pytorch Dropout: "channel will be zeroed out independently" - pytorch

In the pytorch doc it states: During training, randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution. Each channel will be zeroed out independently on every forward call.
What does it mean by "zero out independently on every forward call"? below is the pseudocode of my implementation, are they equivalent to pytorch version?
import numpy as np
p = 0.3
inpt = np.random.randn((2, 3, 3)) # input tensor
# forward, when training is true
mask = np.random.choice(a=[False, True], size=inpt.shape, p=[p, 1 - p])
output = inpt * mask / (1 - p) # output tensor
return output
# forward, when training is false
return inpt # does nothing
# backward propagation
inpt.grad += incoming_gradient * mask # apply the same mask on incoming gradient

You don't need to apply the mask on the gradient, activations are already masked, i.e. the gradient won't flow past the neurons that were masked in the forward pass. See source.

Related

using transforms.LinearTransformation to apply whitening in PyTorch

I need to apply ZCA whitening in PyTorch. I think I have found a way this can be done by using transforms.LinearTransformation and I have found a test in the PyTorch repo which gives some insight into how this is done (see final code block or link below)
https://github.com/pytorch/vision/blob/master/test/test_transforms.py
I am struggling to work out how I apply something like this myself.
Currently I have transforms along the lines of:
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(np.array([125.3, 123.0, 113.9]) / 255.0,
np.array([63.0, 62.1, 66.7]) / 255.0),
])
The documents say they way to use LinearTransformation is as follows:
torchvision.transforms.LinearTransformation(transformation_matrix, mean_vector)
whitening transformation: Suppose X is a column vector zero-centered
data. Then compute the data covariance matrix [D x D] with
torch.mm(X.t(), X), perform SVD on this matrix and pass it as
transformation_matrix.
I can see from the tests I linked above and copied below that they are using torch.mm to calculate what they call a principal_components:
def test_linear_transformation(self):
num_samples = 1000
x = torch.randn(num_samples, 3, 10, 10)
flat_x = x.view(x.size(0), x.size(1) * x.size(2) * x.size(3))
# compute principal components
sigma = torch.mm(flat_x.t(), flat_x) / flat_x.size(0)
u, s, _ = np.linalg.svd(sigma.numpy())
zca_epsilon = 1e-10 # avoid division by 0
d = torch.Tensor(np.diag(1. / np.sqrt(s + zca_epsilon)))
u = torch.Tensor(u)
principal_components = torch.mm(torch.mm(u, d), u.t())
mean_vector = (torch.sum(flat_x, dim=0) / flat_x.size(0))
# initialize whitening matrix
whitening = transforms.LinearTransformation(principal_components, mean_vector)
# estimate covariance and mean using weak law of large number
num_features = flat_x.size(1)
cov = 0.0
mean = 0.0
for i in x:
xwhite = whitening(i)
xwhite = xwhite.view(1, -1).numpy()
cov += np.dot(xwhite, xwhite.T) / num_features
mean += np.sum(xwhite) / num_features
# if rtol for std = 1e-3 then rtol for cov = 2e-3 as std**2 = cov
assert np.allclose(cov / num_samples, np.identity(1), rtol=2e-3), "cov not close to 1"
assert np.allclose(mean / num_samples, 0, rtol=1e-3), "mean not close to 0"
# Checking if LinearTransformation can be printed as string
whitening.__repr__()
How do I apply something like this? do I use it where I define my transforms or apply it in my training loop where I am iterating over my training loop?
Thanks in advance
ZCA whitening is typically a preprocessing step, like center-reduction, which basically aims at making your data more NN-friendly (additional info below). As such, it is supposed to be applied once, right before training.
So right before you starts training your model with a given dataset X, compute the whitened dataset Z, which is simply the multiplication of X with the ZCA matrix W_zca that you can learn to compute here. Then train your model on the whitened dataset.
Finally, you should have something that looks like this
class MyModule(torch.nn.Module):
def __init__(self):
super(MyModule,self).__init__()
# Feel free to use something more useful than a simple linear layer
self._network = torch.nn.Linear(...)
# Do your stuff
...
def fit(self, inputs, labels):
""" Trains the model to predict the right label for a given input """
# Compute the whitening matrix and inputs
self._zca_mat = compute_zca(inputs)
whitened_inputs = torch.mm(self._zca_mat, inputs)
# Apply training on the whitened data
outputs = self._network(whitened_inputs)
loss = torch.nn.MSEloss()(outputs, labels)
loss.backward()
optimizer.step()
def forward(self, input):
# You always need to apply the zca transform before forwarding,
# because your network has been trained with whitened data
whitened_input = torch.mm(self._zca_mat, input)
predicted_label = self._network.forward(whitened_input)
return predicted_label
Additional info
Whitening your data means decorrelating its dimensions so that the correlation matrix of the whitened data is the identity matrix. It is a rotation-scaling operation (thus linear), and there are actually an infinity of possible ZCA transforms. To understand the maths behind ZCA, read this

