I am experimenting with the use of multi-input to a double CNN.
However, I am getting the Graph disconnected: cannot obtain value for tensor Tensor("embedding_1_input:0", shape=(?, 40), dtype=float32) at layer "embedding_1_input". The following previous layers were accessed without issue: []
I didn't find a fix for it, knowing that there are layers with shape = (?, 50) why is there such dimension "?" ????
from keras.models import Model
from keras.layers import Input, Dot
from keras.layers.core import Reshape
from keras.backend import int_shape
max_words=50
thedata = [' '.join(list(x)) for x in self.input_data]
emb_size = 15
tokenizer = Tokenizer(num_words=max_words)
tokenizer.fit_on_texts(thedata)
self.dictionary = tokenizer.word_index
vocab_size = len(tokenizer.word_index) + 1
vocab_size = 5000
allWordIndices = []
for text in thedata:
wordIndices = self.convert_text_to_index_array(text)
allWordIndices.append(wordIndices)
allWordIndices = np.asarray(allWordIndices)
train_x = tokenizer.sequences_to_matrix(allWordIndices, mode='binary')
train_y = list(map(lambda x: self.c[x], self.output_data))
X_train, X_test, Y_train, Y_test = train_test_split(train_x, train_y, test_size = 0.1, shuffle=True)
vocab_size1 = 50000
input_size = 40
input_shape = (input_size, 1)
# first model
L_branch = Sequential()
L_branch.add(Embedding(vocab_size1, emb_size, input_length=max_words, trainable=True))
L_branch.add(Conv1D(50, activation='relu', kernel_size=10, input_shape=input_shape))
L_branch.add(MaxPooling1D(emb_size))
L_branch.add(Flatten())
L_branch.add(Dense(emb_size, activation='sigmoid'))
# second model
R_branch = Sequential()
R_branch.add(Embedding(vocab_size, output_dim=emb_size, input_length=max_words, trainable=True))
R_branch.add(Dense(emb_size, activation='sigmoid'))
input_in1 = Input(shape=(input_size, 1, 1))
input_in2 = Input(shape=(input_size, 1, 1))
merged = Dot(axes=(1, 2))([L_branch.outputs[0], R_branch.outputs[0]])
print(merged.shape)
#
merged = Reshape((-1, int_shape(merged)[1],))(merged)
latent = Conv1D(50, activation='relu', kernel_size=self.nb_classes, input_shape=(1, input_size, 1))(merged)
latent = MaxPooling1D(self.nb_classes)(latent)
out = Dense(self.nb_classes, activation='sigmoid')(latent)
final_model = Model([input_in2, input_in1], out)
final_model.compile(
loss='mse',
optimizer='adam',
metrics=['accuracy'])
final_model.summary()
final_model.fit(
[X_train, train_x],
Y_train,
batch_size=200,
epochs=5,
verbose=1
# validation_split=0.1
)
I tried adding flatten layer after the second embedding but I got an error. Even with a dropout.
I also tried eliminating the maxpooling from the L_branch model.
Tried not working with the reshape and just expand the input dims since I was getting an error of the second Conv1D saying the layer expects dims = 3 but it was getting dims = 2.
latent = Conv1D(50, activation='relu', kernel_size=nb_classes, input_shape=(1, input_size, 1))(merged)
File "/root/anaconda3/envs/oea/lib/python3.7/site-packages/keras/engine/base_layer.py", line 414, in __call__
self.assert_input_compatibility(inputs)
File "/root/anaconda3/envs/oea/lib/python3.7/site-packages/keras/engine/base_layer.py", line 311, in assert_input_compatibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer conv1d_2: expected ndim=3, found ndim=2`
I also didn't get which input is used in the first model and which input is used in the second?
