We Keep Coding

AssertionError: with Keras Functional API

The code I'm trying to run to create a Neural Network model to predict some damping ratio and added mass coefficient. I have 3 inputs of the model (float numbers) and 4 outputs of the model (float numbers).
import numpy as np
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.optimizers import SGD
from keras.models import Model
from keras.layers import Input
from keras.layers import Dense
from keras.layers import Concatenate
from sklearn.model_selection import train_test_split
from Reasearch_project_Code import *
"""Create model"""
Input1 = Input(shape=(1),name="Input1")
Input2 = Input(shape=(1),name="Input2")
Input3 = Input(shape=(1),name="Input3")
Inputs = Concatenate(axis=-1,name="Inputs")([Input1,Input2,Input3])
hidden1 = Dense(100, activation='relu',name="Hidden1")(Inputs)
hidden2 = Dense(100, activation='relu',name="Hidden2")(hidden1)
# Output layer
output1 = Dense(1, activation='linear',name="Output_1")(hidden2)
output2 = Dense(1, activation='linear',name="Output_2")(hidden2)
output3 = Dense(1, activation='linear',name="Output_3")(hidden2)
output4 = Dense(1, activation='linear',name="Output_4")(hidden2)
# output
model = Model(inputs=[Input1,Input2,Input3], outputs=[output1, output2, output3, output4])
# summarize layers
print(model.summary())
opt = SGD(0.001)
model.compile(loss='mean_squared_error', optimizer=opt)
"""Load Data"""
dpath="C:\\Users\\jules\\OneDrive - University of Southampton\\Documents\\Research Project\\5- Codes"
R=RP(dpath)
data="Data/Test3/Test3.csv"
labelss=np.genfromtxt(data,skip_header=1,usecols=(1,2,3),delimiter=",")
sampless=np.genfromtxt(data,skip_header=1,usecols=(4,5,6,7),delimiter=",")
"""scaled data"""
scaler=MinMaxScaler(feature_range=(0,1))
samples = scaler.fit_transform(sampless)
labels = scaler.fit_transform(labelss)
"""split data"""
labels_train, labels_test, samples_train , samples_test= train_test_split(labels,samples,train_size=0.9,random_state=42)
print(f"labels_train:{labels_train.shape}")
print(f"labels_test:{labels_test.shape}")
print(f"samples_train:{samples_train.shape}")
print(f"samples_test:{samples_test.shape}")
history = model.fit(labels_train, samples_train, validation_data=(labels_test, samples_test), epochs=200,batch_size=20, verbose=1)
shape of the data:
labels_train:(6753, 3)
labels_test:(751, 3)
samples_train:(6753, 4)
samples_test:(751, 4)
model:
Model: "functional_115"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
Input1 (InputLayer) [(None, 1)] 0
__________________________________________________________________________________________________
Input2 (InputLayer) [(None, 1)] 0
__________________________________________________________________________________________________
Input3 (InputLayer) [(None, 1)] 0
__________________________________________________________________________________________________
Inputs (Concatenate) (None, 3) 0 Input1[0][0]
Input2[0][0]
Input3[0][0]
__________________________________________________________________________________________________
Hidden1 (Dense) (None, 100) 400 Inputs[0][0]
__________________________________________________________________________________________________
Hidden2 (Dense) (None, 100) 10100 Hidden1[0][0]
__________________________________________________________________________________________________
Output_1 (Dense) (None, 1) 101 Hidden2[0][0]
__________________________________________________________________________________________________
Output_2 (Dense) (None, 1) 101 Hidden2[0][0]
__________________________________________________________________________________________________
Output_3 (Dense) (None, 1) 101 Hidden2[0][0]
__________________________________________________________________________________________________
Output_4 (Dense) (None, 1) 101 Hidden2[0][0]
==================================================================================================
Total params: 10,904
Trainable params: 10,904
Non-trainable params: 0
__________________________________________________________________________________________________
Assertions error:
AssertionError: in user code:
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function *
return step_function(self, iterator)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step **
outputs = model.train_step(data)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:747 train_step
y_pred = self(x, training=True)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:985 __call__
outputs = call_fn(inputs, *args, **kwargs)
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:385 call
return self._run_internal_graph(
C:\Users\jules\anaconda3\lib\site-packages\tensorflow\python\keras\engine\functional.py:517 _run_internal_graph
assert x_id in tensor_dict, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("Output_1/BiasAdd_57:0", shape=(None, 1), dtype=float32)
I'm a beginner and I don't understand where the error come from because my inputs and outputs seems to hae the correct dimensions.
Previously, instead of using 3 inputs layers, I used one with a shape of 3:
Inputs = Input(shape=(3,),name="Inputs")
But this gave me terrible predictions (negative R2)

Trying to build Encoder Decoder with Attention Mechanism, but graph results always disconnected, pls could you help me?

dimensionality = 4
#trainint encoder
encoder_inputs = Input(shape=(None, num_encoder_tokens))
decoder_inputs = Input(shape=(None, num_decoder_tokens))
encoder = Bidirectional(LSTM(dimensionality, return_sequences=True, return_state=True,
go_backwards=True), merge_mode='sum')
encoder_outputs, for_h, for_c, bac_h, bac_c = encoder(encoder_inputs)
encoder_states = [tf.add(for_h, for_c), tf.add(bac_h, bac_h) ]
#training decoder
decoder = LSTM(dimensionality, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder(decoder_inputs, initial_state= encoder_states)
dot_prod = dot([decoder_outputs, encoder_outputs], axes=[2, 2])
attention = Activation('softmax', name='attention')
attention_vec = attention(dot_prod)
context = dot([attention_vec, encoder_outputs], axes=[2, 1])
decoder_comb = concatenate([context, decoder_outputs], name='decoder_comb')
dense = Dense(num_decoder_tokens, activation='softmax')
output = dense(decoder_comb)
training_model = Model([encoder_inputs, decoder_inputs], output)
Here you can find summary:
Model: "functional_12"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_13 (InputLayer) [(None, None, 1780)] 0
__________________________________________________________________________________________________
bidirectional_2 (Bidirectional) [(None, None, 4), (N 57120 input_13[0][0]
__________________________________________________________________________________________________
input_14 (InputLayer) [(None, None, 2257)] 0
__________________________________________________________________________________________________
tf_op_layer_Add_4 (TensorFlowOp [(None, 4)] 0 bidirectional_2[0][1]
bidirectional_2[0][2]
__________________________________________________________________________________________________
tf_op_layer_Add_5 (TensorFlowOp [(None, 4)] 0 bidirectional_2[0][3]
bidirectional_2[0][3]
__________________________________________________________________________________________________
lstm_5 (LSTM) [(None, None, 4), (N 36192 input_14[0][0]
tf_op_layer_Add_4[0][0]
tf_op_layer_Add_5[0][0]
__________________________________________________________________________________________________
dot_12 (Dot) (None, None, None) 0 lstm_5[0][0]
bidirectional_2[0][0]
__________________________________________________________________________________________________
attention (Activation) (None, None, None) 0 dot_12[0][0]
__________________________________________________________________________________________________
dot_13 (Dot) (None, None, 4) 0 attention[0][0]
bidirectional_2[0][0]
__________________________________________________________________________________________________
decoder_comb (Concatenate) (None, None, 8) 0 dot_13[0][0]
lstm_5[0][0]
__________________________________________________________________________________________________
dense_2 (Dense) (None, None, 2257) 20313 decoder_comb[0][0]
==================================================================================================
Total params: 113,625
Trainable params: 113,625
Non-trainable params: 0
__________________________________________________________________________________________________
And finally below I paste my attempt to separate encoder and decoder in order to do inference, but it raises an error. I tried to use training_model layers/output/input whenever I could but there is still something that I am missing.
#inference encoder
encoder_model = Model(encoder_inputs, encoder_states)
#inference decoder
decoder_s_h = Input(shape=(dimensionality, ))
decoder_s_c = Input(shape=(dimensionality, ))
decoder_states_inputs = [decoder_s_h, decoder_s_c]
decoder_outputs, state_h, state_c = decoder(decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
dot_prod = dot([decoder_outputs, encoder_outputs], axes=[2, 2])
attention_vec = attention(dot_prod)
context = dot([attention_vec, encoder_outputs], axes=[2, 1])
decoder_comb = concatenate([context, decoder_outputs])
output= dense(decoder_comb)
decoder_model = Model([decoder_inputs] + decoder_states_inputs, [output] + decoder_states)
I tried so many times to change this configuration but I can't resolve graph disconnection. Could you help me?
PS. I am new to NLP so pls be kind with me, I am a student still not a deep learning specialist...
Thank you so much for your time and help!
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-44-89f9761124cf> in <module>()
18 output= dense(decoder_comb)
19
---> 20 decoder_model = Model([decoder_inputs] + decoder_states_inputs, [output] + decoder_states)
21
22 #encoder decoder model
5 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in _map_graph_network(inputs, outputs)
929 'The following previous layers '
930 'were accessed without issue: ' +
--> 931 str(layers_with_complete_input))
932 for x in nest.flatten(node.outputs):
933 computable_tensors.add(id(x))
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_13:0", shape=(None, None, 1780), dtype=float32) at layer "bidirectional_2". The following previous layers were accessed without issue: ['lstm_5']

