I'm trying to train a sparse model, that is some of the model parameters have to remain zero during optimization.
Is this possible in Keras to define a mask for the parameters so that the optimizer would not update masked ones?
Unfortunately, freezing one layer would not work as I need to mask parameters in a more fine-grained fashion.
You can use tf.where to select elementwise between the parameters and tf.stop_gradient(parameters).
Related
In a custom optimizer I would like to update weights with random values if the loss function has not decreased.
However, I can not see how to do that in the methods you can override (resource_apply_dense, resource_apply_sparse, create_slots, get_config). None of them are passed the loss function.
I have tried overriding minimize(), but that is not called in a standard training loop.
Any ideas?
If you are writing a custom optimizer, I think the easiest way to apply it is to explicitly define the layers, also. In a standard feedforward neural network, if x is the input, then h=tf.tanh(tf.matmul(x,W)+b) is an example of the first hidden layer. Similarly you can get more layers. Then W and b are variables you need to update. The training loop would look something like this:
trainable_variables=[W,b]
for i in range(1000):
optimizer.minimize(loss, trainable_variables)
but with your own optimizer instead of the one from keras.
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.
In TensorFlow's offcial documentations, they always pass training=True when calling a Keras model in a training loop, for example, logits = mnist_model(images, training=True).
I tried help(tf.keras.Model.call) and it shows that
Help on function call in module tensorflow.python.keras.engine.network:
call(self, inputs, training=None, mask=None)
Calls the model on new inputs.
In this case `call` just reapplies
all ops in the graph to the new inputs
(e.g. build a new computational graph from the provided inputs).
Arguments:
inputs: A tensor or list of tensors.
training: Boolean or boolean scalar tensor, indicating whether to run
the `Network` in training mode or inference mode.
mask: A mask or list of masks. A mask can be
either a tensor or None (no mask).
Returns:
A tensor if there is a single output, or
a list of tensors if there are more than one outputs.
It says that training is a Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode. But I didn't find any information about this two modes.
In a nutshell, I don't know what is the influence of this argument. And what if I missed this argument when training?
Some neural network layers behave differently during training and inference, for example Dropout and BatchNormalization layers. For example
During training, dropout will randomly drop out units and correspondingly scale up activations of the remaining units.
During inference, it does nothing (since you usually don't want the randomness of dropping out units here).
The training argument lets the layer know which of the two "paths" it should take. If you set this incorrectly, your network might not behave as expected.
Training indicating whether the layer should behave in training mode or in inference mode.
training=True: The layer will normalize its inputs using the mean and variance of the current batch of inputs.
training=False: The layer will normalize its inputs using the mean and variance of its moving statistics, learned during training.
Usually in inference mode training=False, but in some networks such as pix2pix_cGAN At both times of inference and training, training=True.
I am trying to build a regression model, for which I have a nominal variable with very high cardinality. I am trying to get the categorical embedding of the column.
Input:
df["nominal_column"]
Output:
the embeddings of the column.
I want to use the op of the embedding column alone since I would require that as a input to my traditional regression model. Is there a way to extract that output alone.
P.S I am not asking for code, any suggestion on the approach would be great.
If the embedding is part of the model and you train it, then you can use functional API of keras to get output of any intermediate operation in your graph:
x=Input((number_of_categories,))
y=Embedding(parameters_of_your_embeddings)(x)
output=Rest_of_your_model()(y)
model=Model(inputs=[x],outputs=[output,y])
if you do it before you train the model, you'll have to define custom loss function, that deals only with part of the output. The other way is to train the model with just one output, then create identical model with two outputs and set the weights of the second model from the trained one.
If you want to get the embedding matrix from your model, you can just use method get_weights of the embedding layer which returns the weights in numpy array.
I am implementing a sparse model using TensorFlow and feature columns. I am wondering is there a way to extract all the sparse weights and add L1/L2 regularization? For optimizers other than FTRL, the L1/L2 can be implemented using https://www.tensorflow.org/api_docs/python/tf/contrib/layers/l1_regularizer
But this is very inefficient since it adds all the weights densely. Is there a way to get all the weights sparsely (i.e. the weights for the nonzero features of a batch) from tf.feature_column.linear_model?
Thanks!