stale[bot]
commented
7 years ago This issue has been automatically marked as stale because it has not had recent activity. It will be closed after 30 days if no further activity occurs, but feel free to re-open a closed issue if needed.
my network is given below
case 1 42 features
model = Sequential() model.add(LSTM(4,input_dim=42)) # try using a GRU instead, for fun model.add(Dropout(0.1)) model.add(Dense(5)) model.add(Activation('softmax'))
Visualizing the average activation values of the input features for 10 samples of class 0
def get_activations(model, layer, X_batch): get_activations = K.function([model.layers[0].input, K.learning_phase()], model.layers[layer].output) activations = get_activations([X_batch,0]) return activations my_featuremaps = get_activations(model, 0, ([X_train[:5], 0])[0]) print(my_featuremaps)
activation values [[ 0.762 -0.122 0.044 -0.758] [ 0.762 -0.122 0.044 -0.758] [ 0.762 -0.122 0.044 -0.758] [ 0.762 -0.038 0.043 -0.752] [ 0.762 -0.038 0.043 -0.752] [ 0.762 -0.038 0.043 -0.752] [ 0.125 -0. 0.038 -0.083] [ 0.762 -0.121 0.044 -0.758] [ 0.762 -0.038 0.043 -0.752] [ 0.762 -0.433 0.091 -0.755]]
case 2 12 features
giveing the below output
[[ 0.62 -0.122 0.044 -0.58] [ 0.62 -0.122 0.044 -0.58] [ 0.62 -0.122 0.044 -0.58] [ 0.62 -0.038 0.043 -0.52] [ 0.62 -0.038 0.043 -0.52] [ 0.62 -0.038 0.043 -0.52] [ 0.225 -0. 0.038 -0.093] [ 0.62 -0.121 0.044 -0.58] [ 0.62 -0.038 0.043 -0.52] [ 0.62 -0.433 0.091 -0.55]]
case 2 8 features
[[ 0.62 -0.22 0.44 -0.58] [ 0.62 -0.22 0.44 -0.58] [ 0.62 -0.22 0.44 -0.58] [ 0.62 -0.38 0.43 -0.52] [ 0.62 -0.38 0.43 -0.52] [ 0.62 -0.38 0.43 -0.52] [ 0.225 -0. 0.38 -0.093] [ 0.62 -0.21 0.44 -0.58] [ 0.62 -0.38 0.43 -0.52] [ 0.62 -0.33 0.91 -0.55]]
Could anybody tell how to plot average of the values in a plot (like described in https://www.sec.in.tum.de/assets/Uploads/ConvolutionalNetworks.pdf) Fig 3
Empowering Convolutional Networks for Malware Classification and Analysis