CODEWITHSUNDEEP
tensorflow
mcExchange
mcExchange

Reputation: 6497

Tensorflow: Create a batch from a list of image tensors

I have a function get_image(...) that performs preprocessing on my input images. I gather all images that belong to the same batch in a list like this:

batch = [get_image(file_path) for file_path in batch_files]

Now I want to convert this list into one single tensor with the first dimension being the batch size dimension, such that I could feed it to the input placeholder of my network.

_ = self.sess.run([loss],feed_dict={ input_placeholder: batch })

Any idea how I could do that?

            batch_concat = tf.placeholder(shape=[None] + self.image_shape, dtype=tf.float32) 
            for i in xrange(0,self.batch_size):
                if i == 0:
                    tmp_batch = tf.expand_dims(batch[i], 0)
                    batch_concat = tmp_batch
                else:
                    tmp_batch = tf.expand_dims(batch[i], 0)                        
                    batch_concat = tf.concat(0, [batch_concat, tmp_batch])

When I try to concatenate all tensors, I get the following error:

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

So maybe it would be enough to convert the tensor back into a numpy array before feeding it to the network?

Upvotes: 2

Views: 8051

Answers (3)

rlys
rlys

Reputation: 480

The issue here is using a tensor as a value in feed_dict. Instead of feeding batch as the value for input_placeholder, why don't you use batch instead of input_placeholder, assuming batch is your batched tensor?

So, instead of:

input_placeholder = tf.Placeholder(tf.int32)
loss = some_function(input_placeholder)
sess.run(loss, feed_dict={input_placeholder: batch})

Do:

loss = some_function(batch)
sess.run(batch)

Upvotes: 0

troutinator
troutinator

Reputation: 1198

In the TF r1.1 pack has been replaced with tf.stack

Upvotes: 1

Leon Wolf
Leon Wolf

Reputation: 119

You can use tf.pack to pack a list of tensors into a batch.

image_list = [get_image(file_path) for file_path in batch_files]
image_batch = tf.pack(image_list)

You can also use tf.concat to concatenate the list along the first dimension and reshape it.

Upvotes: 0

Related Questions