you have to define your new model in this way: final_model = Model([L_branch.input, R_branch.input], out)
I provide an example of network with a structure similar to yours
vocab_size1 = 5000
vocab_size2 = 50000
input_size1 = 40
input_size2 = 40
max_words=50
emb_size = 15
nb_classes = 10
# first model
L_branch = Sequential()
L_branch.add(Embedding(vocab_size1, emb_size, input_length=input_size1, trainable=True))
L_branch.add(Conv1D(50, activation='relu', kernel_size=10))
L_branch.add(MaxPooling1D())
L_branch.add(Flatten())
L_branch.add(Dense(emb_size, activation='relu'))
# second model
R_branch = Sequential()
R_branch.add(Embedding(vocab_size2, emb_size, input_length=input_size2, trainable=True))
R_branch.add(Flatten())
R_branch.add(Dense(emb_size, activation='relu'))
merged = Concatenate()([L_branch.output, R_branch.output])
latent = Dense(50, activation='relu')(merged)
out = Dense(nb_classes, activation='softmax')(latent)
final_model = Model([L_branch.input, R_branch.input], out)
final_model.compile(
loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
final_model.summary()
X1 = np.random.randint(0,vocab_size1, (100,input_size1))
X2 = np.random.randint(0,vocab_size2, (100,input_size2))
y = np.random.randint(0,nb_classes, 100)
final_model.fit([X1,X2], y, epochs=10)
Related
I am working on a project where I need to segregate the sleep data and its labels.
But I am stuck with the error mentioned above.
As I am new to the machine learning side I would be highly grateful if someone can help me out with how can I resolve this issue.
I have implemented a model using the following code:
EEG_training_data = EEG_training_data.reshape(EEG_training_data.shape[0], EEG_training_data.shape[1],1)
print(EEG_training_data.shape)# (5360, 5000, 1)
EEG_validation_data = EEG_validation_data.reshape(EEG_validation_data.shape[0], EEG_validation_data.shape[1],1)
print(EEG_validation_data.shape)#(1396, 5000, 1)
label_class = (np.unique(EEG_training_label))
num_classes = label_class.size # num_classes = 5
#define the model using CNN
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(filters=64, kernel_size= 16, activation='relu', batch_input_shape=(None,5000, 1))) # #input_shape=(5000, 1)
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.MaxPool1D(8, padding='same'))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Dense(num_classes, activation='softmax'))
#Summary of the model defined:
model.summary()
#Define loss function
model.compile(
loss= 'categorical_crossentropy', # 'sparse_categorical_crossentropy',
optimizer='adam',
metrics=[tf.keras.metrics.FalseNegatives(), tf.keras.metrics.FalsePositives(), 'accuracy'])
#one Hot Encoding
y_train_hot = tf.keras.utils.to_categorical(EEG_training_label, num_classes)
print('New y_train shape: ', y_train_hot.shape)#(5360, 5)
y_valid_hot = tf.keras.utils.to_categorical(EEG_validation_label, num_classes)
print('New y_valid shape: ', y_valid_hot.shape)#(1396, 5)
# apply fit on data
model_history = model.fit(
x=EEG_training_data,
y=y_train_hot,
batch_size=32,
epochs=5,
validation_data=(EEG_validation_data, y_valid_hot),
)
model_prediction = model.predict(EEG_testing_data)
predicted_matrix = tf.math.confusion_matrix(labels=EEG_testing_label.argmax(axis=1), predictions=model_prediction.argmax(axis=1)).numpy()
print(predicted_matrix)
I'm not experiencing your issue with the code you have provided. Try executing the following code, that should work as expected. If that is the case, double check that the shapes of all your data, i.e. EEG_training_data etc. are like the ones below:
import tensorflow as tf
import numpy as np
EEG_training_data = np.ones((5360, 5000, 1))
EEG_validation_data = np.ones((1396, 5000, 1))
EEG_training_label = np.random.randint(5, size=5360)
EEG_validation_label = np.random.randint(5, size=1396)
label_class = (np.unique(EEG_training_label))
num_classes = label_class.size
print(num_classes) # prints 5
#define the model using CNN
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(filters=64, kernel_size= 16, activation='relu', batch_input_shape=(None, 5000, 1))) # input_shape=(5000, 1)
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.MaxPool1D(8, padding='same'))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Dense(num_classes, activation='softmax'))
