I am training a GRU layer where inputs doesn't have the same length. Therefore, I have padded the inputs' features with 0.0 to make all sequences of same length. On the other hand, I don't want to compute any loss at any time step, for any sample as long as the input feature vector is all zeros. Example, at time step 1000, I have a batch size of 34, but samples number 33 and 34 of this batch lack data or feature values at time step 1000.
I have found that we can use the method Masking()(inputs) in Keras as long as all subsequent layers or operations support masking. But I have implemented my model in tensorflow. So what is the equivalence of Masking() in tensorflow?
Second, how can I know whether: batch normalization, conv layer and any non linear activation function has support for the masking() function in Keras?
Your help is much appreciated!!
So I found the detailed solution in danijar blog https://danijar.com/variable-sequence-lengths-in-tensorflow/.
The masking in keras is used when having incomplete sequences. So usually, you need to pad your sequences with 0.0 in the third dimension (The feature's dimension; when the input dimension has shape = [batch_size, sequence_length, num_features]).Afterwards, the masking in keras will take a number, will output 0 for their activations.
In summary: He showed how to compute the sequence length for each sample in the batch using length() he implemented. The output vector is then fed into the dynamic_rnn which will output zero vectors for incomplete sequences (for states and outputs), which is somehow similar to what happens in Keras Masking() function. Second, we should use a mask when computing the loss function.
All the details are discussed in this blog post.
But regarding the support thingy for masking in batch_norm, conv and non linear activation function; usually, if the output of the LSTM is zeros; then in case with sigmoid activation function at the output; the derivative of the output with respect to the input of the sigmoid function is output(1 - output). Hence, when the output is 0, this derivative is zero as well. And since back propagation applies the chain rule, then the gradients of the current sample with respect to any weight parameter in the network is going to be 0 as well. Hence, there is no need to worry about the support thingy... But the problem arises when the activation is relu for example, this is when the gradients should be explicitely multiplied by zeros before doing the back propagation (I guess). Maybe doing something like this will help:
final_output = output * mask
Then derivative of the final_output with respect to output will be the mask => 0 or 1 (the any time step; for any sample). Then, back propagate this gradient from the output of the activation function to its inputs...followed by chain rule => weights wont be affected in this case.
Related
This question relates to the neural machine translation shown here: Neural Machine Translation
self.W1 and self.W2 are initialized to dense neural layers of 10 units each, in lines 4 and 5 in the __init__ function of class BahdanauAttention
In the code image attached, I am not sure I understand the feed forward neural network set up in line 17 and line 18. So, I broke this formula down into it's parts. See line 23 and line 24.
query_with_time_axis is the input tensor to self.W1 and values is input to self.W2. And each compute the function Z = WX + b, and the Z's are added together. The dimensions of the tensors added together are (64, 1, 10) and (64, 16, 10). I am assuming random weight initialization for both self.W1 and self.W2 is handled by Keras behind the scenes.
Question:
After adding the Z's together, a non-linearity (tanh) is applied to come up with an activation and this resulting activation is input to the next layer self.V, which is a layer with just one output and gives us the score.
For this last step, we don't apply an activation function (tanh etc) to the result of self.V(tf.nn.tanh(self.W1(query_with_time_axis) + self.W2(values))), to get a single output from this last neural network layer.
Is there a reason why an activation function was not used for this last step?
The ouput of the attention form so-called attention energies, i.e., one scalar for each encoder output. These numbers get stacked into a vector a this vector is normalized using softmax, yielding attention distribution.
So, in fact, there is non-linearity applied in the next step, which is the softmax. If you used an activation function before the softmax, you would only decrease the space of distributions that the softmax can do.
I built a CNN model on images one-class classification.
The output tensor is a list which has 65 elements. I make this tensor input to Softmax Function, and got the classified result.
I think the max value in this output tensor is the classified result, why not use this way to do classification task? Just the Softmax Function can be taken the derivative easily?
Softmax is used for multi-class classification. In multi-class class classification the model is expected to classify the input to single class with higher probability. Predicting with high probability enforces probabilities for other classes to be low.
As you stated one of the reason why one uses Softmax over max function is the softmax function is diffrential over Real Numbers and max function is not.
