如何制作单个向量/数组？

Question

Consider the following cnn model

def create_model():
  x_1=tf.Variable(24)
  bias_initializer = tf.keras.initializers.HeNormal()
  model = Sequential()
  model.add(Conv2D(32, (5, 5),  input_shape=(28,28,1),activation="relu", name='conv2d_1', use_bias=True,bias_initializer=bias_initializer))
  model.add(MaxPooling2D(pool_size=(2, 2)))
  model.add(Conv2D(64, (5, 5), activation="relu",name='conv2d_2',  use_bias=True,bias_initializer=bias_initializer))
  model.add(MaxPooling2D(pool_size=(2, 2)))
  model.add(Flatten())
  model.add(Dense(320, name='dense_1',activation="relu", use_bias=True,bias_initializer=bias_initializer),)
  model.add(Dense(10, name='dense_2', activation="softmax", use_bias=True,bias_initializer=bias_initializer),)
  return model

I create a model_1=create_model() instance of the above model. Now consider the following

combine_weights=[]
for layer in model.layers:
  if 'conv' in layer.name or 'fc' in layer.name:
    print(layer)
    we=layer.weights
    combine_weights.append(we)

From model_1 , the above code takes the weights of convolutional layers/fc layers and combine them in a single array of combine_weight . The dtype of combine_weight is attained through print(type(combine_weights)) giving the type <class 'list'>

Now, I try to reshape all these weights to result in a single row vector/1-d array by using the following combine_weights_reshape=tf.reshape(tf.stack(combine_weights,[-1])) which gives the following error

<ipython-input-80-dee21fe38c89> in <module>
----> 1 combine_weights_reshape=tf.reshape(tf.stack(combine_weights,[-1]))

1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name)
   7184 def raise_from_not_ok_status(e, name):
   7185   e.message += (" name: " + name if name is not None else "")
-> 7186   raise core._status_to_exception(e) from None  # pylint: disable=protected-access
   7187 
   7188 

InvalidArgumentError: Shapes of all inputs must match: values[0].shape = [5,5,1,32] != values[1].shape = [32] [Op:Pack] name: stack

How can I reshape the combine_weight into a single row vector/array?

Answer 1

I got the desired result with the following

combine_weights=[]
con=[]
for layer in model.layers:
  if 'conv' in layer.name or 'fc' in layer.name:
    print(layer.name)
    we=layer.weights[0]
    we_reshape=tf.reshape(we,[-1])
    # bi=layer.weights[1]
    combine_weights.append(we_reshape)
    print(combine_weights)
    print(len(combine_weights))
    con=tf.concat([con,we_reshape], axis=[0])
    print(con)

Answer 2

One solution is to flatten the weight tensor before appending it to the list of weights. The original problem was that the weight tensors had different shapes, so tf.stack would not work.

combine_weights = []
for layer in model.layers:
    if "conv" in layer.name or "fc" in layer.name:
        print(layer)
        # Flatten the weights tensor.
        we = tf.reshape(layer.weights, shape=-1)
        combine_weights.append(we)
# Concatenate all of the (flat) weight vectors.
combine_weights = tf.concat(combine_weights, axis=0)