How to build an RNN using numpy

I'm trying to Implement a Recurrent Neural Network using Numpy in python. I'm trying to implement a Many-to-One RNN, for a classification problem. I'm a little fuzzy on the psuedo code, especially on the BPTT concept. I'm comfortable with the forward pass ( not entirely sure if my implementation is correct ) but really confused with back ward pass, and I need some advice from experts in this field.
I did check out related posts :
1) Implementing RNN in numpy
2) Output for RNN
3) How can I build RNN
But I feel my issue is with understanding the psuedo code / concept first up, code in those posts is complete and have reached further stage than mine.
My Implementation is inspired from the tutorial:
WildML RNN from scratch
I did implement a Feed-Forward Neural Network following part of tutorial from the same author, but I'm really confused with this implementation of his. Andrew Ng's RNN video suggests 3 different weights ( Weights for activation, Input and Output layers ) but the above tutorial only has two sets of weights ( correct me if I'm wrong ).
The nomenclature in my code follows that of Andrew Ng's RNN pseudo code ...
I'm reshaping my input samples in to 3D ( batch_size, n_time steps, n_ dimensions ) ... Once , I reshape my samples I'm doing forward pass on each sample seperately ...
Here's my code:
def RNNCell(X, lr, y=None, n_timesteps=None, n_dimensions=None, return_sequence = None, bias = None):
'''Simple function to compute forward and bakward passes for a Many-to-One Recurrent Neural Network Model.
This function Reshapes X,Y in to 3D array of shape (batch_size, n_timesteps, n_ dimensions) and then performs
recurrent operations on each sample of the data for n_timesteps'''
# If user has specified some target variable
if len(y) != 0:
# No. of unique values in the target variables will be the dimesions for the output layer
_,n_unique = np.unique(y, return_counts=True)
else:
# If there's no target variable given, then dimensions of target variable by default is 2
n_unique = 2
# Weights of Vectors to multiply with input samples
Wx = np.random.uniform(low = 0.0,
high = 0.3,
size = (n_dimensions, n_dimensions))
# Weights of Vectors to multiply with resulting activations
Wy = np.random.uniform(low = 0.0,
high = 0.3,
size = (n_dimensions, n_timesteps))
# Weights of Vectors to multiple with activations of previous time steps
Wa = np.random.randn(n_dimensions, n_dimensions)
# List to hold activations of each time step
activations = {'a-0' : np.zeros(shape=(n_timesteps-1, n_dimensions),
dtype=float)}
# List to hold Yhat at each time step
Yhat = []
try:
# Reshape X to align with the shape of RNN architecture
X = np.reshape(X, newshape=(len(X), n_timesteps, n_dimensions))
except:
return "Sorry can't reshape and array in to your shape"
def Forward_Prop(sample):
# Outputs at the last time step
Ot = 0
# In each time step
for time_step in range(n_timesteps+1):
if time_step < n_timesteps:
# activation G ( Wa.a<t> + X<t>.Wx )
activations['a-' + str(time_step+1)] = ReLu( np.dot( activations['a-' + str(time_step)], Wa )
+ np.dot( sample[time_step, :].reshape(1, n_dimensions) , Wx ) )
# IF it's the last time step then use softmax activation function
elif time_step == n_timesteps:
# Wy.a<t> and appending that to Yhat list
Ot = softmax( np.dot( activations['a-' + str(time_step)], Wy ) )
# Return output probabilities
return Ot
def Backward_Prop(Yhat):
# List to hold errors for the last layer
error = []
for ind in range(len(Yhat)):
error.append( y[ind] - Yhat[ind] )
error = np.array(error)
# Calculating Delta for the output layer
delta_out = error * lr
#* relu_derivative(activations['a-' + str(n_timesteps)])
# Calculating gradient for the output layer
grad_out = np.dot(delta_out.reshape(len(X), n_timesteps),
activations['a-' + str(n_timesteps)])
# I'm basically stuck at this point
# Adjusting weights for the output layer
Wy = Wy - (lr * grad_out.reshape((n_dimesions, n_timesteps)))
for sample in X:
Yhat.append( Forward_Prop(sample) )
Backward_Prop(Yhat)
return Yhat
# DUMMY INPUT DATA
X = np.random.random_integers(low=0, high = 5, size = (10, 10 ));
# DUMMY LABELS
y = np.array([[0],
[1],
[1],
[1],
[0],
[0],
[1],
[1],
[0],
[1]])
I understand that my BPTT implementation is wrong, but I'm not thinking clearly and I need some experts' perspective on where exactly I'm missing the trick. I don't expect a detailed debugging of my code, I only require a high level overview of the pseudo code on back propagation ( assuming my forward prop is correct ). I think my fundamental problem can also be with the way I'm doing my forward pass on each sample individually.
I'm stuck on this problem since 3 days now, and it's really frustrating not being able to think clearly. I'd be really grateful if someone could point me in the right direction and clear my confusion. Thank you for your time in advance !! I really appreciate it once again !

