I am using Keras and I want to apply dropConnect on the hidden-to-hidden weights in an LSTM. I found that Keras only allows to apply dropout on the hidden states using (recurrent_dropout).
I am trying to make a custom implementation of this. I am trying to create a custom recurrent_regularizer using the following:
def dropConnect_reg(weight_matrix):
return tf.nn.dropout(weight_matrix, rate = 0.5)
then use it as follows (the task is language modelling, so I apply a softmax layer on the vocab):
model.add(LSTM(650, return_sequences=True, recurrent_regularizer=dropConnect_reg))
model.add(Dense(vocab_size, activation='softmax'))
However, I don't think this works properly. Without using the implemented recurrent_regularizer the loss is a scalar number as expected (the categorical cross-entropy loss). However, when using it, it outputs a full array for the loss instead of having only one number (dimensions: time_steps,time_steps*4). I am also currently not sure if this is applied during training only as it is intended.
Any ideas on how to properly implement this?
If you only want the last output from the LSTM, you'll want to set return_sequences=False. If you only want to apply the dropout during training you'll need something like this:
def dropconnect_regularizer(weight_matrix):
return tf.nn.dropout(weight_matrix, rate=0.5)
if training:
regularizer = dropconnect_regularizer
else:
regularizer = None
model.add(LSTM(650, recurrent_regularizer=regularizer))
Related
Imagine I have a convolutional neural network to classify MNIST digits, such as this Keras example. This is purely for experimentation so I don't have a clear reason or justification as to why I'm doing this, but let's say I would like to regularize or penalize the output of an intermediate layer. I realize that the visualization below does not correspond to the MNIST CNN example and instead just has several fully connected layers. However, to help visualize what I mean let's say I want to impose a penalty on the node values in layer 4 (either pre or post activation is fine with me).
In addition to having a categorical cross entropy loss term which is typical for multi-class classification, I would like to add another term to the loss function that minimizes the squared sum of the output at a given layer. This is somewhat similar in concept to l2 regularization, except that l2 regularization is penalizing the squared sum of all weights in the network. Instead, I am purely interested in the values of a given layer (e.g. layer 4) and not all the weights in the network.
I realize that this requires writing a custom loss function using keras backend to combine categorical crossentropy and the penalty term, but I am not sure how to use an intermediate layer for the penalty term in the loss function. I would greatly appreciate help on how to do this. Thanks!
Actually, what you are interested in is regularization and in Keras there are two different kinds of built-in regularization approach available for most of the layers (e.g. Dense, Conv1D, Conv2D, etc.):
Weight regularization, which penalizes the weights of a layer. Usually, you can use kernel_regularizer and bias_regularizer arguments when constructing a layer to enable it. For example:
l1_l2 = tf.keras.regularizers.l1_l2(l1=1.0, l2=0.01)
x = tf.keras.layers.Dense(..., kernel_regularizer=l1_l2, bias_regularizer=l1_l2)
Activity regularization, which penalizes the output (i.e. activation) of a layer. To enable this, you can use activity_regularizer argument when constructing a layer:
l1_l2 = tf.keras.regularizers.l1_l2(l1=1.0, l2=0.01)
x = tf.keras.layers.Dense(..., activity_regularizer=l1_l2)
Note that you can set activity regularization through activity_regularizer argument for all the layers, even custom layers.
In both cases, the penalties are summed into the model's loss function, and the result would be the final loss value which would be optimized by the optimizer during training.
Further, besides the built-in regularization methods (i.e. L1 and L2), you can define your own custom regularizer method (see Developing new regularizers). As always, the documentation provides additional information which might be helpful as well.
Just specify the hidden layer as an additional output. As tf.keras.Models can have multiple outputs, this is totally allowed. Then define your custom loss using both values.
