Develop Reference

How can I change a tensor to NumPy?

I want to exchange Tensor a to a NumPy two-dimensional array for getting a heat map.
(Tensor(1, 64, 64, 1) -> numpy (64, 64))
I tried x.numpy(), but it doesn't work. The error message is this:
AttributeError: in user code: :187 call * x_np=x.numpy() /usr/local/lib/python3.7/dist packages/tensorflow/python/framework/ops.py:401 getattr self.getattribute(name) AttributeError: 'Tensor' object has no attribute 'numpy'
This is the tensor information and type of the tensor:
Tensor("ExpandDims:0", shape=(1, 64, 64, 1), dtype=float32)
<class 'tensorflow.python.framework.ops.Tensor'>
and I don't know what ExpandDims:0 means (what is this argv?).
Tensorflow:2.6.0
Numpy:1.21.2
I made the test code that has the same Tensor type, shape, and env, and it works.
What should I do?
import tensorflow as tf
import numpy
print(tf.__version__)
print(numpy.__version__)
a = tf.constant([[[[0.1]*1]*64]*64])
print(a)
print(a.numpy())

2D sparse input tensorflow

I try to use 2D sparse input with Tensorflow 2.6, a minimal example is:
input1=keras.layers.Input(shape=(3,64), sparse=True)
layer1=keras.layers.Dense(32)(input1)
output1=keras.layers.Dense(32)(layer1)
model = keras.Model(inputs = [input1], outputs = [output1])
model.compile()
model.summary()
However I end up with the following error message:
TypeError: Failed to convert object of type <class 'tensorflow.python.framework.sparse_tensor.SparseTensor'> to Tensor. Contents: SparseTensor(indices=Tensor("Placeholder_1:0", shape=(None, 3), dtype=int64), values=Tensor("Placeholder:0", shape=(None,), dtype=float32), dense_shape=Tensor("PlaceholderWithDefault:0", shape=(3,), dtype=int64)). Consider casting elements to a supported type.
What am I doing wrong ? it works if I flatten the matrix.

Edited code:
import tensorflow as tf
input1 = tf.keras.layers.Input(shape=(3,), sparse=True)
layer1 = tf.keras.layers.Dense(32)(input1)
output1= tf.keras.layers.Dense(32)(layer1)
model = tf.keras.Model(inputs = [input1], outputs = [output1])
model.compile()
model.summary()
Reference:
https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/guide/sparse_tensor.ipynb#scrollTo=E8za5DK8vfo7

Error when trying to compile a keras model ValueError: Tensor conversion requested dtype int64 for Tensor with dtype float32

I am trying to make a speech recognizer using tensorflow and am getting this error that
ValueError: Tensor conversion requested dtype int64 for Tensor with
dtype float32: 'Tensor("loss_2/lambda_loss/ExpandDims:0", shape=(?,
1), dtype=float32)'
and
TypeError: Input 'y' of 'Mul' Op has type float32 that does not match
type int64 of argument 'x'.
Minimum Running Code where tensorflow is imported as tf
train_input_val = tf.keras.layers.Input(name='the_input', shape=[None,num_features], dtype='float32')
seq_len = tf.keras.layers.Input(name='input_length', shape=[1], dtype='int64')
y_pred = tf.keras.layers.Lambda(ctc_decode_func ,name = 'lambda')([train_input_val, seq_len])
model2 = tf.keras.Model(inputs=[train_input_val,seq_len],outputs=y_pred)
model2.compile(loss={'lambda': lambda y_true, y_pred: y_true}, optimizer='adam')
and ctc_decode_func is defined as
def ctc_decode_func(args):
y_pred, seq_len = args
y_pred,log_prob = tf.keras.backend.ctc_decode(y_pred, tf.squeeze(seq_len))
return y_pred
I tried casting everything to int64 , but still the error persisted. I dont Even know which part of lambda layer is throwing the error.
Please Help

Wrap tensorflow function in keras layer

i'm trying to use the tensorflow unique function (https://www.tensorflow.org/api_docs/python/tf/unique) in a keras lambda layer.
Code below:
def unique_idx(x):
output = tf.unique(x)
return output[1]
then
inp1 = Input(batch_shape(None, 1))
idx = Lambda(unique_idx)(inp1)
model = Model(inputs=inp1, outputs=idx)
when I now use **model.compile(optimizer='Adam', loss='mean_squared_error')**
I get the error:
ValueError: Tensor conversion requested dtype int32 for Tensor with
dtype float32: 'Tensor("lambda_9_sample_weights_1:0", shape=(?,),
dtype=float32)'
Does anybody know whats the error here or a different way of using the tensorflow function?

A keras model expects a float32 as output, but the indices returned from tf.unique is a int32. A casting fixes your problem.
Another issue is that unique expects a flatten array. reshape fixes this one.
import tensorflow as tf
from keras import Input
from keras.layers import Lambda
from keras.engine import Model
def unique_idx(x):
x = tf.reshape(x, [-1])
u, indices = tf.unique(x)
return tf.cast(indices, tf.float32)
x = Input(shape=(1,))
y = Lambda(unique_idx)(x)
model = Model(inputs=x, outputs=y)
model.compile(optimizer='adam', loss='mse')

How to prevent Tensorflow unpack() method casting to float64

I'm trying to set up a sequential RNN in Tensorflow with seq2seq.rnn_decoder(). The input that rnn_decoder() wants is a list of tensors, so to generate this I've passed in a rank-3 tensor and used tf.unpack() to make it into a list. The problem arises when the float32 array that I pass in in turned into a float64 tensor by tf.unpack(), making it incompatible with the rest of the model. Here's the code I put together to convince me that the culprit is tf.unpack():
inputDat = loader.getSequential(BATCH_SIZE)
print(inputDat.shape)
output (BATCH_SIZE is five, sequence length is ten):
(10, 5, 3)
Then I can load this data in a Tensorflow session:
sess = tf.InteractiveSession()
input_tensor = tf.constant(inputDat.astype('float32'), dtype=tf.float32)
print "Input tensor type: " + str(type(input_tensor.eval()[0,0,0]))
input_tensor = tf.unpack(inputDat)
print "Input tensor shape: " + str(len(input_tensor)) + "x" + str(input_tensor[0].eval().shape)
print "Input tensor type: " + str(type(input_tensor[0].eval()[0,0]))
Output:
Input tensor type: <type 'numpy.float32'>
Input tensor shape: 10x(5, 3)
Input tensor type: <type 'numpy.float64'>
What's going on here? Using a FOR loop to iterate through each of the sequential entries and re-cast it seems like the wrong way to do this, and I can't find a method inside Tensorflow to cast every member of a list.

You don't need a for-loop: you can use tf.cast().
Example:
input_tensor = tf.unpack(inputDat) # result is 64-bit
input_tensor = tf.cast(input_tensor, tf.float32) # now it's 32-bit