# What is the difference between float64 and double in TensorFlow?

In storing floating point values both overflow and underflow problems cause loss of data. In machine learning tasks underflow is a common problem. I wanted to know if double is better than float64 in TensorFlow or not and if there is any difference between them?

Taking a look at tensorflow's dtypes.py, there's this line:
double = float64

So double is exactly the same at float64.
• Might be worth noting that in general (including many C libraries unrelated to question), double tracks what the machine calls double precision (so may depend on processor or OS). Whilst float64 is fixed. There may be a good reason why TensorFlow takes a shortcut here, such as it only works on machines where the two are the same in any case. – Neil Slater Nov 30 '17 at 13:52