How to convert Tensor into NumPy array

Question

I have trained ResNet50 model on my data. I want to get the output of a custom layer while making the prediction. I tried using the below code to get the output of a custom layer, it gives data in a tensor format, but I need the data in a NumPy array format. I tried to convert the tensor to NumPy array but getting errors, I have followed this post, but it wasn't helpful

Can anyone share some thoughts, any advice will be very helpful

from keras.models import load_model
import tensorflow as tf
import numpy as np

config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.Session(config=config)

model = load_model(model_path) # load trained model

data = load_data(data_path) # load data for predictions
result = model.predict(data)
print(type(result_dev))
#<class 'numpy.ndarray'> 

result = model.get_layer('avg_pool').output
print(type(result))
#<class 'tensorflow.python.framework.ops.Tensor'>

Things I tried

Option 1

result = result.numpy()

AttributeError: 'Tensor' object has no attribute 'numpy'

Option 2

result = result.eval(session=tf.compat.v1.Session())

2020-09-22 11:21:59.522138: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-09-22 11:21:59.522343: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:

Dependency Installed:

tensorflow-gpu==1.15.0

runDOSrun · Accepted Answer · 2020-09-22 08:56:20Z

0

You can only convert tensors to numpy arrays during Eager execution. Since you're using a version older than 2.0 this is not enabled by default.

In any case, you can call this after importing tensorflow:

tf.compat.v1.enable_eager_execution()

Depending on your framework and usecase, you might also have to run tf.config.run_functions_eagerly (if you have tf.function defined anywhere). For better support of the Eager mode, you should upgrade tensorflow to the newest version and use tf.keras as your code might not work properly with older standalone versions of Keras. In newer versions, you can specify your keras model to run eagerly like this:

model.run_eagerly = True

answered Sep 22, 2020 at 8:56

runDOSrun

11.1k7 gold badges50 silver badges60 bronze badges

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

2 Comments

arush1836 Over a year ago

I tried enabling eager excecution with tf.enable_eager_execution() but it throws error RuntimeError: get_session is not available when TensorFlow is executing eagerly.. I have also tried tensorflow-gpu==2.0 but as model was trained on tensorflow-gpu==1.15 its throwing error while loading it with tensorflow-gpu==2.0

runDOSrun Over a year ago

I was expecting this, hence my warning. Compatibility in these older versions is tricky (see e.g. here) and I won't be able to directly help you with that as it is very project-specific and requires some trial and error until you find the correct package combinations. In any case, my answer stands: If you want to use Eager, this is how you go about it generally.

AVISHEK GARAIN · Accepted Answer · 2020-09-22 09:13:38Z

0

A tensor can be converted into a numpy array using following function of tensorflow:

import tensorflow as tf
tf.make_ndarray(
    tensor
)

For example:

# Tensor a has shape (2,3)
a = tf.constant([[1,2,3],[4,5,6]])
proto_tensor = tf.make_tensor_proto(a)  # convert `tensor a` to a proto tensor
tf.make_ndarray(proto_tensor) # output: array([[1, 2, 3],
#                                              [4, 5, 6]], dtype=int32)
# output has shape (2,3)

answered Sep 22, 2020 at 9:13

AVISHEK GARAIN

8557 silver badges6 bronze badges

3 Comments

arush1836 Over a year ago

tf.make_ndarray(tensor) throws this error AttributeError: 'Tensor' object has no attribute 'tensor_shape'

AVISHEK GARAIN Over a year ago

Check this post: stackoverflow.com/a/38666116/14191955

Allohvk Over a year ago

How does the above link help solve the problem which OP has?

arush1836 · Accepted Answer · 2020-09-28 11:24:17Z

0

Finally approach mentioned here worked for me with tensorflow-gpu==2.0.0 and keras==2.2.4

answered Sep 28, 2020 at 11:24

arush1836

1,5879 gold badges23 silver badges42 bronze badges

Collectives™ on Stack Overflow

How to convert Tensor into NumPy array

Option 1

Option 2

3 Answers 3

2 Comments

3 Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

Option 1

Option 2

3 Answers 3

2 Comments

3 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related