Make a context manager which enables back-propagation.
When you want to enable back-propagation in
no_backprop_mode(), call this method. A
Variablecreated in this context always has a computational graph unless overridden by deeper contexts. If you call this method outside of
no_backprop_mode()context, it changes nothing.
In the following example,
yhas a computational graph and calling
ywill compute and accumulate the gradients of the variables in the graph, in this case only
>>> x = chainer.Variable(np.array([1,], 'f')) >>> with chainer.no_backprop_mode(): ... with chainer.force_backprop_mode(): ... y = x + 1 >>> y.backward() >>> x.grad array([ 1.], dtype=float32)
no_backprop_mode()for details on disabled back-propagation mode.