Extending your example:
input = tf.keras.Input(...)
x1 = tf.keras.layers.Dense(10)(input)
x2 = tf.keras.layers.Dense(10)(x1)
x3 = tf.keras.layers.Dense(10)(x2)
model = tf.keras.Model(inputs=[input], outputs=[x3, x2])
for the custom loss function I think it's something like this:
def custom_loss(y_true, y_pred):
x2, x3 = y_pred
label = y_true # you might need to provide a dummy var for x2
return f1(x2) + f2(y_pred, x3) # whatever you want to do with f1, f2
Another way to add loss based on input or calculations at a given layer is to use the add_loss() API. If you are already creating a custom layer, the custom loss can be added directly to the layer. Or a custom layer can be created that simply takes the input, calculates and adds the loss, and then passes the unchanged input along to the next layer.
Here is the code taken directly from the documentation (in case the link is ever broken):
from tensorflow.keras.layers import Layer
class MyActivityRegularizer(Layer):
"""Layer that creates an activity sparsity regularization loss."""
def __init__(self, rate=1e-2):
super(MyActivityRegularizer, self).__init__()
self.rate = rate
def call(self, inputs):
# We use `add_loss` to create a regularization loss
# that depends on the inputs.
self.add_loss(self.rate * tf.reduce_sum(tf.square(inputs)))
return inputs
I want to use ResNet50 with Imagenet weights.
The last layer of ResNet50 is (from here)
x = layers.Dense(1000, activation='softmax', name='fc1000')(x)
I need to keep the weights of this layer but remove the softmax function.
I want to manually change it so my last layer looks like this
x = layers.Dense(1000, name='fc1000')(x)
but the weights stay the same.
Currently I call my net like this
resnet = Sequential([
Input(shape(224,224,3)),
ResNet50(weights='imagenet', input_shape(224,224,3))
])
I need the Input layer because otherwise the model.compile says that placeholders aren't filled.
Generally there are two ways of achievieng this:
Quick way - supported functions:
To change the final layer's activation function, you can pass an argument classifier_activation.
So in order to get rid of activation all together, your module can be called like:
import tensorflow as tf
resnet = tf.keras.Sequential([
tf.keras.layers.Input(shape=(224,224,3)),
tf.keras.applications.ResNet50(
weights='imagenet',
input_shape=(224,224,3),
pooling="avg",
classifier_activation=None
)
])
This however, is not going to work if the you want a different function, that is not supported by Keras classifer_activation parameter (e. g. custom activation function).
To achieve this you can use the workaround solution:
Long way - copy the model's weights
This solution proposes copying the original model's weights onto your custom one. This approach works because apart from the activation function you are not chaning the model's architecture.
You need to:
1. Download original model.
2. Save it's weights.
3. Declare your modified version of the model (in your case, without the activation function).
4. Set the weights of the new model.
Below snippet explains this concept in more detail:
import tensorflow as tf
# 1. Download original resnet
resnet = tf.keras.Sequential([
tf.keras.layers.Input(shape=(224,224,3)),
tf.keras.applications.ResNet50(
weights='imagenet',
input_shape=(224,224,3),
pooling="avg"
)
])
# 2. Hold weights in memory:
imagenet_weights = resnet.get_weights()
# 3. Declare the model, but without softmax
resnet_no_softmax = tf.keras.Sequential([
tf.keras.layers.Input(shape=(224,224,3)),
tf.keras.applications.ResNet50(
include_top=False,
weights='imagenet',
input_shape=(224,224,3),
pooling="avg"
),
tf.keras.layers.Dense(1000, name='fc1000')
])
# 4. Pass the imagenet weights onto the second resnet
resnet_no_softmax.set_weights(imagenet_weights)
Hope this helps!
I am trying to convert my CNN written with tensorflow layers to use the keras api in tensorflow (I am using the keras api provided by TF 1.x), and am having issue writing a custom loss function, to train the model.
According to this guide, when defining a loss function it expects the arguments (y_true, y_pred)
https://www.tensorflow.org/guide/keras/train_and_evaluate#custom_losses
def basic_loss_function(y_true, y_pred):
return ...
However, in every example I have seen, y_true is somehow directly related to the model (in the simple case it is the output of the network). In my problem, this is not the case. How do implement this if my loss function depends on some training data that is unrelated to the tensors of the model?