You can not use input, output properties when creating models with functional api.
Try to change by something like that:
encoder_inputs = Input(shape=(None, num_encoder_tokens))
decoder_inputs = Input(shape=(None, num_decoder_tokens))
encoder_outputs, for_hidden, for_cell, bac_hidden, bac_cell = training_model(encoder_input, decoder_inputs)
Another error relates to this line:
encoder_model = Model(encoder_inputs, encoder_states)
where encoder_states is not dependent from encoder_input. So tensorflow is not able to build graph.

How can I use tf.keras.Model.summary to see the layers of a child model which in a father model?

I have a subclass Model of tf.keras.Model,code is following
import tensorflow as tf
class Mymodel(tf.keras.Model):
def __init__(self, classes, backbone_model, *args, **kwargs):
super(Mymodel, self).__init__(self, args, kwargs)
self.backbone = backbone_model
self.classify_layer = tf.keras.layers.Dense(classes,activation='sigmoid')
def call(self, inputs):
x = self.backbone(inputs)
x = self.classify_layer(x)
return x
inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61,
backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
model.summary()
the result is :
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
mobilenet_1.00_224 (Model) (None, 1000) 4253864
_________________________________________________________________
dense (Dense) multiple 61061
=================================================================
Total params: 4,314,925
Trainable params: 4,293,037
Non-trainable params: 21,888
_________________________________________________________________
but I want to see the all layers of mobilenet,then I tried to extract all layers of mobilenet and put in the model:
import tensorflow as tf
class Mymodel(tf.keras.Model):
def __init__(self, classes, backbone_model, *args, **kwargs):
super(Mymodel, self).__init__(self, args, kwargs)
self.backbone = backbone_model
self.classify_layer = tf.keras.layers.Dense(classes,activation='sigmoid')
def my_process_layers(self,inputs):
layers = self.backbone.layers
tmp_x = inputs
for i in range(1,len(layers)):
tmp_x = layers[i](tmp_x)
return tmp_x
def call(self, inputs):
x = self.my_process_layers(inputs)
x = self.classify_layer(x)
return x
inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61,
backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
model.summary()
then the resule not changed.
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
mobilenet_1.00_224 (Model) (None, 1000) 4253864
_________________________________________________________________
dense (Dense) multiple 61061
=================================================================
Total params: 4,314,925
Trainable params: 4,293,037
Non-trainable params: 21,888
_________________________________________________________________
then I tried to extract one layer insert to the model :
import tensorflow as tf
class Mymodel(tf.keras.Model):
def __init__(self, classes, backbone_model, *args, **kwargs):
super(Mymodel, self).__init__(self, args, kwargs)
self.backbone = backbone_model
self.classify_layer = tf.keras.layers.Dense(classes,activation='sigmoid')
def call(self, inputs):
x = self.backbone.layers[1](inputs)
x = self.classify_layer(x)
return x
inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61,
backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
model.summary()
It did not change either.I am so confused.
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
mobilenet_1.00_224 (Model) (None, 1000) 4253864
_________________________________________________________________
dense (Dense) multiple 244
=================================================================
Total params: 4,254,108
Trainable params: 4,232,220
Non-trainable params: 21,888
_________________________________________________________________
but I find that the parameter of dense layer changed,I dont know what happend.

