View source on GitHub |
A block of reversible residual layers.
tf.contrib.layers.rev_block(
x1, x2, f, g, num_layers=1, f_side_input=None, g_side_input=None,
is_training=True
)
A reversible residual layer is defined as:
y1 = x1 + f(x2, f_side_input)
y2 = x2 + g(y1, g_side_input)
A reversible residual block, defined here, is a series of reversible residual layers.
Limitations:
- f and g must not close over any Tensors; all side inputs to f and g should be passed in with f_side_input and g_side_input which will be forwarded to f and g.
- f and g must not change the dimensionality of their inputs in order for the addition in the equations above to work.
Args | |
---|---|
x1
|
a float Tensor. |
x2
|
a float Tensor. |
f
|
a function, (Tensor) -> (Tensor) (or list of such of length num_layers). Should not change the shape of the Tensor. Can make calls to get_variable. See f_side_input if there are side inputs. |
g
|
a function, (Tensor) -> (Tensor) (or list of such of length num_layers). Should not change the shape of the Tensor. Can make calls to get_variable. See g_side_input if there are side inputs. |
num_layers
|
int, number of reversible residual layers. Each layer will apply f and g according to the equations above, with new variables in each layer. |
f_side_input
|
list of Tensors, side input to f. If not None, signature of f
should be (Tensor, list |
g_side_input
|
list of Tensors, side input to g. If not None, signature of g
should be (Tensor, list |
is_training
|
bool, whether to actually use the efficient backprop codepath. |
Returns | |
---|---|
y1, y2: tuple of float Tensors. |