To be concrete, here is my problem:
I am trying to learn an image embedding trained on pairs of images. My training data includes image pairs and annotations of matching points between the image pairs (image coordinates). The input feature is only the image pairs, and the network is trained in a siamese configuration.
I am able to implement this successfully with tensorflow layers and train it sucesfully with tensorflow estimators.
My current implementations builds a tf Dataset from a large database of tf Records, where the features is a dictionary containing the images and arrays of matching points. Before I could easily feed these arrays of image coordinates to the loss function, but here it is unclear how to do so.
There is a hack I often use that is to calculate the loss within the model, by means of Lambda layers. (When the loss is independent from the true data, for instance, and the model doesn't really have an output to be compared)
In a functional API model:
def loss_calc(x):
loss_input_1, loss_input_2 = x #arbirtray inputs, you choose
#according to what you gave to the Lambda layer
#here you use some external data that doesn't relate to the samples
externalData = K.constant(external_numpy_data)
#calculate the loss
return the loss
Using the outputs of the model itself (the tensor(s) that are used in your loss)
loss = Lambda(loss_calc)([model_output_1, model_output_2])
Create the model outputting the loss instead of the outputs:
model = Model(inputs, loss)
Create a dummy keras loss function for compilation:
def dummy_loss(y_true, y_pred):
return y_pred #where y_pred is the loss itself, the output of the model above
model.compile(loss = dummy_loss, ....)
Use any dummy array correctly sized regarding number of samples for training, it will be ignored:
model.fit(your_inputs, np.zeros((number_of_samples,)), ...)
Another way of doing it, is using a custom training loop.
This is much more work, though.
Although you're using TF1, you can still turn eager execution on at the very beginning of your code and do stuff like it's done in TF2. (tf.enable_eager_execution())
Follow the tutorial for custom training loops: https://www.tensorflow.org/tutorials/customization/custom_training_walkthrough
Here, you calculate the gradients yourself, of any result regarding whatever you want. This means you don't need to follow Keras standards of training.
Finally, you can use the approach you suggested of model.add_loss.
In this case, you calculate the loss exaclty the same way I did in the first answer. And pass this loss tensor to add_loss.
You can probably compile a model with loss=None then (not sure), because you're going to use other losses, not the standard one.
In this case, your model's output will probably be None too, and you should fit with y=None.
I am using keras to build a multi-output classification model. My dataset is such as
[x1,x2,x3,x4,y1,y2,y3]
x1,x2,x3 are the features, and y1,y2,y3 are the labels, the y1,y2,y3 are multi-classes.
And I already built a model (I ingore some hidden layers):
def baseline_model(input_dim=23,output_dim=3):
model_in = Input(shape=(input_dim,))
model = Dense(input_dim*5,kernel_initializer='uniform',input_dim=input_dim)(model_in)
model = Activation(activation='relu')(model)
model = Dropout(0.5)(model)
...................
model = Dense(output_dim,kernel_initializer='uniform')(model)
model = Activation(activation='sigmoid')(model)
model = Model(model_in,model)
model.compile(optimizer='adam',loss='binary_crossentropy', metrics=['accuracy'])
return model
And then I try to use the method of keras to make it support classification:
estimator = KerasClassifier(build_fn=baseline_model)
estimator.fit()
estimator.predict(df[0:10])
But I found that the result is not multi-output, only one dimension is output.
[0,0,0,0,0,0,0,0,0,0]
So for the multi-output classification problem, we can not use KerasClassifier function to learn it?
You do not need to wrap the model in KerasClassifier. That wrapper is so that you can use the Keras model with Scikit-Learn. The type of model (classifier, regression, multiclass classifier, etc) is ultimately determined by the shape and activation of the final layer of your model.
