Optimization of Hyperparameters in a CNN - optimization

Question

EDIT: I adjusted the model as suggested. That means I included lr and dropout as arguments in the ConvNet function.
I am new to Neural Networks and CNNs and facing a problem regarding Optimization of Hyperparameters. So now I will explain my process so far:
With the help of various excellent Blog-Posts I was able to build a CNN that works for my project. In my project I am trying to predict the VIX and S&P 500 with the help of the FOMC meeting statements. So basically I habe text data on the one hand and financial data (returns) on the other hand. After preprocessing and applying Googles Word2Vec pre-trained Word-Embeddings I built the following Convolutional Network:
def ConvNet(embeddings, max_sequence_length, num_words, embedding_dim, trainable=False, extra_conv=True,
lr=0.001, dropout=0.5):
embedding_layer = Embedding(num_words,
embedding_dim,
weights=[embeddings],
input_length=max_sequence_length,
trainable=trainable)
sequence_input = Input(shape=(max_sequence_length,), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
convs = []
filter_sizes = [3, 4, 5]
for filter_size in filter_sizes:
l_conv = Conv1D(filters=128, kernel_size=filter_size, activation='relu')(embedded_sequences)
l_pool = MaxPooling1D(pool_size=3)(l_conv)
convs.append(l_pool)
l_merge = concatenate([convs[0], convs[1], convs[2]], axis=1)
# add a 1D convnet with global maxpooling, instead of Yoon Kim model
conv = Conv1D(filters=128, kernel_size=3, activation='relu')(embedded_sequences)
pool = MaxPooling1D(pool_size=3)(conv)
if extra_conv == True:
x = Dropout(dropout)(l_merge)
else:
# Original Yoon Kim model
x = Dropout(dropout)(pool)
x = Flatten()(x)
x = Dense(128, activation='relu')(x)
preds = Dense(1, activation='linear')(x)
model = Model(sequence_input, preds)
sgd = SGD(learning_rate = lr, momentum= 0.8)
model.compile(loss='mean_squared_error',
optimizer= sgd,
metrics=['mean_squared_error'])
model.summary()
return model
My model architecture looks like this:
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 1086) 0
__________________________________________________________________________________________________
embedding_1 (Embedding) (None, 1086, 300) 532500 input_1[0][0]
__________________________________________________________________________________________________
conv1d_1 (Conv1D) (None, 1084, 128) 115328 embedding_1[0][0]
__________________________________________________________________________________________________
conv1d_2 (Conv1D) (None, 1083, 128) 153728 embedding_1[0][0]
__________________________________________________________________________________________________
conv1d_3 (Conv1D) (None, 1082, 128) 192128 embedding_1[0][0]
__________________________________________________________________________________________________
max_pooling1d_1 (MaxPooling1D) (None, 361, 128) 0 conv1d_1[0][0]
__________________________________________________________________________________________________
max_pooling1d_2 (MaxPooling1D) (None, 361, 128) 0 conv1d_2[0][0]
__________________________________________________________________________________________________
max_pooling1d_3 (MaxPooling1D) (None, 360, 128) 0 conv1d_3[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 1082, 128) 0 max_pooling1d_1[0][0]
max_pooling1d_2[0][0]
max_pooling1d_3[0][0]
__________________________________________________________________________________________________
dropout_2 (Dropout) (None, 1082, 128) 0 concatenate_1[0][0]
__________________________________________________________________________________________________
flatten_1 (Flatten) (None, 138496) 0 dropout_2[0][0]
__________________________________________________________________________________________________
dense_3 (Dense) (None, 128) 17727616 flatten_1[0][0]
__________________________________________________________________________________________________
dense_4 (Dense) (None, 1) 129 dense_3[0][0]
==================================================================================================
Total params: 18,721,429
Trainable params: 18,188,929
Non-trainable params: 532,500
So, now I am facing the next big problem, and I am really running out of ideas how to solve is: Optimization of hyperparameters
My problem ist, that every code example I found so far is applied to the Optimization of hyperparameters is to the architecture:
model = Sequential()
embedding = model.add(layers.Embedding(MAX_VOCAB_SIZE, EMBEDDING_DIM, input_length=MAX_SEQUENCE_LENGTH))
model.add(layers.Conv1D(filters=128, kernel_size=5, activation='relu'))
model.add(layers.MaxPool1D(pool_size=3))
model.add(Dropout(0.25))
So my specific question is, how to perform the Optimization of hyperparameters, because whenever I change something in my ConvNet I am getting errors an as I said all tutorials I can find are applied to model = Sequential().
The new error message is:
__________________________________________________________________________________________________
0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
job exception: 'Model' object is not subscriptable
Traceback (most recent call last):
File "/Users/lukaskoston/Desktop/MasterarbeitFOMCAnalysis/07_Regression/CNN regression neu.py", line 262, in <module>
max_evals=100)
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/fmin.py", line 482, in fmin
show_progressbar=show_progressbar,
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/base.py", line 686, in fmin
show_progressbar=show_progressbar,
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/fmin.py", line 509, in fmin
rval.exhaust()
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/fmin.py", line 330, in exhaust
self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/fmin.py", line 286, in run
self.serial_evaluate()
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/fmin.py", line 165, in serial_evaluate
result = self.domain.evaluate(spec, ctrl)
File "/Users/lukaskoston/.local/lib/python3.7/site-packages/hyperopt/base.py", line 894, in evaluate
rval = self.fn(pyll_rval)
File "/Users/lukaskoston/Desktop/MasterarbeitFOMCAnalysis/07_Regression/CNN regression neu.py", line 248, in train_and_score
return hist['val_loss'][-1]
TypeError: 'Model' object is not subscriptable
Thanks in advance,
Lukas

Answer 1

You should make your hyperparameters arguments to your method.
def ConvNet(embeddings, max_sequence_length, num_words, embedding_dim, trainable=False, extra_conv=True
lr=1.0, dropout=0.5):
# ...
Then you can update your code to use those values instead of the fixed values or Keras defaults.
if extra_conv == True:
x = Dropout(dropout)(l_merge)
else:
# Original Yoon Kim model
x = Dropout(dropout)(pool)
And:
model.compile(loss='mean_squared_error',
optimizer=keras.optimizers.Adadelta(learning_rate=lr).
metrics=['mean_squared_error'])
I would start with those two, and leave batch size and epoch count for later. Those can have a big effect on run time, which is hard to account for in the hyperparameter optimization.
Then you can optimize with a library like hyperopt.
from hyperopt import fmin, hp, tpe, space_eval
def train_and_score(args):
# Train the model the fixed params plus the optimization args.
# Note that this method should return the final History object.
hist = ConvNet(embeddings, max_sequence_length, num_words,
embedding_dim, trainable=False, extra_conv=True,
lr=args['lr'], dropout=args['dropout'])
# Unpack and return the last validation loss from the history.
return hist['val_loss'][-1]
# Define the space to optimize over.
space = {
'lr': hp.loguniform('lr', np.log(0.1), np.log(10.0)),
'dropout': hp.uniform('dropout', 0, 1),
}
# Minimize the training score over the space.
trials = Trials()
best = fmin(train_and_score, space, trials=trials, algo=tpe.suggest, max_evals=100)
# Print details about the best results and hyperparameters.
print(best)
print(space_eval(space, best))
There are also libraries that will help you directly integrate this with Keras. A popular choice is hyperas. In that case you would modify your function to use some templates instead of parameters, but it is otherwise very similar.