test_opt.py 文件源码

def test_local_IncSubtensor_serialize():
    d = numpy.random.normal(0, 0.01, size=(100, 100))
    d = d.astype(theano.config.floatX)

    W = theano.shared(d, name='W')
    i = T.vector('i', dtype='int64')
    j = T.vector('j', dtype='int64')
    t = T.scalar('t')
    if theano.tensor.subtensor.inplace_increment:
        y = (W[i] + W[j] + W[1] + W[i, j]).sum()
    else:
        y = (W[i] + W[j] + W[1]).sum()
    cost = T.sqr(t - y)
    dW = theano.grad(cost, W)
    mode = theano.compile.mode.get_default_mode().excluding('fusion')
    mode = mode.including("local_IncSubtensor_serialize")
    f = theano.function([i, j, t], updates=[(W, W - 0.01 * dW)], mode=mode)
    topo = f.maker.fgraph.toposort()
    adds = [n for n in topo if isinstance(n.op, T.Elemwise) and
            isinstance(n.op.scalar_op, theano.scalar.Add)]
    for a in adds:
        assert not any([inp.owner and
                        isinstance(inp.owner.op,
                                   (tensor.IncSubtensor,
                                    tensor.AdvancedIncSubtensor,
                                    tensor.AdvancedIncSubtensor1))
                        for inp in a.inputs])

    # Now test that the stack trace is copied over properly,
    # if we return the gradients. We need to use same mode as before.
    f = theano.function([i, j, t], dW, mode=mode)
    assert check_stack_trace(f, ops_to_check=[
        tensor.IncSubtensor, tensor.AdvancedIncSubtensor,
        tensor.AdvancedIncSubtensor1])