How to get output from a layer during training in Keras?

Click For Summary

Discussion Overview

The discussion revolves around obtaining the output from a hidden layer during the training process of a neural network using Keras. Participants explore the challenges of accessing these outputs in real-time as samples are evaluated and losses are calculated.

Discussion Character

  • Exploratory, Technical explanation, Debate/contested

Main Points Raised

  • One participant asks how to retrieve the output of the last hidden layer during training using the model.fit() method in Keras.
  • Another participant suggests that existing resources provide methods to obtain outputs after training, but not during the training process itself.
  • Some participants propose that modifications to the training process may be necessary, including potentially altering the Keras source code.
  • One participant expresses uncertainty about how to implement a solution, indicating they are new to Keras.
  • There are repeated requests for implementation examples to demonstrate how to manipulate training to achieve the desired output retrieval.
  • Another participant suggests that manipulating training by processing one element at a time might be a possible approach.
  • One participant humorously notes that the task is left to the student, implying that finding a solution is part of the learning process.

Areas of Agreement / Disagreement

Participants do not reach a consensus on how to obtain the outputs during training, and multiple competing views and uncertainties remain regarding the best approach to achieve this.

Contextual Notes

Some participants express a lack of familiarity with Keras, which may limit their ability to provide concrete solutions. There is also mention of potential modifications to the Keras source code, indicating a complexity in the task that may not be straightforward.

Atr cheema
Messages
67
Reaction score
0
In Keras, the method model.fit() is used to train the neural network. How can I get the output from any hidden layer during training? Consider following code where neural network is trained to add two time series
Python: 
#multivariate data preparation
#multivariate multiple input cnn example
from numpy import array
from numpy import hstackfrom tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense
from tensorflow.python.keras.layers import Flatten
from tensorflow.python.keras.layers.convolutional import Conv1D
from tensorflow.python.keras.layers.convolutional import MaxPooling1D#split a multivariate sequence into samples
def split_sequences(sequences, n_steps):
    X, y = list(), list()
    for i in range(len(sequences)):
        # find the end of this pattern
        end_ix = i + n_steps
        # check if we are beyond the dataset
        if end_ix > len(sequences):
            break
        # gather input and output parts of the pattern
        seq_x, seq_y = sequences[i:end_ix, :-1], sequences[end_ix-1, -1]
        X.append(seq_x)
        y.append(seq_y)
    return array(X), array(y)

#define input sequence
dataset_len = 100
is1 = array([i*10+10 for i in range(dataset_len)])
is2 = array([i*10+15 for i in range(dataset_len)])

out_seq = array([is1[i]+is2[i]
                for i in range(len(is1))])
#convert to [rows, columns] structure
is1 = is1.reshape((len(is1), 1))
is2 = is2.reshape((len(is2), 1))

out_seq = out_seq.reshape((len(out_seq), 1))
#horizontally stack columns
dataset = hstack((is1, is2,
                  #is3,is4,is5,is6,is7,is8,is9,
                  out_seq))
#print('raw input data is : \n{}\n'.format(dataset[0:7]))

#choose a number of time steps
n_steps = 3
#convert into input/output
X, y = split_sequences(dataset, n_steps)

#print('given \n{} we want to predict {}\n'.format(X[0], y[0]))

#model input must have shape [samples, timesteps, features]

#the dataset knows the number of features, e.g. 2
n_features = X.shape[2]
#define model
model = Sequential()
conv1d = Conv1D(filters=64, kernel_size=2, activation='relu', input_shape=(n_steps, n_features))
model.add(conv1d)
mp1d = MaxPooling1D(pool_size=2)
model.add(mp1d)
fl = Flatten()
model.add(fl)
model.add(Dense(50, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(2, activation='relu'))
model.add(Dense(1))

#print('\nCompiling model\n')

model.compile(optimizer='adam', loss='mse')
#plot_model(model, to_file='multivariate_laos.png', show_shapes=True,)

#fit model
model.fit(X, y, epochs=1000, batch_size=None, verbose=0, shuffle=False, steps_per_epoch=None)##demonstrate prediction
x_input = array([[80, 85], [90, 95], [100, 105]])
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
print(yhat)`

I the above code, how can I get output of last hidden layer which is in this case dense layer, but I want the output during training of neural network. This means I want output every time a 'sample' is evaluated and its corresponding loss function is calculated.
 