Linear regression with pytorch

I tried to run linear regression on ForestFires dataset.
Dataset is available on Kaggle and gist of my attempt is here:
https://gist.github.com/Chandrak1907/747b1a6045bb64898d5f9140f4cf9a37
I am facing two problems:
Output from prediction is of shape 32x1 and target data shape is 32.
input and target shapes do not match: input [32 x 1], target [32]¶
Using view I reshaped predictions tensor.
y_pred = y_pred.view(inputs.shape[0])
Why there is a mismatch in shapes of predicted tensor and actual tensor?
SGD in pytorch never converges. I tried to compute MSE manually using
print(torch.mean((y_pred - labels)**2))
This value does not match
loss = criterion(y_pred,labels)
Can someone highlight where is the mistake in my code?
Thank you.
Problem 1
This is reference about MSELoss from Pytorch docs: https://pytorch.org/docs/stable/nn.html#torch.nn.MSELoss
Shape:
- Input: (N,∗) where * means, any number of additional dimensions
- Target: (N,∗), same shape as the input
So, you need to expand dims of labels: (32) -> (32,1), by using: torch.unsqueeze(labels, 1) or labels.view(-1,1)
https://pytorch.org/docs/stable/torch.html#torch.unsqueeze
torch.unsqueeze(input, dim, out=None) → Tensor
Returns a new tensor with a dimension of size one inserted at the specified position.
The returned tensor shares the same underlying data with this tensor.
Problem 2
After reviewing your code, I realized that you have added size_average param to MSELoss:
criterion = torch.nn.MSELoss(size_average=False)
size_average (bool, optional) – Deprecated (see reduction). By default, the losses are averaged over each loss element in the batch. Note that for some losses, there multiple elements per sample. If the field size_average is set to False, the losses are instead summed for each minibatch. Ignored when reduce is False. Default: True
That's why 2 computed values not matched. This is sample code:
import torch
import torch.nn as nn
loss1 = nn.MSELoss()
loss2 = nn.MSELoss(size_average=False)
inputs = torch.randn(32, 1, requires_grad=True)
targets = torch.randn(32, 1)
output1 = loss1(inputs, targets)
output2 = loss2(inputs, targets)
output3 = torch.mean((inputs - targets) ** 2)
print(output1) # tensor(1.0907)
print(output2) # tensor(34.9021)
print(output3) # tensor(1.0907)

