0
$\begingroup$

I am trying to use CNN on multivariate time series instead the most common usage on images. The number of features are between 90 and 120, depending on which I need to consider and experiment. This is my code

scaler = StandardScaler()
X_train_s = scaler.fit_transform(X_train)
X_test_s = scaler.transform(X_test)

X_train_s = X_train_s.reshape((X_train_s.shape[0], X_train_s.shape[1],1))
X_test_s = X_test_s.reshape((X_test_s.shape[0], X_test_s.shape[1],1))

batch_size = 1024
length = 120
n_features = X_train_s.shape[1]

generator = TimeseriesGenerator(X_train_s, pd.DataFrame.to_numpy(Y_train[['TARGET_KEEP_LONG', 
                                                                          'TARGET_KEEP_SHORT']]), 
                                                                 length=length, 
                                                                 batch_size=batch_size)

validation_generator = TimeseriesGenerator(X_test_s, pd.DataFrame.to_numpy(Y_test[['TARGET_KEEP_LONG', 'TARGET_KEEP_SHORT']]), length=length, batch_size=batch_size)


early_stop = EarlyStopping(monitor = 'val_accuracy', mode = 'max', verbose = 1, patience = 20)

CNN_model = Sequential()
   
model.add(
    Conv2D(
        filters=64,
        kernel_size=(1, 5),
        strides=1,
        activation="relu",
        padding="valid",
        input_shape=(length, n_features, 1),
        use_bias=True,
    )
)
model.add(MaxPooling2D(pool_size=(1, 2)))
model.add(
    Conv2D(
        filters=64,
        kernel_size=(1, 5),
        strides=1,
        activation="relu",
        padding="valid",
        use_bias=True,
    )
)
model.add(MaxPooling2D(pool_size=(1, 2)))


CNN_model.add(MaxPooling1D(pool_size=2))
CNN_model.add(Flatten())
CNN_model.add(Dense(units=119, activation="relu", ))
CNN_model.add(Dropout(0.65))
CNN_model.add(Dense(units=36, activation="relu", ))
CNN_model.add(Dropout(0.65))
CNN_model.add(Dense(units=2, activation="softmax", ))

CNN_model.summary()

CNN_model.compile(
    optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"]
)

CNN_model.fit_generator(
    generator, steps_per_epoch=1, 
    validation_data=validation_generator,
    epochs=200,
)

In other words, I take the features as one dimension and a certain number of rows as the other dimension. But I get this error

ValueError: Input 0 of layer "conv2d_5" is incompatible with the layer: expected min_ndim=4, found ndim=2. Full shape received: (None, 2)

that is referred to the first CNN layer as stated here

Cell In [26], line 50
     25 CNN_model = Sequential()
     27 # CNN_model.add(
     28 #     Conv1D(
     29 #         filters=128,
   (...)
     47 #     )
     48 # )
---> 50 model.add(
     51     Conv2D(
     52         filters=64,
     53         kernel_size=(1, 5),
     54         strides=1,
     55         activation="relu",
     56         padding="valid",
     57         input_shape=(batch_size, length, n_features, 1),
     58         use_bias=True,
     59     )
     60 )
     61 model.add(MaxPooling2D(pool_size=(1, 2)))
     62 model.add(
     63     Conv2D(
     64         filters=64,
$\endgroup$
2
  • $\begingroup$ How model is initialized? $\endgroup$ Dec 6, 2022 at 15:12
  • 1
    $\begingroup$ Based on the final code block in your question the expected input shape to the model is: input_shape=(batch_size, length, n_features, 1). When you pass data into the model, it should have 4 dimensions (batch dimension, length dimension, feature dimension, and padded dimension of 1). Your generator seems to produce data with 2 dimensions. To know how to fix this, we would have to see the generator code, but my guess is your generator only produces a single sample at a time (missing batch dimension) and does not add the padded dimension. $\endgroup$ Dec 7, 2022 at 14:45

1 Answer 1

0
$\begingroup$

After days of attempts and looking to post that gave some indirect insights, I found the trouble and I can share the solution for

