CODEWITHSUNDEEP
tensorflowdimensions
bugler
bugler

Reputation: 41

Tensorflow. Difference between [batch_size, 1] & [batch_size]

In tensorflow tutorial for word embedding one finds:

# Placeholders for inputs
train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])

What is possibly the difference between these two placeholders. Aren't they both a int32 column vector of size batch_size?

Thanks.

Upvotes: 2

Views: 488

Answers (2)

Liwei
Liwei

Reputation: 481

train_inputs is a row vector while train_labels is a column vector.

Upvotes: 0

bugler
bugler

Reputation: 41

I found the answer with a little debugging.

[batch_size] = [ 0, 2, ...]
[batch_size, 1] = [ [0], [2], ...]

Though still don't know why using the second form.

Upvotes: 2

Related Questions