You can simply use model.fit() function that is part of Keras. Make sure that you pass the data into the function. You can see more info on the fit function here: https://keras.io/models/model/#fit
Also your loss is setup as binary_crossentropy. For a multi-class problem you will want to use categorical_crossentropy.
model.compile(optimizer='adam',loss='categorical_crossentropy', metrics=['accuracy'])
This model isn't really what Keras refers to as multi-output as far as I can tell. With multi-output you are trying to get the output from several different layers and possibly apply different loss functions to them.
Base on the setup in your question you would be able to use the Keras Sequential model instead of the Functional model if you wanted. Keras recommends using the Sequential model if you can because its simpler. https://keras.io/getting-started/sequential-model-guide/
Can someone help me understand a bit better this problem? I must train a neural network which should output 200 mutually independent categories, each of these categories is a percentage ranging from 0 to 1. This seems to me like a binary_crossentropy problem, but every example I see on the internet uses binary_crossentropy with a single output. Since my output should be 200, if I apply binary_crossentropy, would that be correct?
This is what I have in mind, is that a correct approach or should I change it?
inputs = Input(shape=(input_shape,))
hidden = Dense(2048, activation='relu')(inputs)
hidden = Dense(2048, activation='relu')(hidden)
output = Dense(200, name='output_cat', activation='sigmoid')(hidden)
model = Model(inputs=inputs, outputs=[output])
loss_map = {'output_cat': 'binary_crossentropy'}
model.compile(loss=loss_map, optimizer="sgd", metrics=['mae', 'accuracy'])
To optimize for multiple independent binary classification problems (and not multiple category problem where you can use categorical_crossentropy) using Keras, you could do the following (here I take the example of 2 independent binary outputs, but you can extend that as much as needed):
inputs = Input(shape=(input_shape,))
hidden = Dense(2048, activation='relu')(inputs)
hidden = Dense(2048, activation='relu')(hidden)
output = Dense(units = 2, activation='sigmoid')(hidden )
here you split your output using Keras's Lambda layer:
output_1 = Lambda(lambda x: x[...,:1])(output)
output_2 = Lambda(lambda x: x[...,1:])(output)
adad = optimizers.Adadelta()
your model output becomes a list of the different independent outputs
model = Model(inputs, [output_1, output_2])
you compile the model using one loss function for each output, in a list. (In fact, if you give only one kind of loss function, I believe it will apply it to all the outputs independently)
model.compile(optimizer=adad, loss=['binary_crossentropy','binary_crossentropy'])
I know this is an old question, but I believe the accepted answer is incorrect and the most upvoted answer is workable but not optimal. The original poster's method is the correct way to solve this problem. His output is 200 independent probabilities from 0 to 1, so his output layer should be a dense layer with 200 neurons and a sigmoid activation layer. It's not a categorical_crossentropy problem because it's not 200 mutually exclusive categories. Also, there's no reason to split the output using a lambda layer when a single dense layer will do. The original poster's method is correct. Here's another way to do it using the Keras interface.
model = Sequential()
model.add(Dense(2048, input_dim=n_input, activation='relu'))
model.add(Dense(2048, input_dim=n_input, activation='relu'))
model.add(Dense(200, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
binary_crossentropy with Sigmoid activation function is used for binary (positive and negative) classification, whereas your case is multi-class classification. In the case of multi-class classification, categorical_crossentropy with softmax activation is used. The Sigmoid activation function generates the probability of input being positive class, and SoftMax generates probability corresponding to input being in each class. The class with maximum probability is assigned to the input.
For multiple category classification problems, you should use categorical_crossentropy rather than binary_crossentropy. With this, when your model classifies an input, it is going give a dispersion of probabilities between all 200 categories. The category that receives the highest probability will be the output for that particular input.
You can see this when you call model.predict(). If you were to call this function only on one input, for example, and print the results, you will see a result of 200 percentages (in total summing to 1). The hope is that one of those 200 percentages would be vastly higher than the others, which signals that the model thinks that there is a strong probability that this is the correct output (category) for this particular input.
This video may help clarify the prediction piece. Printing out the predictions starts around 3:17, but to get the full context, you'll need to start from the beginning.
When there are multiple classes, categorical_crossentropy should be used. Refer to another answer here.