#Summary of the model defined:
model.summary()
#Define loss function
model.compile(loss = 'categorical_crossentropy',
optimizer='adam',
metrics=[tf.keras.metrics.FalseNegatives(), tf.keras.metrics.FalsePositives(), 'accuracy'])
#one Hot Encoding
y_train_hot = tf.keras.utils.to_categorical(EEG_training_label, num_classes)
print('New y_train shape: ', y_train_hot.shape) #(5360, 5)
y_valid_hot = tf.keras.utils.to_categorical(EEG_validation_label, num_classes)
print('New y_valid shape: ', y_valid_hot.shape) #(1396, 5)
# apply fit on data
model_history = model.fit(x=EEG_training_data,
y=y_train_hot,
batch_size=32,
epochs=5,
validation_data=(EEG_validation_data, y_valid_hot),
)
model_prediction = model.predict(EEG_validation_data)
predicted_matrix = tf.math.confusion_matrix(labels=EEG_validation_label.argmax(axis=1), predictions=model_prediction.argmax(axis=1)).numpy()
print(predicted_matrix)
I'm looking into examples for time series with Keras and found some good examples for cases where the target is one data point, e.e. in the below code:
import numpy as np
import pandas as pd
import datetime as dt
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM
## data
x_train = np.random.random((100, 10))
x_train = np.reshape(x_train,(100,10,1))
y_train = np.random.random((100, 1))
###training
model = Sequential()
x_shape = 10
y_shape = 1
y_units = 1
model.add(LSTM(units=50, return_sequences=True, input_shape=(x_shape,y_shape)))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50))
model.add(Dropout(0.2))
model.add(Dense(units=y_units)) #Prediction of the next closing price
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(x_train, y_train, epochs=25, batch_size=32)
## inference
model.predict(x_train).shape
(100, 1)
My question is, which should be the data shapes and NN to predict two values, at first glance what makes sense to me is to have:
x_train = np.random.random((100, 10))
x_train = np.reshape(x_train,(100,10,1))
y_train = np.random.random((100, 2))
y_train = np.reshape(y_train,(100,2) )
model = Sequential()
x_shape = 10
y_shape = 2
y_units = 2
model.add(LSTM(units=50, return_sequences=True, input_shape=(x_shape,y_shape)))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50))
model.add(Dropout(0.2))
model.add(Dense(units=y_units)) #Prediction of the next closing price
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(x_train, y_train, epochs=25, batch_size=32)
But then I get the error:
ValueError: Input 0 is incompatible with layer sequential_25: expected shape=(None, None, 2), found shape=(None, 10, 1)
What it has worked is in that same code to change:
y_shape = 1
then I get the rigth output shape, but I dont understand why the shape of y is set to one if it is a two dimentions array
Input data must be with two units also
x_train = tf.random.uniform(shape=(100, 10, 2))
I am trying to create a LSTM/GRU model in keras to categorise given articles in one of the 4 classes.
input > embedding layer > LSTM/GRU layer > [context vector] > Dense(softmax activation) > output class
In the training input data there are 39978 articles each article has 20 sentences and each sentence has 20 words. As for the target variable there are 4 target classes.
x_train.shape is (39978, 20, 20) and
y_train.shape is (39978, 4)
embedding_matrix.shape is (27873, 100) embedding_matrix is created on vocabulary with glove.6B.100d.txt
I am trying to create a sequential model like below
vocab_size = len(tokenizer.word_index.keys()) # 27873
MAX_SENT_LENGTH = 20
model = Sequential()
embedding_dimentations = embedding_matrix.shape[1]
e = Embedding(vocab_size,
embedding_dimentations,
weights=[embedding_matrix],
input_length=MAX_SENT_LENGTH,
trainable=False)
model.add(e)
model.add(Bidirectional(GRU(embedding_dimentations, dropout=0.25, recurrent_dropout=0.25)))
model.add(Dense(4, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
on above model if i do a fit
batch_size = 128
epochs = 3
print('Training.....')
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
validation_split=.2)
I am getting following error
ValueError: Error when checking input: expected embedding_6_input to have 2 dimensions, but got array with shape (39978, 20, 20)
I tried specifying input shape tuple in Embedding() but its not working. Can someone point me in right direction?