#Ioannis 's answer is perfectly fine, but unfortunately it drops the keras 'Model Subclassing' structure that is present in the question. If, just like me, you want to keep this model subclassing and still show all layers in the summary, you can branch down into all the individual layers of the more complex model using a for loop:
class MyMobileNet(tf.keras.Sequential):
def __init__(self, input_shape=(224, 224, 3), classes=61):
super(MyMobileNet, self).__init__()
self.backbone_model = [layer for layer in
tf.keras.applications.MobileNet(input_shape, include_top=False, pooling='avg').layers]
self.classificator = tf.keras.layers.Dense(classes,activation='sigmoid', name='classificator')
def call(self, inputs):
x = inputs
for layer in self.backbone_model:
x = layer(x)
x = self.classificator(x)
return x
model = MyMobileNet()
After this we can directly build the model and call the summary:
model.build(input_shape=(None, 224, 224, 3))
model.summary()
>
Model: "my_mobile_net"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1_pad (ZeroPadding2D) (None, 225, 225, 3) 0
_________________________________________________________________
conv1 (Conv2D) (None, 112, 112, 32) 864
_________________________________________________________________
conv1_bn (BatchNormalization (None, 112, 112, 32) 128
_________________________________________________________________
....
....
conv_pw_13 (Conv2D) (None, 7, 7, 1024) 1048576
_________________________________________________________________
conv_pw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
global_average_pooling2d_13 (None, 1024) 0
_________________________________________________________________
classificator (Dense) multiple 62525
=================================================================
Total params: 3,291,389
Trainable params: 3,269,501
Non-trainable params: 21,888
_________________________________________________________________

In order to be able to view backbone's layers, you' ll have to construct your new model using backbone.input and backbone.output
from tensorflow.keras.models import Model
def Mymodel(backbone_model, classes):
backbone = backbone_model
x = backbone.output
x = tf.keras.layers.Dense(classes,activation='sigmoid')(x)
model = Model(inputs=backbone.input, outputs=x)
return model
input_shape = (224, 224, 3)
model = Mymodel(backbone_model=tf.keras.applications.MobileNet(input_shape=input_shape, include_top=False, pooling='avg'),
classes=61)
model.summary()

There is an argument expand_nested in the Method summary.
model.summary(expand_nested=True)

for layer in model.layers:
layer.summary()

Keras - Error in stack Conv1D with Bidirectional LSTM

Hi I am trying to do a multi-class classification using embedding, and stack Conv1D with Bidirectional LSTM, Here is my script:
embed_dim = 100
lstm_out = 128
max_features = 5000
model8 = Sequential()
model8.add(Embedding(max_features, embed_dim, input_length = X.shape[1]))
model8.add(Dropout(0.2))
model8.add(Conv1D(filters=100, kernel_size=3, padding='same', activation='relu'))
model8.add(MaxPooling1D(pool_size=2))
model8.add(Bidirectional(LSTM(lstm_out)))
model8.add(Dense(124,activation='softmax'))
model8.compile(loss = 'categorical_crossentropy', optimizer='adam',metrics = ['accuracy'])
print model8.summary()
I got error message as below:
TypeErrorTraceback (most recent call last)
<ipython-input-51-6c831fc4581f> in <module>()
9 model8.add(Embedding(max_features, embed_dim))
10 model8.add(Dropout(0.2))
---> 11 model8.add(Conv1D(filters=100, kernel_size=3, padding='same', activation='relu'))
12 model8.add(MaxPooling1D(pool_size=2))
13 model8.add(Bidirectional(LSTM(lstm_out)))
/jupyter/local/lib/python2.7/site-packages/tensorflow/python/training/checkpointable/base.pyc in _method_wrapper(self, *args, **kwargs)
362 self._setattr_tracking = False # pylint: disable=protected-access
363 try:
--> 364 method(self, *args, **kwargs)
365 finally:
366 self._setattr_tracking = previous_value # pylint: disable=protected-access
/jupyter/local/lib/python2.7/site-packages/tensorflow/python/keras/engine/sequential.pyc in add(self, layer)
128 raise TypeError('The added layer must be '
129 'an instance of class Layer. '
--> 130 'Found: ' + str(layer))
131 self.built = False
132 if not self._layers:
TypeError: The added layer must be an instance of class Layer. Found: <keras.layers.convolutional.Conv1D object at 0x7f62907f8590>
What I did wrong? Thanks!

