I'm trying to use the shape of an incoming tensor to form the output, sort of like this:
import tensorflow.keras.backend as K
def myFunc(x):
sz = tf.shape(x)[1]
# .. other stuff
z = K.repeat_elements(y, sz, axis=1)
This results in TypeError: Tensor object cannot be interpreted as integer.
How do I get around this?
If you know are that the dimension of x is known in advance, you can use x.shape[1] instead of tf.shape(x)[1], which will return an integer.
But I would advise to use tf.repeat instead of tf.keras.backend.repeat_elements. tf.repeat will work regardless the usage of tf.shape(x) or x.shape.
Related
I know this is dumb, but I need the equivalent of np.sqrt(2.0*np.pi) in my loss function. How can I get it? Statements like this give error: 'float object has no attribute dtype':
pi = np.pi
def myLoss(...):
k = K.sqrt(2.0*pi)
...
Even K.sqrt(2.0*3.14159) is disallowed.
Use it like this:
k = K.sqrt(tf.constant([2.0*np.pi]))
Since, it accepts an object which has dtype. One option is a Tensor.
Another option is to not using keras backend, but using numpy:
k = np.sqrt(2.0*np.pi)
I'm struggling with this for a while. I searched stack and check tf2
doc a bunch of times. There is one solution indicated, but
I don't understand why my solution doesn't work.
In my case, I store a binary string (i.e., bytes) in tfrecords.
if I iterate over dataset via as_numpy_list or directly call numpy()
on each item, I can get back binary string.
while iterating the dataset, it does work.
I'm not sure what exactly map() passes to test_callback.
I see doesn't have a method nor property numpy, and the same about type
tf.io.decode_raw return. (it is Tensor, but it has no numpy as well)
Essentially I need to take a binary string, parse it via my
x = decoder.FromString(y) and then pass it my encoder
that will transform x binary string to tensor.
def test_callback(example_proto):
# I tried to figure out. can I use bytes?decode
# directly and what is the most optimal solution.
parsed_features = tf.io.decode_raw(example_proto, out_type=tf.uint8)
# tf.io.decoder returns tensor with N bytes.
x = creator.FromString(parsed_features.numpy)
encoded_seq = midi_encoder.encode(x)
return encoded_seq
raw_dataset = tf.data.TFRecordDataset(filenames=["main.tfrecord"])
raw_dataset = raw_dataset.map(test_callback)
Thank you, folks.
I found one solution but I would love to see more suggestions.
def test_callback(example_proto):
from_string = creator.FromString(example_proto.numpy())
encoded_seq = encoder.encoder(from_string)
return encoded_seq
raw_dataset = tf.data.TFRecordDataset(filenames=["main.tfrecord"])
raw_dataset = raw_dataset.map(lambda x: tf.py_function(test_callback, [x], [tf.int64]))
My understanding that tf.py_function has a penalty on performance.
Thank you
I'm wrapping a function as a layer. In this function, I need to know what is the shape of the input. The first index of shape is the batch_size, I need to know it! The problem is that K.int_shape returns something like (None, 2, 10). But, this (None) thing should be known at runtime, right? it is still None and causes an error.
Basically, in my function I want to create a constant that is as long as the batch_size.
Here is my function for what its worth
def func(inputs):
max_iter=3
x, y= inputs
c= tf.complex(x, y)
print(K.int_shape(c))
z= tf.zeros(shape=K.int_shape(c), dtype='complex64')
#b=K.switch(K.greater( tf.abs(c) , 4), K.constant(1, shape=(1,1)), K.constant(0, shape=(1,1)))
for i in range(max_iter):
c= c * c + z
return c
layer= Lambda(func)
You can see where I created the constant z. I want its shape to be equal to the input shape. But this is causing an error with massive trace. If I replace that with a fixed shape it works. I traced the error to this damn None thing.
Instead of using int_shape, you can use tf.zeros_like to create z
z= tf.zeros_like(c, dtype='complex64')
Tensorflow has tf.logical_and() and tf.logical_or() for comparison of two boolean tensors, i.e. tf.logical_and(x,y)==TRUE if x==TRUE and y==TRUE (doc). I can't find anything like this in the Keras backend though. They have keras.backend.any() and .all(), but this is for aggregation within a tensor, not between. I've been having to use workarounds with nested K.switch() functions, but it is painfully inelegant.
Let x and y be boolean keras tensors of the same shape.
To take elementwise or, do the following:
keras.backend.any(keras.backend.stack([x, y], axis=0), axis=0)
To take elementwise and, do the following:
keras.backend.all(keras.backend.stack([x, y], axis=0), axis=0)
Here keras.backend.stack([x, y], axis=0) stacks x and y into a new tensor with an additional dimension at number 0. After that keras.backend.any takes a logical or along the new dimension, and keras.backend.any takes the logical and.
My solution (perhaps not the best, because I haven't found others either), is:
A = K.cast(someBooleanTensor, K.floatx())
B = K.cast(anotherBooleanTensor, K.floatx())
A_and_B = A * B #this is also something I use a lot for gathering elements
A_or_B = 1 -((1-A)*(1-B))
But thinking about it now... I never tested python operators... perhaps they work?
I have tensor that has shape (?, 3), looks like this [x, y, z] and I need to create function that take argmax of it, creates new vector and assign values with respect to dimension and argmax.
Example:
f(y):
v = tf.variable(tf.zeros(y.get_shape()))
index = tf.argmax(y)
v[index] = 1.0
return v
Unfortunately this doesn't work and I can't figure out how can one do it.
Are you sure that you want to create and assign to a tf.Variable here? It would probably be simpler to use the tf.one_hot() op (available from version 0.8 onwards) to build the result functionally, as you wouldn't have to worry about initialization, etc. For example, you could do the following:
def f(y):
index = tf.argmax(y, 1)
return tf.one_hot(index, tf.shape(y)[1], 1.0, 0.0)