I am working on customizing a layer to use in my model. The core part is the "call" function as,
class Custom_Layer(Layer):
// some code
def call(self, inputs, **kwargs):
kernel = mul(self.base, self.diag_start - self.diag_end)
outputs = matmul(a=inputs, b=kernel)
if self.use_bias:
outputs = tf.nn.bias_add(outputs, self.bias)
if self.activation is not None:
outputs = self.activation(outputs)
return outputs
// some code
and it is used in a simple model.
inputs = tf.keras.layers.Input(shape=(784,),dtype='float32')
layer1 = Custom_layer(2000, **Custom_layer_config, activation='tanh')(inputs)
layer2 = Custom_layer(200, **Custom_layer_config, activation='tanh')(layer1)
output_lay = Custom_layer(10, **Custom_layer_config, activation='softmax')(layer2)
model = tf.keras.models.Model(inputs=inputs, outputs=output_lay)
opt = tf.keras.optimizers.Adamax(learning_rate=0.02)
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.summary()
It is supposed to print like this:
Model: "functional_13"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_8 (InputLayer) [(None, 784)] 0
_________________________________________________________________
CustomLayer_18 (Custom_Layer) (None, 2000) 1570784
_________________________________________________________________
CustomLayer_19 (Custom_Layer) (None, 200) 402200
_________________________________________________________________
CustomLayer_20 (Custom_Layer) (None, 10) 2210
=================================================================
Total params: 1,975,194
Trainable params: 5,194
Non-trainable params: 1,970,000
_________________________________________________________________
But prints this:
Model: "model_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) [(None, 784)] 0
tf.linalg.matmul_3 (TFOpLam (None, 2000) 0
bda)
tf.math.tanh_2 (TFOpLambda) (None, 2000) 0
tf.linalg.matmul_4 (TFOpLam (None, 200) 0
bda)
tf.math.tanh_3 (TFOpLambda) (None, 200) 0
tf.linalg.matmul_5 (TFOpLam (None, 10) 0
bda)
tf.compat.v1.nn.softmax_1 ( (None, 10) 0
TFOpLambda)
=================================================================
Total params: 0
Trainable params: 0
Non-trainable params: 0
The first summary is what I got from author's repository and the second summary is from my run of the same code without changing anything..
The code is not a complex one but it is weird why there is no parameters at all. My question is that what is wrong here.
Try to make it as an inherited class from this example.
Sample: Custom LSTM class
import tensorflow as tf
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Class / Definition
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
class MyLSTMLayer( tf.keras.layers.LSTM ):
def __init__(self, units, return_sequences, return_state):
super(MyLSTMLayer, self).__init__( units, return_sequences=True, return_state=False )
self.num_units = units
def build(self, input_shape):
self.kernel = self.add_weight("kernel",
shape=[int(input_shape[-1]),
self.num_units])
def call(self, inputs):
return tf.matmul(inputs, self.kernel)
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
start = 3
limit = 12
delta = 3
sample = tf.range( start, limit, delta )
sample = tf.cast( sample, dtype=tf.float32 )
sample = tf.constant( sample, shape=( 1, 1, 3 ) )
layer = MyLSTMLayer( 3, True, False )
model = tf.keras.Sequential([
tf.keras.Input(shape=(1, 3)),
layer,
])
model.summary()
print( sample )
print( model.predict(sample) )
Output:
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
my_lstm_layer (MyLSTMLayer) (None, 1, 3) 9
=================================================================
Total params: 9
Trainable params: 9
Non-trainable params: 0
_________________________________________________________________
tf.Tensor([[[3. 6. 9.]]], shape=(1, 1, 3), dtype=float32)
1/1 [==============================] - 1s 575ms/step
[[[-2.8894916 -2.146874 13.688236 ]]]