Styjun

Why is the Grievance Studies affair considered to be research requiring IRB approval?

What to do about my 1-month-old boy peeing through diapers?

How do Barton (Hawkeye/Ronin) and Romanov (Black Widow) end up on the Benatar on Morag in 2014?

Number of Fingers for a Math Oriented Race

Another "Ask One Question" Question

Which polygons can be turned inside out by a smooth deformation?

Spicing up a moment of peace

Why can't you say don't instead of won't?

Is there a way to tell what frequency I need a PWM to be?

What checks exist against overuse of presidential pardons in the USA?

Why does a sticker slowly peel off, but if it is pulled quickly it tears?

Defending Castle from Zombies

Is this position a forced win for Black after move 14?

Fantasy Macro Economics: What would Merfolk trade for?

Is it unusual for a math department not to have a mail/web server?

Why Can't A Name Be Written Literally In Japanese?

Why did Lucius make a deal out of Buckbeak hurting Draco but not about Draco being turned into a ferret?

Why did Starhopper's exhaust plume become brighter just before landing?

In how many ways we can distribute 7 distinct balls among 3 students such that everyone gets at least 2 balls?

Count the number of triangles

Are sweatpants frowned upon on flights?

Stolen MacBook should I worry about my data?

Find feasible point in polynomial time in linear programming

Did ancient peoples ever hide their treasure behind puzzles?

Keras LSTM input ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4

Understanding Keras LSTMsHow to change batch size of an intermediate layer in Keras?Keras LSTM ValueError: Input 0 is incompatible with layer lstm_24: expected ndim=3, found ndim=4Keras LSTM input incompatible with layer, expected ndim=3, found ndim=4Keras AttributeError: 'list' object has no attribute 'ndim'How to use Scikit Learn Wrapper around Keras Bi-directional LSTM ModelLSTM Nerual Network Input/Output dimensions errorIs it possible to train a CNN starting at an intermediate layer (in general and in Keras)?AttributeError: 'Sequential' object has no attribute '_feed_input_names' in Keras Theano'Sequential' object has no attribute 'loss' - When I used GridSearchCV to tuning my Keras model

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

1

1

When I run my code I get this error:
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4

def keras_experiment(true_examples,true_labels):
 # print len(true_examples[1])
 x_train = np.array(true_examples[:700])
 y_train = np.array(true_labels[:700])
 x_test = np.array(true_examples[700:])
 y_test = np.array(true_labels[700:])

 from keras.models import Sequential
 from keras.layers import LSTM, Dense
 print x_train[0]
 data_dim = 378
 timesteps = 7
 num_classes = 2

 # expected input data shape: (batch_size, timesteps, data_dim)
 model = Sequential()
 model.add(LSTM(32, return_sequences=False,
 input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
 model.add(Dense(10, activation='softmax'))

 model.compile(loss='categorical_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

 model.fit(x_train[0], y_train[0],
 batch_size=64, epochs=5,
 validation_data=(x_test, y_test))

 score = model.evaluate(x_test, y_test, batch_size=16)
 print score

Here is the result of print x_train[0]:

[[0.82183125 0.45548045 0.86122581 ... 3.16044199 1.43419966 0.45379718]
 [0.84371381 0.47813553 0.83602898 ... 2.64684385 1.58629507 0.5993157 ]
 [0.72253171 0.42504681 0.88999478 ... 2.09510967 1.87146875 0.89325575]
 ...
 [0.79126543 0.45734966 0.85694022 ... 2.68172079 1.54250728 0.57519309]
 [0.79846062 0.41452213 0.72903777 ... 2.492895 1.53964412 0.6176129 ]
 [0.8246961 0.39966809 0.52778689 ... 2.02451504 1.42316496 0.70296586]]

So it looks like what I think it should, a list of 700 examples, which are lists of 7 timesteps, which are lists of 378 features

python input keras lstm

share|improve this question

edited Mar 28 at 19:17

Ethan Hartzell

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Hello and welcome to Stack Overflow. What is your question exactly? Please take a moment to review the following how-to resources: How to Ask and Complete Examples
  
  – Pedro Rodrigues
  Mar 27 at 21:22
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  I think it's pretty clearly stated: running the function gets the following error -- ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4 but I don't understand why. Can anyone help me understand the error?
  
  – Ethan Hartzell
  Mar 28 at 13:56
  
  

  
  
  
  

add a comment | 

1

1

When I run my code I get this error:
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4

def keras_experiment(true_examples,true_labels):
 # print len(true_examples[1])
 x_train = np.array(true_examples[:700])
 y_train = np.array(true_labels[:700])
 x_test = np.array(true_examples[700:])
 y_test = np.array(true_labels[700:])

 from keras.models import Sequential
 from keras.layers import LSTM, Dense
 print x_train[0]
 data_dim = 378
 timesteps = 7
 num_classes = 2

 # expected input data shape: (batch_size, timesteps, data_dim)
 model = Sequential()
 model.add(LSTM(32, return_sequences=False,
 input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
 model.add(Dense(10, activation='softmax'))

 model.compile(loss='categorical_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

 model.fit(x_train[0], y_train[0],
 batch_size=64, epochs=5,
 validation_data=(x_test, y_test))

 score = model.evaluate(x_test, y_test, batch_size=16)
 print score

Here is the result of print x_train[0]:

[[0.82183125 0.45548045 0.86122581 ... 3.16044199 1.43419966 0.45379718]
 [0.84371381 0.47813553 0.83602898 ... 2.64684385 1.58629507 0.5993157 ]
 [0.72253171 0.42504681 0.88999478 ... 2.09510967 1.87146875 0.89325575]
 ...
 [0.79126543 0.45734966 0.85694022 ... 2.68172079 1.54250728 0.57519309]
 [0.79846062 0.41452213 0.72903777 ... 2.492895 1.53964412 0.6176129 ]
 [0.8246961 0.39966809 0.52778689 ... 2.02451504 1.42316496 0.70296586]]

So it looks like what I think it should, a list of 700 examples, which are lists of 7 timesteps, which are lists of 378 features

python input keras lstm

share|improve this question

edited Mar 28 at 19:17

Ethan Hartzell

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Hello and welcome to Stack Overflow. What is your question exactly? Please take a moment to review the following how-to resources: How to Ask and Complete Examples
  
  – Pedro Rodrigues
  Mar 27 at 21:22
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  I think it's pretty clearly stated: running the function gets the following error -- ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4 but I don't understand why. Can anyone help me understand the error?
  
  – Ethan Hartzell
  Mar 28 at 13:56
  
  

  
  
  
  

add a comment | 

When I run my code I get this error:
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4

def keras_experiment(true_examples,true_labels):
 # print len(true_examples[1])
 x_train = np.array(true_examples[:700])
 y_train = np.array(true_labels[:700])
 x_test = np.array(true_examples[700:])
 y_test = np.array(true_labels[700:])

 from keras.models import Sequential
 from keras.layers import LSTM, Dense
 print x_train[0]
 data_dim = 378
 timesteps = 7
 num_classes = 2

 # expected input data shape: (batch_size, timesteps, data_dim)
 model = Sequential()
 model.add(LSTM(32, return_sequences=False,
 input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
 model.add(Dense(10, activation='softmax'))

 model.compile(loss='categorical_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

 model.fit(x_train[0], y_train[0],
 batch_size=64, epochs=5,
 validation_data=(x_test, y_test))

 score = model.evaluate(x_test, y_test, batch_size=16)
 print score

Here is the result of print x_train[0]:

[[0.82183125 0.45548045 0.86122581 ... 3.16044199 1.43419966 0.45379718]
 [0.84371381 0.47813553 0.83602898 ... 2.64684385 1.58629507 0.5993157 ]
 [0.72253171 0.42504681 0.88999478 ... 2.09510967 1.87146875 0.89325575]
 ...
 [0.79126543 0.45734966 0.85694022 ... 2.68172079 1.54250728 0.57519309]
 [0.79846062 0.41452213 0.72903777 ... 2.492895 1.53964412 0.6176129 ]
 [0.8246961 0.39966809 0.52778689 ... 2.02451504 1.42316496 0.70296586]]

So it looks like what I think it should, a list of 700 examples, which are lists of 7 timesteps, which are lists of 378 features

python input keras lstm

share|improve this question

edited Mar 28 at 19:17

Ethan Hartzell

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges

def keras_experiment(true_examples,true_labels):
 # print len(true_examples[1])
 x_train = np.array(true_examples[:700])
 y_train = np.array(true_labels[:700])
 x_test = np.array(true_examples[700:])
 y_test = np.array(true_labels[700:])

 from keras.models import Sequential
 from keras.layers import LSTM, Dense
 print x_train[0]
 data_dim = 378
 timesteps = 7
 num_classes = 2

 # expected input data shape: (batch_size, timesteps, data_dim)
 model = Sequential()
 model.add(LSTM(32, return_sequences=False,
 input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
 model.add(Dense(10, activation='softmax'))

 model.compile(loss='categorical_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

 model.fit(x_train[0], y_train[0],
 batch_size=64, epochs=5,
 validation_data=(x_test, y_test))

 score = model.evaluate(x_test, y_test, batch_size=16)
 print score

[[0.82183125 0.45548045 0.86122581 ... 3.16044199 1.43419966 0.45379718]
 [0.84371381 0.47813553 0.83602898 ... 2.64684385 1.58629507 0.5993157 ]
 [0.72253171 0.42504681 0.88999478 ... 2.09510967 1.87146875 0.89325575]
 ...
 [0.79126543 0.45734966 0.85694022 ... 2.68172079 1.54250728 0.57519309]
 [0.79846062 0.41452213 0.72903777 ... 2.492895 1.53964412 0.6176129 ]
 [0.8246961 0.39966809 0.52778689 ... 2.02451504 1.42316496 0.70296586]]

share|improve this question

edited Mar 28 at 19:17

Ethan Hartzell

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges

share|improve this question

edited Mar 28 at 19:17

Ethan Hartzell

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges

asked Mar 27 at 21:16

Ethan HartzellEthan Hartzell

622 bronze badges