How to print value of tensorflow.python.framework.ops.Tensor in Tensorflow 2.0?

Question

I have a few tensors in my code and and need to get the values of those tensors. This is one them. How to print the values of tensor OA?

Input:OA
Output: <tf.Tensor 'Sum_1:0' shape=(1, 600) dtype=float32>

Input:type(OA)
Output: tensorflow.python.framework.ops.Tensor

I have tried all the available functions like tf.print(), eval(), tensor.numpy(). None of them worked for me in Tensorflow 2.0. It seems they work only for 'EagerTensor' and not for 'ops.Tensor'.

1) OA.eval(session=sess) Error: ValueError: Cannot use the given session to evaluate tensor: the tensor's graph is different from the session's graph.

2) tf.print(OA) Output:

3) print (OA.numpy()) Output: AttributeError: 'Tensor' object has no attribute 'numpy'

Is there any way to convert ops.Tensor to EagerTensor to try the above functions? Or is there any other option to print the values of ops.Tensor. Please advise.

--Adding the minimal code to reproduce the example ops.Tensor in TF2.0.

!pip install tensorflow==2.0.0
tf.__version__

import tensorflow as tf
from keras.layers import Dense, Conv1D, MaxPooling1D, Flatten, Dropout, Input, Embedding, Bidirectional, LSTM
from tensorflow.keras import regularizers

EMBEDDING_DIM = 300
max_length = 120
batch_size = 512
vocab_size = 1000
units = 300

from keras.layers import Dense, Conv1D, MaxPooling1D, Flatten, Dropout, Input, Embedding, Bidirectional, LSTM
from tensorflow.keras import regularizers

input_text = tf.keras.Input(shape= (max_length), batch_size=batch_size)

embedding_layer = tf.keras.layers.Embedding(vocab_size, EMBEDDING_DIM, input_length =max_length, name="Embedding_Layer_1")
embedding_sequence = embedding_layer(input_text)

HQ = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(units,recurrent_dropout=0.5,kernel_regularizer=regularizers.l2(0.001),return_sequences=True,name='Bidirectional_1'))(embedding_sequence)
HQ = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(units,recurrent_dropout=0.5,kernel_regularizer=regularizers.l2(0.001),name='Bidirectional_2'))(HQ)

print (HQ)

Output: Tensor("bidirectional_3/concat:0", shape=(512, 600), dtype=float32)

type(HQ)

Output: tensorflow.python.framework.ops.Tensor

How to check the actual values of this tensor?

Please provide a minimal, reproducible example. How do you create OA? — jkr
– jkr, Commented Feb 21, 2020 at 12:54
@jakub - Can you please check now. I updated the question with minimal reproducible example. — Raghu
– Raghu, Commented Mar 6, 2020 at 11:12
@Raghu - I had a similar need. I wanted to inspect the embedding tensor of a constant sequence of indices using: MyEmbedding = tf.keras.layers.Embedding(tf.constant([[[0], [1], [5], [500]]])). As a result, MyEmbedding was a tensorflow.python.framework.ops.Tensor object. The only way I could print the array was by following the first example here: stackoverflow.com/questions/52215711/…, using tf.enable_eager_execution() and tensor.numpy(). Hope it helps. — George
– George, Commented Sep 25, 2020 at 1:40
tf.config.run_functions_eagerly(True) executed once at the beginning solved the problem for me for a similar problem — Lostefra
– Lostefra, Commented Oct 25, 2021 at 10:13

MSS · Accepted Answer · 2022-12-12 15:52:38Z

1

Directly you cannot print the values of tensors the way you are trying to do. Tensorflow 2.x by default runs in eager mode and also you have given no input to your incomplete model.

The way to do it is by using the custom training loop. Suppose the layers mentioned in your code stack up to create a model my_model.

from tensorflow.keras import Model


my_model = Model(input_text, outputs=HQ)

with tf.GradientTape() as t:
    HQ_predictions = my_model(input_data)
print(HQ_predictions)

answered Dec 12, 2022 at 15:52

MSS

3,6832 gold badges28 silver badges57 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

DachuanZhao · Accepted Answer · 2021-03-11 02:19:40Z

0

Use .numpy() attribute like :

your_tensor.numpy()

answered Mar 11, 2021 at 2:19

DachuanZhao

1,3594 gold badges20 silver badges38 bronze badges

1 Comment

Alonso Herrera Sep 19 at 17:13

This worked for me, thank you!

Yaoshiang · Accepted Answer · 2021-08-05 20:51:45Z

0

Your graph is not complete at the point you are printing HQ. You need to complete the model creation. Presumably something like

output = tf.keras.layers.xyz()(HQ)
model = tf.keras.models.Model(input_text, output)

The trick to print an intermediate layer is to just make it an output. You can make it an additional output of your existing model temporarily, or just make a new model.

inspection_model = tf.keras.models.Model(input_text, [output, HQ])

now run inference on your inspection_model to get the value of the intermediate activation HQ.

print(inspection_model(xyz))

answered Aug 5, 2021 at 20:51

Yaoshiang

1,95110 silver badges16 bronze badges

Comments

ncica · Accepted Answer · 2023-11-14 14:48:27Z

0

This video explains in details what is on going under the hood. to get around this, try the following :

run your function in eager mode using tf.config.run_functions_eagerly(True) , you can find an example tensorflow documentation, or you can enable eager mode for all operations using tf.compat.v1.enable_eager_execution() after that you can access your values using something like this

OA.numpy( )

run your operation in a tf.Session( )

with tf.Session( ) as sess:
   print( sess.run(OA) )

EDIT :

After the development of tensorflow 2 , you can pass your data to each layer of your model without any problems, but while fitting the model, all values inside a tensor cannot be retieved unless you use one of the following fixes:

apply model.compile(...., run_eagerly=True)
you can call tf.compat.v1.enable_eager_execution() at the beginning of your code to avoid any issues
if you want to access the values inside the tensor you can use

with tf.Session( ) as sess:
   t =  sess.run(HQ) 
   print( t ) # to print the tensor

after that you can manipulate your tensor as any normal tf.Tensor, this should allow you to also use

n = t.numpy( ) # to transform the tensor to a numpy array

now that n contains all the values of HQ you can access each individual element the same way you handle numpy arrays

you can also check this thread for more information

edited Nov 14, 2023 at 14:48

ncica

7,2161 gold badge19 silver badges41 bronze badges

answered Jun 7, 2023 at 9:01

hafedh

795 bronze badges

2 Comments

Chenmunka Over a year ago

While this link may answer the question, it is better to include the essential parts of the answer here and provide the link for reference. Link-only answers can become invalid if the linked page changes. - From Review

hafedh Over a year ago

That's a great idea, I'll edit my response to include all the necessary information.

joanis · Accepted Answer · 2024-01-05 15:33:58Z

0

Please try

print("inputs_expand.shape=",inputs_expand.shape)

i.e. the simple print and also try tf.print & tf.print_v2 Also try Serial.println.

Actually I was also suffering from the same session eval() issue which throws errors that session cannot be created this that and finally I got the solution and missed to save it.

edited Jan 5, 2024 at 15:33

joanis

13k23 gold badges38 silver badges50 bronze badges

answered Jan 4, 2024 at 11:03

Minakshi Boruah

53 bronze badges

Collectives™ on Stack Overflow

How to print value of tensorflow.python.framework.ops.Tensor in Tensorflow 2.0?

5 Answers 5

Comments

1 Comment

Comments

2 Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

5 Answers 5

Comments

1 Comment

Comments

2 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related