Edit:
There are some other properties of softmax function that makes it suitable to use for neural networks compared to max. Firstly it is soft version of max function. Let's say the logits of neural network has 4 outputs of [0.5, 0.5, 0.69, 0.7]. Hard max returns 1 for maximum index(in this case for 4th index) and 0 for other indexes. This results information loss.
Second important property of softmax is the output of sofmax function are in interval [0,1] and the sum of these values is equal to 1. For this reason the output of softmax function can be interpreted as probability. This means output can be considered as the confidence of the model to classify inputs to one of each output classes.
I have a model that outputs a Softmax, and I would like to develop a custom loss function. The desired behaviour would be:
1) Softmax to one-hot (normally I do numpy.argmax(softmax_vector) and set that index to 1 in a null vector, but this is not allowed in a loss function).
2) Multiply the resulting one-hot vector by my embedding matrix to get an embedding vector (in my context: the word-vector that is associated to a given word, where words have been tokenized and assigned to indices, or classes for the Softmax output).
3) Compare this vector with the target (this could be a normal Keras loss function).
I know how to write a custom loss function in general, but not to do this. I found this closely related question (unanswered), but my case is a bit different, since I would like to preserve my softmax output.
It is possible to mix tensorflow and keras in you customer loss function. Once you can access to all Tensorflow function, things become very easy. I just give you a example of how this function could be imlement.
import tensorflow as tf
def custom_loss(target, softmax):
max_indices = tf.argmax(softmax, -1)
# Get the embedding matrix. In Tensorflow, this can be directly done
# with tf.nn.embedding_lookup
embedding_vectors = tf.nn.embedding_lookup(you_embedding_matrix, max_indices)
# Do anything you want with normal keras loss function
loss = some_keras_loss_function(target, embedding_vectors)
loss = tf.reduce_mean(loss)
return loss
Fan Luo's answer points in the right direction, but ultimately will not work because it involves non-derivable operations. Note such operations are acceptable for the real value (a loss function takes a real value and a predicted value, non-derivable operations are only fine for the real value).
To be fair, that was what I was asking in the first place. It is not possible to do what I wanted, but we can get a similar and derivable behaviour:
1) Element-wise power of the softmax values. This makes smaller values much smaller. For example, with a power of 4 [0.5, 0.2, 0.7] becomes [0.0625, 0.0016, 0.2400]. Note that 0.2 is comparable to 0.7, but 0.0016 is negligible with respect to 0.24. The higher my_power is, the more similar to a one-hot the final result will be.
soft_extreme = Lambda(lambda x: x ** my_power)(softmax)
2) Importantly, both softmax and one-hot vectors are normalized, but not our "soft_extreme". First, find the sum of the array:
norm = tf.reduce_sum(soft_extreme, 1)
3) Normalize soft_extreme:
almost_one_hot = Lambda(lambda x: x / norm)(soft_extreme)
Note: Setting my_power too high in 1) will result in NaNs. If you need a better softmax to one-hot conversion, then you may do steps 1 to 3 two or more times in a row.
4) Finally we want the vector from the dictionary. Lookup is forbidden, but we can take the average vector using matrix multiplication. Because our soft_normalized is similar to one-hot encoding this average will be similar to the vector associated to the highest argument (original intended behaviour). The higher my_power is in (1), the truer this will be:
target_vectors = tf.tensordot(almost_one_hot, embedding_matrix, axes=[[1], [0]])
Note: This will not work directly using batches! In my case, I reshaped my "one hot" (from [batch, dictionary_length] to [batch, 1, dictionary_length] using tf.reshape. Then tiled my embedding_matrix batch times and finally used:
predicted_vectors = tf.matmul(reshaped_one_hot, tiled_embedding)
There may be more elegant solutions (or less memory-hungry, if tiling the embedding matrix is not an option), so feel free to explore more.
My question is in the end.
An example CNN trained with mini-batch GD and used the dropout in the last fully-connected layer (line 60) as
fc1 = tf.layers.dropout(fc1, rate=dropout, training=is_training)
At first I thought the tf.layers.dropout or tf.nn.dropout randomly sets neurons to zero in columns. But I recently found it's not the case. The below piece of code prints what the dropout does. I used the fc0 as a 4 sample x 10 feature matrix, and the fc as the dropped out version.
import tensorflow as tf
import numpy as np
fc0 = tf.random_normal([4, 10])
fc = tf.nn.dropout(fc0, 0.5)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
a, b = sess.run([fc0, fc])
np.savetxt("oo.txt", np.vstack((a, b)), fmt="%.2f", delimiter=",")
And in the output oo.txt (original matrix: line 1-4, dropped out matrix: line 5-8):
0.10,1.69,0.36,-0.53,0.89,0.71,-0.84,0.24,-0.72,-0.44
0.88,0.32,0.58,-0.18,1.57,0.04,0.58,-0.56,-0.66,0.59
-1.65,-1.68,-0.26,-0.09,-1.35,-0.21,1.78,-1.69,-0.47,1.26
-1.52,0.52,-0.99,0.35,0.90,1.17,-0.92,-0.68,-0.27,0.68
0.20,0.00,0.71,-0.00,0.00,0.00,-0.00,0.47,-0.00,-0.87
0.00,0.00,0.00,-0.00,3.15,0.07,1.16,-0.00,-1.32,0.00
-0.00,-3.36,-0.00,-0.17,-0.00,-0.42,3.57,-3.37,-0.00,2.53
-0.00,1.05,-1.99,0.00,1.80,0.00,-0.00,-0.00,-0.55,1.35
My understanding of the proper? dropout is, knocking out p% same units for each sample in a mini-batch or batch gradient descent phase, and the back-propagation updates the weights and biases of the "thinned network". However, in the implementation of the example, the neurons of each sample in one batch were randomly dropped out, as illustrated in the oo.txt line 5 to 8, and for each sample, the "thinned network" is different.
As a comparison, in a stochastic gradient descent case, samples are fed into the neural network one-by-one, and in each iteration, weights of each tf.layers.dropout introduced "thinned network" are updated.
My question is, in the mini-batch or batch training, shouldn't it be implemented to knock out same neurons for all samples in one batch? Maybe by applying one mask to all input batch samples at each iteration?
Something like:
# ones: a 1xN all 1s tensor
# mask: a 1xN 0-1 tensor, multiply fc1 by mask with broadcasting along the axis of samples
mask = tf.layers.dropout(ones, rate=dropout, training=is_training)
fc1 = tf.multiply(fc1, mask)
Now I'm thinking the dropout strategy in the example may be a weighted way of updating weights of a certain neuron, that if a neuron is kept in 1 out of 10 samples in a mini-batch, its weights will be updated by alpha * 1/10 * (y_k_hat-y_k) * x_k, compared with alpha * 1/10 * sum[(y_k_hat-y_k) * x_k] for weights of another neuron kept in all 10 samples?
the screenshot from here
Dropouts are commonly used to prevent overfitting. In this case it would be a huge weight applied to one of the neurons. By randomly making it 0 from time to time, you force the network to use more neurons in determining the outcome. For this to work well you should drop different neurons for each example so that the gradient you compute is more similar to the one you would get without the dropout.
If you were to drop the same neurons for each example in the batch, my guess is that you will have a less stable gradient (might not matter for your application).
In addition dropout up-scales the rest of the values to keep the average activation at about the same level. Without it the network would learn wrong biases or would over-saturate when you turn dropout off.
If you still want the same neurons to be dropped in the batch then apply dropout to a all 1 tensor of shape (1, num_neurons) and then multiply it with the activations.
When using dropout, you are effectively trying to estimate the average performance of the network for a randomly chosen dropout mask, using Monte-Carlo sampling (by differentiation under the integral sign, the average gradient is equal to the gradient of the average). By fixing a dropout mask for each mini-batch, you are just introducing correlation between successive gradient estimates, which increases the variance and leads to slower training.
Imagine using a different dropout-mask for each image in the mini-batch, but forming the mini-batch from k copies of the same image; it's obvious that this would be a complete waste of effort!
This question already has answers here:
What are logits? What is the difference between softmax and softmax_cross_entropy_with_logits?
(8 answers)
Closed 2 years ago.
In the following TensorFlow function, we must feed the activation of artificial neurons in the final layer. That I understand. But I don't understand why it is called logits? Isn't that a mathematical function?
loss_function = tf.nn.softmax_cross_entropy_with_logits(
logits = last_layer,
labels = target_output
)
Logits is an overloaded term which can mean many different things:
In Math, Logit is a function that maps probabilities ([0, 1]) to R ((-inf, inf))
Probability of 0.5 corresponds to a logit of 0. Negative logit correspond to probabilities less than 0.5, positive to > 0.5.
In ML, it can be
the vector of raw (non-normalized) predictions that a classification
model generates, which is ordinarily then passed to a normalization
function. If the model is solving a multi-class classification
problem, logits typically become an input to the softmax function. The
softmax function then generates a vector of (normalized) probabilities
with one value for each possible class.
Logits also sometimes refer to the element-wise inverse of the sigmoid function.
Just adding this clarification so that anyone who scrolls down this much can at least gets it right, since there are so many wrong answers upvoted.
Diansheng's answer and JakeJ's answer get it right.
A new answer posted by Shital Shah is an even better and more complete answer.
Yes, logit as a mathematical function in statistics, but the logit used in context of neural networks is different. Statistical logit doesn't even make any sense here.
I couldn't find a formal definition anywhere, but logit basically means:
The raw predictions which come out of the last layer of the neural network.
1. This is the very tensor on which you apply the argmax function to get the predicted class.
2. This is the very tensor which you feed into the softmax function to get the probabilities for the predicted classes.
Also, from a tutorial on official tensorflow website:
Logits Layer
The final layer in our neural network is the logits layer, which will return the raw values for our predictions. We create a dense layer with 10 neurons (one for each target class 0–9), with linear activation (the default):
logits = tf.layers.dense(inputs=dropout, units=10)
If you are still confused, the situation is like this:
raw_predictions = neural_net(input_layer)
predicted_class_index_by_raw = argmax(raw_predictions)
probabilities = softmax(raw_predictions)
predicted_class_index_by_prob = argmax(probabilities)
where, predicted_class_index_by_raw and predicted_class_index_by_prob will be equal.
Another name for raw_predictions in the above code is logit.
As for the why logit... I have no idea. Sorry.
[Edit: See this answer for the historical motivations behind the term.]
Trivia
Although, if you want to, you can apply statistical logit to probabilities that come out of the softmax function.
If the probability of a certain class is p,
Then the log-odds of that class is L = logit(p).
Also, the probability of that class can be recovered as p = sigmoid(L), using the sigmoid function.
Not very useful to calculate log-odds though.
Summary
In context of deep learning the logits layer means the layer that feeds in to softmax (or other such normalization). The output of the softmax are the probabilities for the classification task and its input is logits layer. The logits layer typically produces values from -infinity to +infinity and the softmax layer transforms it to values from 0 to 1.
Historical Context
Where does this term comes from? In 1930s and 40s, several people were trying to adapt linear regression to the problem of predicting probabilities. However linear regression produces output from -infinity to +infinity while for probabilities our desired output is 0 to 1. One way to do this is by somehow mapping the probabilities 0 to 1 to -infinity to +infinity and then use linear regression as usual. One such mapping is cumulative normal distribution that was used by Chester Ittner Bliss in 1934 and he called this "probit" model, short for "probability unit". However this function is computationally expensive while lacking some of the desirable properties for multi-class classification. In 1944 Joseph Berkson used the function log(p/(1-p)) to do this mapping and called it logit, short for "logistic unit". The term logistic regression derived from this as well.
The Confusion
Unfortunately the term logits is abused in deep learning. From pure mathematical perspective logit is a function that performs above mapping. In deep learning people started calling the layer "logits layer" that feeds in to logit function. Then people started calling the output values of this layer "logit" creating the confusion with logit the function.
TensorFlow Code
Unfortunately TensorFlow code further adds in to confusion by names like tf.nn.softmax_cross_entropy_with_logits. What does logits mean here? It just means the input of the function is supposed to be the output of last neuron layer as described above. The _with_logits suffix is redundant, confusing and pointless. Functions should be named without regards to such very specific contexts because they are simply mathematical operations that can be performed on values derived from many other domains. In fact TensorFlow has another similar function sparse_softmax_cross_entropy where they fortunately forgot to add _with_logits suffix creating inconsistency and adding in to confusion. PyTorch on the other hand simply names its function without these kind of suffixes.
Reference
The Logit/Probit lecture slides is one of the best resource to understand logit. I have also updated Wikipedia article with some of above information.
Logit is a function that maps probabilities [0, 1] to [-inf, +inf].
Softmax is a function that maps [-inf, +inf] to [0, 1] similar as Sigmoid. But Softmax also normalizes the sum of the values(output vector) to be 1.
Tensorflow "with logit": It means that you are applying a softmax function to logit numbers to normalize it. The input_vector/logit is not normalized and can scale from [-inf, inf].
This normalization is used for multiclass classification problems. And for multilabel classification problems sigmoid normalization is used i.e. tf.nn.sigmoid_cross_entropy_with_logits
Personal understanding, in TensorFlow domain, logits are the values to be used as input to softmax. I came to this understanding based on this tensorflow tutorial.
https://www.tensorflow.org/tutorials/layers
Although it is true that logit is a function in maths(especially in statistics), I don't think that's the same 'logit' you are looking at. In the book Deep Learning by Ian Goodfellow, he mentioned,
The function σ−1(x) is called the logit in statistics, but this term
is more rarely used in machine learning. σ−1(x) stands for the
inverse function of logistic sigmoid function.
In TensorFlow, it is frequently seen as the name of last layer. In Chapter 10 of the book Hands-on Machine Learning with Scikit-learn and TensorFLow by Aurélien Géron, I came across this paragraph, which stated logits layer clearly.
note that logits is the output of the neural network before going
through the softmax activation function: for optimization reasons, we
will handle the softmax computation later.
That is to say, although we use softmax as the activation function in the last layer in our design, for ease of computation, we take out logits separately. This is because it is more efficient to calculate softmax and cross-entropy loss together. Remember that cross-entropy is a cost function, not used in forward propagation.
(FOMOsapiens).
If you check math Logit function, it converts real space from [0,1] interval to infinity [-inf, inf].
Sigmoid and softmax will do exactly the opposite thing. They will convert the [-inf, inf] real space to [0, 1] real space.
This is why, in machine learning we may use logit before sigmoid and softmax function (since they match).
And this is why "we may call" anything in machine learning that goes in front of sigmoid or softmax function the logit.
Here is G. Hinton video using this term.
Here is a concise answer for future readers. Tensorflow's logit is defined as the output of a neuron without applying activation function:
logit = w*x + b,
x: input, w: weight, b: bias. That's it.
The following is irrelevant to this question.
For historical lectures, read other answers. Hats off to Tensorflow's "creatively" confusing naming convention. In PyTorch, there is only one CrossEntropyLoss and it accepts un-activated outputs. Convolutions, matrix multiplications and activations are same level operations. The design is much more modular and less confusing. This is one of the reasons why I switched from Tensorflow to PyTorch.
logits
The vector of raw (non-normalized) predictions that a classification model generates, which is ordinarily then passed to a normalization function. If the model is solving a multi-class classification problem, logits typically become an input to the softmax function. The softmax function then generates a vector of (normalized) probabilities with one value for each possible class.
In addition, logits sometimes refer to the element-wise inverse of the sigmoid function. For more information, see tf.nn.sigmoid_cross_entropy_with_logits.
official tensorflow documentation
They are basically the fullest learned model you can get from the network, before it's been squashed down to apply to only the number of classes we are interested in. Check out how some researchers use them to train a shallow neural net based on what a deep network has learned: https://arxiv.org/pdf/1312.6184.pdf
It's kind of like how when learning a subject in detail, you will learn a great many minor points, but then when teaching a student, you will try to compress it to the simplest case. If the student now tried to teach, it'd be quite difficult, but would be able to describe it just well enough to use the language.
The logit (/ˈloʊdʒɪt/ LOH-jit) function is the inverse of the sigmoidal "logistic" function or logistic transform used in mathematics, especially in statistics. When the function's variable represents a probability p, the logit function gives the log-odds, or the logarithm of the odds p/(1 − p).
See here: https://en.wikipedia.org/wiki/Logit