10

I'm trying to apply Conv1D layers for a classification model which has a numeric dataset. The neural network of my model is as follows:

model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv1D(8,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu',input_shape = (14999,7)))
model.add(tf.keras.layers.Conv1D(16,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.MaxPooling1D(2))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Conv1D(32,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.Conv1D(64,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.MaxPooling1D(2))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Conv1D(128,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.Conv1D(256,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.MaxPooling1D(2))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(512,activation = 'relu'))
model.add(tf.keras.layers.Dense(128,activation = 'relu'))
model.add(tf.keras.layers.Dense(32,activation = 'relu'))
model.add(tf.keras.layers.Dense(3, activation = 'softmax'))

And the model's input shape is (14999, 7).

model.summary() gives the following output

Model: "sequential_8"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d_24 (Conv1D)           (None, 14997, 8)          176       
_________________________________________________________________
conv1d_25 (Conv1D)           (None, 14995, 16)         400       
_________________________________________________________________
max_pooling1d_10 (MaxPooling (None, 7497, 16)          0         
_________________________________________________________________
dropout_9 (Dropout)          (None, 7497, 16)          0         
_________________________________________________________________
conv1d_26 (Conv1D)           (None, 7495, 32)          1568      
_________________________________________________________________
conv1d_27 (Conv1D)           (None, 7493, 64)          6208      
_________________________________________________________________
max_pooling1d_11 (MaxPooling (None, 3746, 64)          0         
_________________________________________________________________
dropout_10 (Dropout)         (None, 3746, 64)          0         
_________________________________________________________________
conv1d_28 (Conv1D)           (None, 3744, 128)         24704     
_________________________________________________________________
conv1d_29 (Conv1D)           (None, 3742, 256)         98560     
_________________________________________________________________
max_pooling1d_12 (MaxPooling (None, 1871, 256)         0         
_________________________________________________________________
dropout_11 (Dropout)         (None, 1871, 256)         0         
_________________________________________________________________
flatten_3 (Flatten)          (None, 478976)            0         
_________________________________________________________________
dense_14 (Dense)             (None, 512)               245236224 
_________________________________________________________________
dense_15 (Dense)             (None, 128)               65664     
_________________________________________________________________
dense_16 (Dense)             (None, 32)                4128      
_________________________________________________________________
dense_17 (Dense)             (None, 3)                 99        
=================================================================
Total params: 245,437,731
Trainable params: 245,437,731
Non-trainable params: 0

The code for model fitting is:

model.compile(loss = 'sparse_categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
history = model.fit(xtrain_scaled, ytrain_scaled, epochs = 30, batch_size = 5, validation_data = (xval_scaled, yval_scaled))

While executing, I'm facing the following error:

ValueError: Input 0 is incompatible with layer model: expected shape=(None, 14999, 7), found shape=(None, 7)

Could anyone help to sort out this issue?

Hagbard
  • 3,430
  • 5
  • 28
  • 64
MOULISHANKAR
  • 111
  • 1
  • 1
  • 6

1 Answers1

6

TL;DR:

Change

model.add(tf.keras.layers.Conv1D(8,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu',input_shape = (14999,7)))

to

model.add(tf.keras.layers.Conv1D(8,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu',input_shape = (7)))

Full answer:

Assumption: I am guessing the reason you chose to write 14999 in the input shape is because that's your batch size / total size of training data

Problem with this:

  • Tensorflow assumes the input shape does not include the batch size
    • By specifying a 2D input_shape you're making Tensorflow expect a 3D input of shape (Batch_size, 14999, 7). But your input is clearly of size (Batch_size, 7)

Solution:

Change the shape from (14999, 7) to just (7)

  • TF will now be expecting the same shape that you are providing

PS: Don't be worried about informing your model of how many training examples you have in the dataset. TF Keras works with the assumption it can be shown unlimited training examples.

rishabhjha
  • 96
  • 2