Technology news on Phys.org
Borg said:
Maybe this will help?
https://stackoverflow.com/questions/41711190/keras-how-to-get-the-output-of-each-layer
All the answers in that post provide the way to get output once the training is finished but I want the output during the training process simultaneously. This might require some modification in model.fit method in training.py file but I am unable to find a solution so far. Can you tell me which line in Keras source code actually runs the tensorflow session during execution of model.fit() method. .
 
I don't know - I'm pretty new at Keras as well. I know that it's mainly a wrapper around Tensorflow to make life easier but, if you want something else, you may have to build your model without it. Maybe @jedishrfu knows a way.
 
The only thing i can think of is to manipulate your training using one element at a time.
 
jedishrfu said:
The only thing i can think of is to manipulate your training using one element at a time.
Can you implement this for this example code? Thanks.
 
Atr cheema said:
Can you implement this for this example code? Thanks.

Nope, the task is left to the student. :-)
 
Atr cheema said:
In Keras, the method model.fit() is used to train the neural network. How can I get the output from any hidden layer during training? Consider following code where neural network is trained to add two time series
Python: 
#multivariate data preparation
#multivariate multiple input cnn example
from numpy import array
from numpy import hstackfrom tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense
from tensorflow.python.keras.layers import Flatten
from tensorflow.python.keras.layers.convolutional import Conv1D
from tensorflow.python.keras.layers.convolutional import MaxPooling1D#split a multivariate sequence into samples
def split_sequences(sequences, n_steps):
    X, y = list(), list()
    for i in range(len(sequences)):
        # find the end of this pattern
        end_ix = i + n_steps
        # check if we are beyond the dataset
        if end_ix > len(sequences):
            break
        # gather input and output parts of the pattern
        seq_x, seq_y = sequences[i:end_ix, :-1], sequences[end_ix-1, -1]
        X.append(seq_x)
        y.append(seq_y)
    return array(X), array(y)

#define input sequence
dataset_len = 100
is1 = array([i*10+10 for i in range(dataset_len)])
is2 = array([i*10+15 for i in range(dataset_len)])

out_seq = array([is1[i]+is2[i]
                for i in range(len(is1))])
#convert to [rows, columns] structure
is1 = is1.reshape((len(is1), 1))
is2 = is2.reshape((len(is2), 1))

out_seq = out_seq.reshape((len(out_seq), 1))
#horizontally stack columns
dataset = hstack((is1, is2,
                  #is3,is4,is5,is6,is7,is8,is9,
                  out_seq))
#print('raw input data is : \n{}\n'.format(dataset[0:7]))

#choose a number of time steps
n_steps = 3
#convert into input/output
X, y = split_sequences(dataset, n_steps)

#print('given \n{} we want to predict {}\n'.format(X[0], y[0]))

#model input must have shape [samples, timesteps, features]

#the dataset knows the number of features, e.g. 2
n_features = X.shape[2]
#define model
model = Sequential()
conv1d = Conv1D(filters=64, kernel_size=2, activation='relu', input_shape=(n_steps, n_features))
model.add(conv1d)
mp1d = MaxPooling1D(pool_size=2)
model.add(mp1d)
fl = Flatten()
model.add(fl)
model.add(Dense(50, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(2, activation='relu'))
model.add(Dense(1))

#print('\nCompiling model\n')

model.compile(optimizer='adam', loss='mse')
#plot_model(model, to_file='multivariate_laos.png', show_shapes=True,)

#fit model
model.fit(X, y, epochs=1000, batch_size=None, verbose=0, shuffle=False, steps_per_epoch=None)##demonstrate prediction
x_input = array([[80, 85], [90, 95], [100, 105]])
x_input = x_input.reshape((1, n_steps, n_features))
yhat = model.predict(x_input, verbose=0)
print(yhat)`

I the above code, how can I get output of last hidden layer which is in this case dense layer, but I want the output during training of neural network. This means I want output every time a 'sample' is evaluated and its corresponding loss function is calculated.
Hi Atr cheema,
I have the same problem, did you find a solution for your question?