifier = load_model(model_filename) if warming_up else getattr(network_models, network_name)(
input_shape=train_data.shape[1:], **model_kwargs)
e2efs_layer = e2efs_class(1, input_shape=train_data.shape[1:],)
# kernel_initializer=initializers.constant(mask))
model = e2efs_layer.add_to_model(classifier, input_shape=test_data.shape[1:])
# optimizer = custom_optimizers.E2EFS_SGD(e2efs_layer=e2efs_layer, lr=1e-1) # optimizers.adam(lr=1e-2)
optimizer = custom_optimizers.E2EFS_Adam(e2efs_layer=e2efs_layer, lr=1e-2)
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['acc'])
model.fs_layer = e2efs_layer
model.classifier = classifier
model.summary()
model.fit_generator(
generator_fs.flow(train_data, train_labels, **generator_kwargs),
steps_per_epoch=train_data.shape[0] // batch_size, epochs=20000,
callbacks=[
E2EFSCallback(units=int(total_features * 0.05),
verbose=verbose)
],
validation_data=(test_data, test_labels),
validation_steps=test_data.shape[0] // batch_size,
verbose=verbose
)
heatmap += K.eval(model.heatmap)
del model
K.clear_session()
if not os.path.isdir(temp_directory):
os.makedirs(temp_directory)
np.save(temp_filename, heatmap)
times.append(time.time() - start_time)
fs_rank = np.argsort(heatmap)[::-1]
for i, factor in enumerate([.05, .1, .25, .5]):
print('factor : ', factor, ' , rep : ', r)
n_features = int(total_features * factor)
mask = np.zeros(train_data.shape[1:])
mask.flat[fs_rank[:n_features]] = 1.
np.random.seed(cont_seed)
tf.set_random_seed(cont_seed)
cont_seed += 1
model = load_model(model_filename) if warming_up else getattr(network_models, network_name)(input_shape=train_data.shape[1:], **model_kwargs)
# optimizer = optimizers.RMSprop(learning_rate=1e-2) # optimizers.SGD(lr=1e-1) #
optimizer = optimizers.Adam(lr=1e-2)
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['acc'])
model.fit_generator(
generator.flow(mask * train_data, train_labels, **generator_kwargs),
steps_per_epoch=train_data.shape[0] // batch_size, epochs=80,
callbacks=[
callbacks.LearningRateScheduler(scheduler()),
],
validation_data=(mask * test_data, test_labels),
validation_steps=test_data.shape[0] // batch_size,
verbose=verbose
)
acc = model.evaluate(mask * test_data, test_labels, verbose=0)[-1]
if i < len(accuracies):
accuracies[i].append(acc)
else:
accuracies.append([acc])
nfeats.append(n_features)
del model
K.clear_session()
print(
'n_features : ', n_features, ', acc : ', acc, ', time : ', times[-1]
)
output_filename = directory + network_name + '_' + e2efs_class.__name__ + \
'_e2efs_results_warming_' + str(warming_up) + '.json'
try:
with open(output_filename) as outfile:
info_data = json.load(outfile)
except:
info_data = {}
if name not in info_data:
info_data[name] = []
info_data[name].append(
{
'regularization': regularization,
'reps': reps,
'classification': {
'n_features': nfeats,
'accuracy': accuracies,
'times': times
}
}
)
with open(output_filename, 'w') as outfile:
json.dump(info_data, outfile)