TypeError: ('An update must have the same type as the original shared variable (shared_var=<TensorType(float32, matrix)>, shared_var.type=TensorType(float32, matrix), update_val=Elemwise{add,no_inplace}.0, update_val.type=TensorType(float64, matrix)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')

[chandanmishra-03]

def adam(lr, tparams, grads, inp, cost):
gshared = [theano.shared(p.get_value() * 0., name='%s_grad'%k) for k, p in tparams.iteritems()]
gsup = [(gs, g) for gs, g in zip(gshared, grads)]

f_grad_shared = theano.function(inp, cost, updates=gsup, profile=False)

b1 = 0.1
b2 = 0.001
e = 1e-8

updates = []

i = theano.shared(numpy.float32(0.))
i_t = i + 1.
fix1 = 1. - b1**(i_t)
fix2 = 1. - b2**(i_t)
lr_t = lr * (tensor.sqrt(fix2) / fix1)

for p, g in zip(tparams.values(), gshared):
    m = theano.shared(p.get_value() * 0.)
    v = theano.shared(p.get_value() * 0.)
    m_t = (b1 * g) + ((1. - b1) * m)
    v_t = (b2 * tensor.sqr(g)) + ((1. - b2) * v)
    g_t = m_t / (tensor.sqrt(v_t) + e)
    p_t = p - (lr_t * g_t)
    updates.append((m, m_t))
    updates.append((v, v_t))
    updates.append((p, p_t))
updates.append((i, i_t))


f_update = theano.function([lr], [], updates=updates, on_unused_input='raise', profile=False)

return f_grad_shared, f_update

getting the error in line "f_update = theano.function([lr], [], updates=updates, on_unused_input='raise', profile=False)". Help me to fix it.

[shiv6891]

Hi, anyone got the solution for this? Kindly help.

[bchen1116]

You can set in your os environment
os.environ["THEANO_FLAGS"] = "floatX=float32"

[shiv6891]

Thanks for the response @bchen1116 , this solves it.