[python] How to convert numpy arrays to standard TensorFlow format?

I have two numpy arrays:

  • One that contains captcha images
  • Another that contains the corresponding labels (in one-hot vector format)

I want to load these into TensorFlow so I can classify them using a neural network. How can this be done?

What shape do the numpy arrays need to have?

Additional Info - My images are 60 (height) by 160 (width) pixels each and each of them have 5 alphanumeric characters. Here is a sample image:

sample image.

Each label is a 5 by 62 array.

This question is related to python numpy machine-learning tensorflow

The answer is

You can use tf.convert_to_tensor():

import tensorflow as tf
import numpy as np

data = [[1,2,3],[4,5,6]]
data_np = np.asarray(data, np.float32)

data_tf = tf.convert_to_tensor(data_np, np.float32)

sess = tf.InteractiveSession()  


Here's a link to the documentation for this method:


Similar questions with python tag:

Similar questions with numpy tag:

Similar questions with machine-learning tag:

Similar questions with tensorflow tag: