Get activations while training about keract

[philipperemy]

@AtrCheema you mean with Dropout?

[philipperemy]

Please give more information thanks

[AtrCheema]

@philipperemy Thankyou for your response. I want to visualize the output of certain layer in ConvNet while it is being trained. Let's suppose if second last layer has 10 neurons and last layer has 1 neuron. I want to see 10 values from second last layer while the network is being trained.

[philipperemy]

@AtrCheema Can you show that on a code example? For example is it during fit()?

[AtrCheema]

@philipperemy Yes I want during fit. For example following code makes NN to learn add 2 time series. I want to get output of second last layer which has 2 nodes

`
#https://machinelearningmastery.com/how-to-develop-convolutional-neural-network-models-for-time- series-forecasting/

#multivariate data preparation
#multivariate multiple input cnn example
from numpy import array
from numpy import hstack


from 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)`

[philipperemy]

At every batch, every epoch, every what? @AtrCheema

[AtrCheema]

@philipperemy At every time a 'sample' is evaluated and corresponding loss is calculated. I suppose this requires some modification in fit method of class Model in training.py but I am unable to figure out how.

[philipperemy]

@AtrCheema https://keras.io/callbacks/
This is what you need: on_batch_end.