我如何使用经过mnist训练的模型来预测图像

Question

I'm new to Tensorflow. I've done MNIST training by this example

steps = 5000

with tf.Session() as sess:

    sess.run(init)

    for i in range(steps):

       batch_x , batch_y = mnist.train.next_batch(50)

       sess.run(train,feed_dict={x:batch_x,y_true:batch_y,hold_prob:0.5})

       # PRINT OUT A MESSAGE EVERY 100 STEPS
       if i%100 == 0:

          print('Currently on step {}'.format(i))
          print('Accuracy is:')
          # Test the Train Model
          matches = tf.equal(tf.argmax(y_pred,1),tf.argmax(y_true,1))

          acc = tf.reduce_mean(tf.cast(matches,tf.float32))

          print(sess.run(acc,feed_dict=
              {x:mnist.test.images,y_true:mnist.test.labels,hold_prob:1.0}))
          print('\n')

now I want to do prediction by this model. I open and process the image with these lines of code.

 image = cv2.imread("Untitled.jpg")
 image = np.multiply(image, 1.0/255.0)
 images=tf.reshape(image,[-1,28,28,1])

when I use this:

   feed_dict1 = {x: images}
   classification = sess.run(y_pred, feed_dict1)
   print (classification)

It returns this error.

TypeError: The value of a feed cannot be a tf.Tensor object. Acceptable feed values include Python scalars, strings, lists, numpy ndarrays, or TensorHandles.

Answer 1

You try to feed into your placeholder the tf-object:

images = tf.reshape(image,[-1,28,28,1])

but you cannot do that since placeholder expects number for example np.array . So use numpy.reshape instead of tf.reshape . Second one you can use inside of your session. For example you can feed flat arrays into placeholder and then create a node inside of your session that reshape this array into 2D matrix.