How to correctly implement backpropagation for machine learning the MNIST dataset?

So, I'm using Michael Nielson's machine learning book as a reference for my code (it is basically identical): http://neuralnetworksanddeeplearning.com/chap1.html
The code in question:
def backpropagate(self, image, image_value) :
# declare two new numpy arrays for the updated weights & biases
new_biases = [np.zeros(bias.shape) for bias in self.biases]
new_weights = [np.zeros(weight_matrix.shape) for weight_matrix in self.weights]
# -------- feed forward --------
# store all the activations in a list
activations = [image]
# declare empty list that will contain all the z vectors
zs = []
for bias, weight in zip(self.biases, self.weights) :
print(bias.shape)
print(weight.shape)
print(image.shape)
z = np.dot(weight, image) + bias
zs.append(z)
activation = sigmoid(z)
activations.append(activation)
# -------- backward pass --------
# transpose() returns the numpy array with the rows as columns and columns as rows
delta = self.cost_derivative(activations[-1], image_value) * sigmoid_prime(zs[-1])
new_biases[-1] = delta
new_weights[-1] = np.dot(delta, activations[-2].transpose())
# l = 1 means the last layer of neurons, l = 2 is the second-last, etc.
# this takes advantage of Python's ability to use negative indices in lists
for l in range(2, self.num_layers) :
z = zs[-1]
sp = sigmoid_prime(z)
delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
new_biases[-l] = delta
new_weights[-l] = np.dot(delta, activations[-l-1].transpose())
return (new_biases, new_weights)
My algorithm can only get to the first round backpropagation before this error occurs:
File "D:/Programming/Python/DPUDS/DPUDS_Projects/Fall_2017/MNIST/network.py", line 97, in stochastic_gradient_descent
self.update_mini_batch(mini_batch, learning_rate)
File "D:/Programming/Python/DPUDS/DPUDS_Projects/Fall_2017/MNIST/network.py", line 117, in update_mini_batch
delta_biases, delta_weights = self.backpropagate(image, image_value)
File "D:/Programming/Python/DPUDS/DPUDS_Projects/Fall_2017/MNIST/network.py", line 160, in backpropagate
z = np.dot(weight, activation) + bias
ValueError: shapes (30,50000) and (784,1) not aligned: 50000 (dim 1) != 784 (dim 0)
I get why it's an error. The number of columns in weights doesn't match the number of rows in the pixel image, so I can't do matrix multiplication. Here's where I'm confused -- there are 30 neurons used in the backpropagation, each with 50,000 images being evaluated. My understanding is that each of the 50,000 should have 784 weights attached, one for each pixel. But when I modify the code accordingly:
count = 0
for bias, weight in zip(self.biases, self.weights) :
print(bias.shape)
print(weight[count].shape)
print(image.shape)
z = np.dot(weight[count], image) + bias
zs.append(z)
activation = sigmoid(z)
activations.append(activation)
count += 1
I still get a similar error:
ValueError: shapes (50000,) and (784,1) not aligned: 50000 (dim 0) != 784 (dim 0)
I'm just really confuzzled by all the linear algebra involved and I think I'm just missing something about the structure of the weight matrix. Any help at all would be greatly appreciated.
It looks like the issue is in your changes to the original code.
I’be downloaded example from the link you provided and it works without any errors:
Here is full source code I used:
import cPickle
import gzip
import numpy as np
import random
def load_data():
"""Return the MNIST data as a tuple containing the training data,
the validation data, and the test data.
The ``training_data`` is returned as a tuple with two entries.
The first entry contains the actual training images. This is a
numpy ndarray with 50,000 entries. Each entry is, in turn, a
numpy ndarray with 784 values, representing the 28 * 28 = 784
pixels in a single MNIST image.
The second entry in the ``training_data`` tuple is a numpy ndarray
containing 50,000 entries. Those entries are just the digit
values (0...9) for the corresponding images contained in the first
entry of the tuple.
The ``validation_data`` and ``test_data`` are similar, except
each contains only 10,000 images.
This is a nice data format, but for use in neural networks it's
helpful to modify the format of the ``training_data`` a little.
That's done in the wrapper function ``load_data_wrapper()``, see
below.
"""
f = gzip.open('../data/mnist.pkl.gz', 'rb')
training_data, validation_data, test_data = cPickle.load(f)
f.close()
return (training_data, validation_data, test_data)
def load_data_wrapper():
"""Return a tuple containing ``(training_data, validation_data,
test_data)``. Based on ``load_data``, but the format is more
convenient for use in our implementation of neural networks.
In particular, ``training_data`` is a list containing 50,000
2-tuples ``(x, y)``. ``x`` is a 784-dimensional numpy.ndarray
containing the input image. ``y`` is a 10-dimensional
numpy.ndarray representing the unit vector corresponding to the
correct digit for ``x``.
``validation_data`` and ``test_data`` are lists containing 10,000
2-tuples ``(x, y)``. In each case, ``x`` is a 784-dimensional
numpy.ndarry containing the input image, and ``y`` is the
corresponding classification, i.e., the digit values (integers)
corresponding to ``x``.
Obviously, this means we're using slightly different formats for
the training data and the validation / test data. These formats
turn out to be the most convenient for use in our neural network
code."""
tr_d, va_d, te_d = load_data()
training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
training_results = [vectorized_result(y) for y in tr_d[1]]
training_data = zip(training_inputs, training_results)
validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
validation_data = zip(validation_inputs, va_d[1])
test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
test_data = zip(test_inputs, te_d[1])
return (training_data, validation_data, test_data)
def vectorized_result(j):
"""Return a 10-dimensional unit vector with a 1.0 in the jth
position and zeroes elsewhere. This is used to convert a digit
(0...9) into a corresponding desired output from the neural
network."""
e = np.zeros((10, 1))
e[j] = 1.0
return e
class Network(object):
def __init__(self, sizes):
"""The list ``sizes`` contains the number of neurons in the
respective layers of the network. For example, if the list
was [2, 3, 1] then it would be a three-layer network, with the
first layer containing 2 neurons, the second layer 3 neurons,
and the third layer 1 neuron. The biases and weights for the
network are initialized randomly, using a Gaussian
distribution with mean 0, and variance 1. Note that the first
layer is assumed to be an input layer, and by convention we
won't set any biases for those neurons, since biases are only
ever used in computing the outputs from later layers."""
self.num_layers = len(sizes)
self.sizes = sizes
self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
self.weights = [np.random.randn(y, x)
for x, y in zip(sizes[:-1], sizes[1:])]
def feedforward(self, a):
"""Return the output of the network if ``a`` is input."""
for b, w in zip(self.biases, self.weights):
a = sigmoid(np.dot(w, a)+b)
return a
def SGD(self, training_data, epochs, mini_batch_size, eta,
test_data=None):
"""Train the neural network using mini-batch stochastic
gradient descent. The ``training_data`` is a list of tuples
``(x, y)`` representing the training inputs and the desired
outputs. The other non-optional parameters are
self-explanatory. If ``test_data`` is provided then the
network will be evaluated against the test data after each
epoch, and partial progress printed out. This is useful for
tracking progress, but slows things down substantially."""
if test_data: n_test = len(test_data)
n = len(training_data)
for j in xrange(epochs):
random.shuffle(training_data)
mini_batches = [
training_data[k:k+mini_batch_size]
for k in xrange(0, n, mini_batch_size)]
for mini_batch in mini_batches:
self.update_mini_batch(mini_batch, eta)
if test_data:
print "Epoch {0}: {1} / {2}".format(
j, self.evaluate(test_data), n_test)
else:
print "Epoch {0} complete".format(j)
def update_mini_batch(self, mini_batch, eta):
"""Update the network's weights and biases by applying
gradient descent using backpropagation to a single mini batch.
The ``mini_batch`` is a list of tuples ``(x, y)``, and ``eta``
is the learning rate."""
nabla_b = [np.zeros(b.shape) for b in self.biases]
nabla_w = [np.zeros(w.shape) for w in self.weights]
for x, y in mini_batch:
delta_nabla_b, delta_nabla_w = self.backprop(x, y)
nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
self.weights = [w-(eta/len(mini_batch))*nw
for w, nw in zip(self.weights, nabla_w)]
self.biases = [b-(eta/len(mini_batch))*nb
for b, nb in zip(self.biases, nabla_b)]
def backprop(self, x, y):
"""Return a tuple ``(nabla_b, nabla_w)`` representing the
gradient for the cost function C_x. ``nabla_b`` and
``nabla_w`` are layer-by-layer lists of numpy arrays, similar
to ``self.biases`` and ``self.weights``."""
nabla_b = [np.zeros(b.shape) for b in self.biases]
nabla_w = [np.zeros(w.shape) for w in self.weights]
# feedforward
activation = x
activations = [x] # list to store all the activations, layer by layer
zs = [] # list to store all the z vectors, layer by layer
for b, w in zip(self.biases, self.weights):
z = np.dot(w, activation)+b
zs.append(z)
activation = sigmoid(z)
activations.append(activation)
# backward pass
delta = self.cost_derivative(activations[-1], y) * \
sigmoid_prime(zs[-1])
nabla_b[-1] = delta
nabla_w[-1] = np.dot(delta, activations[-2].transpose())
# Note that the variable l in the loop below is used a little
# differently to the notation in Chapter 2 of the book. Here,
# l = 1 means the last layer of neurons, l = 2 is the
# second-last layer, and so on. It's a renumbering of the
# scheme in the book, used here to take advantage of the fact
# that Python can use negative indices in lists.
for l in xrange(2, self.num_layers):
z = zs[-l]
sp = sigmoid_prime(z)
delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
nabla_b[-l] = delta
nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
return (nabla_b, nabla_w)
def evaluate(self, test_data):
"""Return the number of test inputs for which the neural
network outputs the correct result. Note that the neural
network's output is assumed to be the index of whichever
neuron in the final layer has the highest activation."""
test_results = [(np.argmax(self.feedforward(x)), y)
for (x, y) in test_data]
return sum(int(x == y) for (x, y) in test_results)
def cost_derivative(self, output_activations, y):
"""Return the vector of partial derivatives \partial C_x /
\partial a for the output activations."""
return (output_activations-y)
#### Miscellaneous functions
def sigmoid(z):
"""The sigmoid function."""
return 1.0/(1.0+np.exp(-z))
def sigmoid_prime(z):
"""Derivative of the sigmoid function."""
return sigmoid(z)*(1-sigmoid(z))
training_data, validation_data, test_data = load_data_wrapper()
net = Network([784, 30, 10])
net.SGD(training_data, 30, 10, 3.0, test_data=test_data)
Additional info:
However, I would recommend using one of existing frameworks, for example - Keras to don't reinvent the wheel
Also, it was checked with python 3.6:
Kudos on digging into Nielsen's code. It's a great resource to develop thorough understanding of NN principles. Too many people leap ahead to Keras without knowing what goes on under the hood.
Each training example doesn't get its own weights. Each of the 784 features does. If each example got its own weights then each weight set would overfit to its corresponding training example. Also, if you later used your trained network to run inference on a single test example, what would it do with 50,000 sets of weights when presented with just one handwritten digit? Instead, each of the 30 neurons in your hidden layer learns a set of 784 weights, one for each pixel, that offers high predictive accuracy when generalized to any handwritten digit.
Import network.py and instantiate a Network class like this without modifying any code:
net = network.Network([784, 30, 10])
..which gives you a network with 784 input neurons, 30 hidden neurons and 10 output neurons. Your weight matrices will have dimensions [30, 784] and [10, 30], respectively. When you feed the network an input array of dimensions [784, 1] the matrix multiplication that gave you an error is valid because dim 1 of the weight matrix equals dim 0 of the input array (both 784).
Your problem is not implementation of backprop but rather setting up a network architecture appropriate for the shape of your input data. If memory serves Nielsen leaves backprop as a black box in chapter 1 and doesn't dive into it until chapter 2. Keep at it, and good luck!

Restricting the output values of layers in Keras

I have defined my MLP in the code below. I want to extract the values of layer_2.
def gater(self):
dim_inputs_data = Input(shape=(self.train_dim[1],))
dim_svm_yhat = Input(shape=(3,))
layer_1 = Dense(20,
activation='sigmoid')(dim_inputs_data)
layer_2 = Dense(3, name='layer_op_2',
activation='sigmoid', use_bias=False)(layer_1)
layer_3 = Dot(1)([layer_2, dim_svm_yhat])
out_layer = Dense(1, activation='tanh')(layer_3)
model = Model(input=[dim_inputs_data, dim_svm_yhat], output=out_layer)
adam = optimizers.Adam(lr=0.01)
model.compile(loss='mse', optimizer=adam, metrics=['accuracy'])
return model
Suppose the output of layer_2 is below in matrix form
0.1 0.7 0.8
0.1 0.8 0.2
0.1 0.5 0.5
....
I would like below to be fed into layer_3 instead of above
0 0 1
0 1 0
0 1 0
Basically, I want the first maximum values to be converted to 1 and other to 0.
How can this be achieved in keras?.
Who decides the range of output values?
Output range of any layer in a neural network is decided by the activation function used for that layer. For example, if you use tanh as your activation function, your output values will be restricted to [-1,1] (and the values are continuous, check how the values get mapped from [-inf,+inf] (input on x-axis) to [-1,+1] (output on y-axis) here, understanding this step is very important)
What you should be doing is add a custom activation function that restricts your values to a step function i.e., either 1 or 0 for [-inf, +inf] and apply it to that layer.
How do I know which function to use?
You need to create y=some_function that satisfies all your needs (the input to output mapping) and convert that to Python code just like this one:
from keras import backend as K
def binaryActivationFromTanh(x, threshold) :
# convert [-inf,+inf] to [-1, 1]
# you can skip this step if your threshold is actually within [-inf, +inf]
activated_x = K.tanh(x)
binary_activated_x = activated_x > threshold
# cast the boolean array to float or int as necessary
# you shall also cast it to Keras default
# binary_activated_x = K.cast_to_floatx(binary_activated_x)
return binary_activated_x
After making your custom activation function, you can use it like
x = Input(shape=(1000,))
y = Dense(10, activation=binaryActivationFromTanh)(x)
Now test the values and see if you are getting the values like you expected. You can now throw this piece into a bigger neural network.
I strongly discourage adding new layers to add restriction to your outputs, unless it is solely for activation (like keras.layers.LeakyReLU).
Use Numpy in between. Here is an example with a random matrix:
a = np.random.random((5, 5)) # simulate random value output of your layer
result = (a == a.max(axis=1)[:,None]).astype(int)
See also this thread: Numpy: change max in each row to 1, all other numbers to 0
You than feed in result as input to your next layer.
For wrapping the Numpy calculation you could use the Lambda layer. See examples here: https://keras.io/layers/core/#lambda
Edit:
Suggestion doesn´t work. I keep answer only to keep related comments.

Resources