Thanks
vocab_size = len(tokenizer.word_index.keys()) # 27873
MAX_SENT_LENGTH = 20
embedding_dimentations = embedding_matrix.shape[1]
model = Sequential()
encoder_inputs = Input(shape=(20, 20))
x1 = Reshape((400,))(encoder_inputs)
x2 = Embedding(vocab_size,
embedding_dimentations,
weights=[embedding_matrix],
input_length=400,
trainable=False)(x1)
# should use Bidirectional GRU
encoder = GRU(embedding_dimentations, dropout=0.25, recurrent_dropout=0.25, return_state=True)
encoder_outputs, state_h = encoder(x2)
predictions = Dense(4, activation='softmax')(encoder_outputs)
model = Model(inputs=encoder_inputs, outputs=predictions)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
Used Reshape layer before the Embedding layer to get the data into correct shape. This approach is working for me.
I'm pretty new to Keras and LSTMs. I've been trying to train my model of sequences to predict the future price of a stock with the code below but the error above kept popping up.
I have tried changing the dtypes of both x_data, y_data with .astype(np.float16). However, all times I am returned with the TypeError stating that I have a float32 type.
If it helps, here are the shapes of my data:
xtrain.shape : (32, 24, 67), ytrain.shape : (32, 24, 1), xtest.shape
: (38, 67), ytest.shape : (38, 1)
Does anyone have any idea on what might be wrong? I've been stuck at this for awhile. It would be great if someone could give me a hint.
y_data = y_data.to_numpy().astype(np.float32)
x_data = main_df.to_numpy().astype(np.float32)
num_x_signals = x_data.shape[1]
num_y_signals = y_data.shape[1]
# SPLIT TRAIN TEST DATA
ratio = 0.85
train_ratio = int(ratio * len(x_data))
x_train = x_data[0:train_ratio]
x_test = x_data[train_ratio:]
y_train = y_data[0:train_ratio]
y_test = y_data[train_ratio:]
# GENERATE RANDOM SEQUENCES
batch_size = 32
sequence_length = 24
EPOCHS = 50
def batch_generator(x_train, y_train, batch_size, sequence_length, num_x_signals, num_y_signals, num_train):
while True:
x_shape = (batch_size, sequence_length, num_x_signals)
x_batch = np.zeros(shape = x_shape).astype(np.float32)
y_shape = (batch_size, sequence_length, num_y_signals)
y_batch = np.zeros(shape = y_shape).astype(np.float32)
for i in range(batch_size):
idx = np.random.randint(num_train - sequence_length)
x_batch[i] = x_train[idx:idx+sequence_length]
y_batch[i] = y_train[idx:idx+sequence_length]
yield (x_batch, y_batch)
generator = batch_generator(x_train, y_train, batch_size, sequence_length, num_x_signals, num_y_signals, train_ratio)
xtrain, ytrain = next(generator)
xtest, ytest = (np.expand_dims(x_test, axis=0),
np.expand_dims(y_test, axis=0))
# LSTM MODEL
model = Sequential()
model.add(LSTM(32, input_shape = (None, num_x_signals,), return_sequences = True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences = True))
model.add(Dropout(0.15))
model.add(BatchNormalization())
model.add(LSTM(128))
model.add(Dropout(0.18))
model.add(BatchNormalization())
model.add(Dense(32, activation = 'relu'))
model.add(Dropout(0.2))
model.add(Dense(1, activation = 'softmax'))
opt = tf.keras.optimizers.Adam(lr = 0.001, decay = 1e-6)
model.compile(
loss = 'sparse_categorical_crossentropy',
optimizer = opt,
metrics = ['accuracy']
)
name_of_file = f"{to_predict}-{sequence_length}-{future_predict}-{int(time.time())}"
tensorboard = TensorBoard(log_dir = "logs/{}".format(name_of_file))
filepath = "LSTM_Final-{epoch:02d}-{val_acc:.3f}"
checkpoint = ModelCheckpoint("models/{}.model".format(filepath, monitor = 'val_acc', verbose = 1, save_best_only = True, mode = 'max')) # saves only the best ones
history = model.fit(
xtrain, ytrain,
epochs = EPOCHS,
validation_data = (xtest, ytest),
callbacks = [tensorboard, checkpoint]
)
score = model.evaluate(xtest, ytest, verbose = 0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model.save("models/{}".format(name_of_file))
I found this issue had to do with the loss function specified.