from keras.layers import Dense, Embedding, Dropout, LSTM
from keras.models import Sequential
from keras.layers import Bidirectional
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
embed_dim = 100
lstm_out = 128
max_features = 5000
model8 = Sequential()
model8.add(Embedding(max_features, embed_dim, input_length = X.shape[1]))
model8.add(Dropout(0.2))
model8.add(Conv1D(filters=100, kernel_size=3, padding='same', activation='relu'))
model8.add(MaxPooling1D(pool_size=2))
model8.add(Bidirectional(LSTM(lstm_out)))
model8.add(Dense(124,activation='softmax'))
model8.compile(loss = 'categorical_crossentropy', optimizer='adam',metrics =
['accuracy'])
print(model8.summary())
Prints the model summary without any error:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_8 (Embedding) (None, 100, 100) 500000
_________________________________________________________________
dropout_5 (Dropout) (None, 100, 100) 0
_________________________________________________________________
conv1d_3 (Conv1D) (None, 100, 100) 30100
_________________________________________________________________
max_pooling1d_3 (MaxPooling1 (None, 50, 100) 0
_________________________________________________________________
bidirectional_7 (Bidirection (None, 256) 234496
_________________________________________________________________
dense_7 (Dense) (None, 124) 31868
=================================================================
Total params: 796,464
Trainable params: 796,464
Non-trainable params: 0
_________________________________________________________________
None

Keras - functional and sequential model give different results

I implemented two models, one time using the sequential way and one time with the functional API. Now the both models give different results, which kind of makes no sense to me.
I cannot figure out, what the problem is. Any ideas or solutions?
Here both models:
Sequential Model:
model = Sequential()
embedding_layer = Embedding(VOCAB_SIZE +1, EMBEDDING_SIZE, mask_zero= True)
model.add(embedding_layer)
model.add(Bidirectional(LSTM(HIDDEN_SIZE, return_sequences= True))),
model.add(TimeDistributed(Dense(NUM_LABELS, activation='softmax')))
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(train_sents_padded, train_labels_padded, batch_size=4, epochs=10,
validation_data=(dev_sents_padded, dev_labels_padded))
score, acc = model.evaluate(dev_sents_padded, dev_labels_padded)
print("\nAccuracy: ", acc)
Functional Model:
inputs = Input(shape=(MAX_LENGTH,))
embedding = Embedding(VOCAB_SIZE +1, EMBEDDING_SIZE, mask_zero= True)(inputs)
left = LSTM(HIDDEN_SIZE, return_sequences=True)(embedding)
right = LSTM(HIDDEN_SIZE, go_backwards=True, return_sequences=True)
(embedding)
left_right = concatenate([left, right])
left_right = TimeDistributed(Dense(NUM_LABELS, activation='softmax'))
(left_right)
combined_model = Model(inputs=inputs, outputs=left_right)
combined_model.compile(loss='categorical_crossentropy', optimizer='adam',
metrics=['accuracy'])
combined_model.fit(
train_sents_padded,
train_labels_padded,
batch_size=4,
epochs=10,
validation_data=(dev_sents_padded, dev_labels_padded)
)
score, acc = combined_model.evaluate(dev_sents_padded, dev_labels_padded)
print("\nBidirectional LSTM Accuracy: ", acc)
+++
Summaries:
Sequential model:
Layer (type) Output Shape Param #
=================================================================
embedding_1 (Embedding) (None, None, 50) 26150
_________________________________________________________________
bidirectional_1 (Bidirection (None, None, 100) 40400
_________________________________________________________________
time_distributed_1 (TimeDist (None, None, 61) 6161
=================================================================
Total params: 72,711
Trainable params: 72,711
Non-trainable params: 0 `
Functional model:
Layer (type) Output Shape Param # Connected to
========================================================================
input_1 (InputLayer) (None, 34) 0
____________________________________________________________________
embedding_2 (Embedding) (None, 34, 50) 26150 input_1[0][0]
______________________________________________________________________
lstm_2 (LSTM) (None, 34, 50) 20200 embedding_2[0][0]
____________________________________________________________________
lstm_3 (LSTM) (None, 34, 50) 20200 embedding_2[0][0]
_________________________________________________________________
concatenate_1 (Concatenate)(None, 34, 100) 0 lstm_2[0][0]
lstm_3[0][0]
___________________________________________________________
time_distributed_2 (TimeDistrib (None, 34, 61) 6161 concatenate_1[0][0]
=====================================================================
Total params: 72,711
Trainable params: 72,711
Non-trainable params: 0`
+++
If I change VOCAB_SIZE + 1 to VOCAB_SIZE in the seqential model the acc is 59, but only on every third run??