How to find the predicted output of a classification neural network in python?

Question

I a newbie to python and learning neural networks. I have a trained 3 layer feed forward neural network with 2 neurons in the hidden layer and 3 in the output layer. I am wondering that how to calculate the output layer values/ predicted output

I have weights and biases extracted from the network and activation values calculated of the hidden layer. I just want to confirm that how can I use softmax function to calculate the out put of the output layer neurons?

My implementation is as follows:

weights_from_hiddenLayer_to_OutputLayer = [
    [x, y],  # two weights connected to the output neuron 1 from hidden neurons 1 and 2
    [a, b],  # two weights connected to the output neuron 2 from hidden neurons 1 and 2
    [c, d]   # two weights connected to the output neuron 3 from hidden neurons 1 and 2I
    ]

# output layer biases extracted from the neural network
biases_output_layer = [a, b, c]

act1 = m  # activation value of hidden neuron 1
act2 = n  # activation value of hidden neuron 2
arr = []
for i, weights in enumerate(weights_from_hiddenLayer_to_OutputLayer):
            arr.append(m*weights[0]+n*weights[1] +
                       biases_output_layer[i])
# i believe this will be the brightest neuron / predicted neural networks output ?  
print(np.argmax(arr))

I have searched over the internet for using softmax in python and here I have reached. My predicted output is mostly different from what neural networks prediction. Whereas I am using exact same values from the same trained model.

Answer 1

Your output would be the matrix multiplication of weights_from_hiddenLayer_to_OutputLayer and the previous activations. You can then pass it through the softmax function to get a probability distribution and use argmax as you guessed to get the corresponding class.

weights_from_hiddenLayer_to_OutputLayer = np.array([
    [x, y],  # two weights connected to the output neuron 1 from hidden neurons 1 and 2
    [a, b],  # two weights connected to the output neuron 2 from hidden neurons 1 and 2
    [c, d]   # two weights connected to the output neuron 3 from hidden neurons 1 and 2I
    ])

act = np.array([m, n])
biases_output_layer = [a, b, c]
arr = np.dot(weights_from_hiddenLayer_to_OutputLayer, act)    # matrix multiplication of weights and activations
arr = arr + biases_output_layer
     
probability = np.exp(arr) / np.sum(np.exp(arr), axis=0)       # softmax
print(np.argmax(probability))

Note that you technically don't need to use softmax unless you are back-propagating or trying to assess the confidence of the output as the result of np.argmax() will be the same regardless of whether you pass in arr or the corresponding probability.