为什么我的CNN回归网络无法学习？

Question

I am running a Convolutional Neural Network of regressive type. This network takes a 55x1756 image and outputs another image of dimensions 11x1756. For this reason the last layer of my architecture (shown below) consists of a dense layer which has as argument the output dimensions multiplied together.

As shown below, I am using "tanh" activation function and "adam" as optimizer. I have been training the network for some time now but the result is pretty much always the same. The loss remains steady as well as the root mean squared error, in addition to the fact that the validation loss is lower than the training loss which is not ideal. Attached below are both the training schematics and the model summary.

Do you have any suggestion on how I could improve it? Thanks in advance!

def generator(data_arr, batch_size = 10):

    num = len(data_arr) 
    num = int(num/batch_size)

    # Loop forever so the generator never terminates
    while True: 

        for offset in range(0, num):

            batch_samples = (data_arr[offset*batch_size:(offset+1)*batch_size])

            samples = []
            labels = []

            for batch_sample in batch_samples:

                samples.append(batch_sample[0])
                labels.append((np.array(batch_sample[1].flatten())).transpose())

            X_ = np.array(samples)
            Y_ = np.array(labels)

            X_ = X_[:, :, :, newaxis]

            yield (X_, Y_)

    # compile and train the model using the generator function
    train_generator = generator(training_data, batch_size = 10)
    validation_generator = generator(val_data, batch_size = 10)

    model = Sequential()

    model.add(Conv2D(4, (2, 2), input_shape = (55, 1756, 1)))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size = (3, 3)))
    model.add(BatchNormalization())

    model.add(Conv2D(8, (2, 2)))
    model.add(Activation('tanh'))
    model.add(MaxPooling2D(pool_size = (3, 3)))
    model.add(BatchNormalization())

    model.add(Conv2D(16, (2, 2)))
    model.add(Activation('tanh'))
    model.add(MaxPooling2D(pool_size = (3, 3)))
    model.add(BatchNormalization())

    model.add(Flatten()) 
    model.add(Dense(19316))
    model.add(Activation('softmax'))

    def nrmse(y_true, y_pred):
        return backend.sqrt(backend.mean(backend.square(y_pred - 
            y_true)))/(2)

    def rmse(y_true, y_pred):
        return backend.sqrt(backend.mean(backend.square(y_pred - y_true)))

    model.compile(loss = 'mean_squared_error',
                  optimizer = 'adam',
                  metrics = [rmse, nrmse, 'mae'])

    model.summary()

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 27, 878, 4)        20        
_________________________________________________________________
activation_1 (Activation)    (None, 27, 878, 4)        0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 9, 292, 4)         0         
_________________________________________________________________
batch_normalization_1 (Batch (None, 9, 292, 4)         16        
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 8, 291, 8)         136       
_________________________________________________________________
activation_2 (Activation)    (None, 8, 291, 8)         0         
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 2, 97, 8)          0         
_________________________________________________________________
batch_normalization_2 (Batch (None, 2, 97, 8)          32        
_________________________________________________________________
flatten_1 (Flatten)          (None, 1552)              0         
_________________________________________________________________
dense_1 (Dense)              (None, 19316)             29997748  
_________________________________________________________________
activation_3 (Activation)    (None, 19316)             0

=================================================================
Total params: 29,997,952
Trainable params: 29,997,928
Non-trainable params: 24
_________________________________________________________________

Epoch 1/6
6660/6660 [==============================] - 425s 64ms/step - loss: 0.0135 - rmse: 0.0986 - nrmse: 0.0577 - mean_absolute_error: 0.0333 - val_loss: 0.0133 - val_rmse: 0.0971 - val_nrmse: 0.0572 - val_mean_absolute_error: 0.0327
Epoch 2/6
6660/6660 [==============================] - 422s 63ms/step - loss: 0.0135 - rmse: 0.0986 - nrmse: 0.0577 - mean_absolute_error: 0.0332 - val_loss: 0.0133 - val_rmse: 0.0971 - val_nrmse: 0.0572 - val_mean_absolute_error: 0.0327
Epoch 3/6
6660/6660 [==============================] - 422s 63ms/step - loss: 0.0135 - rmse: 0.0986 - nrmse: 0.0577 - mean_absolute_error: 0.0332 - val_loss: 0.0133 - val_rmse: 0.0971 - val_nrmse: 0.0572 - val_mean_absolute_error: 0.0327
Epoch 4/6
6660/6660 [==============================] - 422s 63ms/step - loss: 0.0135 - rmse: 0.0986 - nrmse: 0.0577 - mean_absolute_error: 0.0332 - val_loss: 0.0133 - val_rmse: 0.0971 - val_nrmse: 0.0572 - val_mean_absolute_error: 0.0327
Epoch 5/6
6660/6660 [==============================] - 422s 63ms/step - loss: 0.0135 - rmse: 0.0986 - nrmse: 0.0577 - mean_absolute_error: 0.0332 - val_loss: 0.0133 - val_rmse: 0.0971 - val_nrmse: 0.0572 - val_mean_absolute_error: 0.0327
Epoch 6/6
6660/6660 [==============================] - 421s 63ms/step - loss: 0.0135 - rmse: 0.0986 - nrmse: 0.0577 - mean_absolute_error: 0.0332 - val_loss: 0.0133 - val_rmse: 0.0971 - val_nrmse: 0.0572 - val_mean_absolute_error: 0.03274

Answer 1

It could be vanishing gradient problem which happens if you employ activation functions other than ReLu. Try changing functions to ReLu and then see whether it improves or not.