My code:
import tensorflow as tf
from tensorflow import keras
model = tf.keras.Sequential([
keras.layers.Dense(64, activation=tf.nn.relu, input_shape=[3]),
keras.layers.Dense(64, activation=tf.nn.relu),
keras.layers.Dense(1)
])
#I changed the loss function from 'sparse_categorical_crossentropy' to 'mean_squared error'
model.compile(optimizer='adam',loss='mean_squared_error',metrics=['accuracy'])
X = train_dataset.to_numpy()
y = train_labels.to_numpy()
model.fit(X,y, epochs=5)
X shape was (920,3) and dtype = float64
y shape was (920,1) and dtype = float64
My problem was in the model.fit method. I took the 'sparse_categorical_crossentropy' function from an image recognition example and what I was trying here is a neural network for house prices prediction.
I am trying to implement a system by encoding inputs using CNN. After CNN, I need to get a vector and use it in another deep learning method.
def get_input_representation(self):
# get word vectors from embedding
inputs = tf.nn.embedding_lookup(self.embeddings, self.input_placeholder)
sequence_length = inputs.shape[1] # 56
vocabulary_size = 160 # 18765
embedding_dim = 256
filter_sizes = [3,4,5]
num_filters = 3
drop = 0.5
epochs = 10
batch_size = 30
# this returns a tensor
print("Creating Model...")
inputs = Input(shape=(sequence_length,), dtype='int32')
embedding = Embedding(input_dim=vocabulary_size, output_dim=embedding_dim, input_length=sequence_length)(inputs)
reshape = Reshape((sequence_length,embedding_dim,1))(embedding)
conv_0 = Conv2D(num_filters, kernel_size=(filter_sizes[0], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
conv_1 = Conv2D(num_filters, kernel_size=(filter_sizes[1], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
conv_2 = Conv2D(num_filters, kernel_size=(filter_sizes[2], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
maxpool_0 = MaxPool2D(pool_size=(sequence_length - filter_sizes[0] + 1, 1), strides=(1,1), padding='valid')(conv_0)
maxpool_1 = MaxPool2D(pool_size=(sequence_length - filter_sizes[1] + 1, 1), strides=(1,1), padding='valid')(conv_1)
maxpool_2 = MaxPool2D(pool_size=(sequence_length - filter_sizes[2] + 1, 1), strides=(1,1), padding='valid')(conv_2)
concatenated_tensor = Concatenate(axis=1)([maxpool_0, maxpool_1, maxpool_2])
flatten = Flatten()(concatenated_tensor)
dropout = Dropout(drop)(flatten)
output = Dense(units=2, activation='softmax')(dropout)
model = Model(inputs=inputs, outputs=output)
adam = Adam(lr=1e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])
adam = Adam(lr=1e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])
print("Traning Model...")
model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, callbacks=[checkpoint], validation_data=(X_test, y_test)) # starts training
return ??
The above code, trains the model using X_train and Y_train and then tests it. However in my system I do not have Y_train or Y_test, I only need the vector in the last hidden layer before softmax layer. How can I obtain it?
For that you can define a backend function to get the output of arbitrary layer(s):
from keras import backend as K
func = K.function([model.input], [model.layers[index_of_layer].output])
You can find the index of your desired layer using model.summary() where the layers are listed starting from index zero. If you need the layer before the last layer you can use -2 as the index (i.e. .layers attribute is actually a list so you can index it like a list in python). Then you can use the function you have defined by passing a list of input array(s):
outputs = func(inputs)
Alternatively, you can also define a model for this purpose. This has been covered in Keras documentation more thoroughly so I advise you to read that.