  • using 2DCNN models with time series and not images
  • avoiding memory troubles for preparing the dataset using TimeseriesGenerator

As expected the trouble was in preparing the dataset with the proper shape. The main bug in my code was this

X_train_s = X_train_s.reshape((X_train_s.shape[0], X_train_s.shape[1],1))
X_test_s = X_test_s.reshape((X_test_s.shape[0], X_test_s.shape[1],1))

that should be replaced with this (I also changed the names of the series, but just to keep the original one untouched)

X_train_s_CNN = X_train_s.reshape(*X_train_s.shape, 1)
X_test_s_CNN = X_test_s.reshape(*X_test_s.shape, 1)

Here is the full working code

from tensorflow.keras.layers import Conv1D, MaxPooling1D, Dense, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.layers import BatchNormalization

scaler = StandardScaler()
X_train_s = scaler.fit_transform(X_train)
X_test_s = scaler.transform(X_test)

X_train_s_CNN = X_train_s.reshape(*X_train_s.shape, 1)
X_test_s_CNN = X_test_s.reshape(*X_test_s.shape, 1)


batch_size = 64
length = 300
n_features = X_train_s.shape[1]

generator = TimeseriesGenerator(X_train_s_CNN, pd.DataFrame.to_numpy(Y_train[['TARGET_KEEP_LONG', 
                                                                          'TARGET_KEEP_SHORT']]), 
                                                                    length=length, 
                                                                    batch_size=batch_size)

validation_generator = TimeseriesGenerator(X_test_s, pd.DataFrame.to_numpy(Y_test[['TARGET_KEEP_LONG', 
                                                                                   'TARGET_KEEP_SHORT']]), 
                                                                           length=length, 
                                                                           batch_size=batch_size)


early_stop = EarlyStopping(monitor = 'val_accuracy', mode = 'max', verbose = 1, patience = 10)

CNN_model = Sequential()


CNN_model.add(
    Conv2D(
        filters=64,
        kernel_size=(2,2),
        strides=1,
        activation="relu",
        padding="same",
        input_shape=(length, n_features, 1),
        use_bias=True,
    )
)
CNN_model.add(BatchNormalization())
CNN_model.add(MaxPooling2D(pool_size=(2, 2)))
#CNN_model.add(Dropout(0.2))

CNN_model.add(
    Conv2D(
        filters=128,
        kernel_size=(2,2),
        strides=1,
        activation="relu",
        padding="same"
    )
)
CNN_model.add(BatchNormalization())
CNN_model.add(MaxPooling2D(pool_size=(2, 2)))
#CNN_model.add(Dropout(0.3))

# CNN_model.add(
#    Conv2D(
#        filters=256,
#        kernel_size=(2,2),
#        strides=1,
#        activation="relu",
#        padding="same"
#    )
# )
# CNN_model.add(
#    Conv2D(
#        filters=256,
#        kernel_size=(2,2),
#        strides=1,
#        activation="relu",
#        padding="same"
#    )
# )
# CNN_model.add(BatchNormalization())
# CNN_model.add(MaxPooling2D(pool_size=(2, 2)))
# CNN_model.add(Dropout(0.3))


CNN_model.add(Flatten())
# CNN_model.add(Dense(units=4096, activation="relu", ))
# CNN_model.add(BatchNormalization())
# #CNN_model.add(Dropout(0.5))
# CNN_model.add(Dense(units=128, activation="relu", ))
# CNN_model.add(BatchNormalization())
# # CNN_model.add(Dropout(0.5))
CNN_model.add(Dense(units=2, activation="softmax", ))


CNN_model.compile(
    optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"]
)



CNN_model.fit(
    generator, steps_per_epoch=1, 
    validation_data=validation_generator,
    epochs=200,
)

In the remarked parts the variants that I have tested. Regretfully, in this specific case, the results are very unstable in terms of accuracy and val_accuracy. The most disturbing is the accuracy of having really erratic behavior. Not clear why.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.