utils.py 文件源码

def build_vae_loss(input_var, l_z_mu, l_z_ls, l_x_mu_list, l_x_ls_list, l_x_list, l_x,
        deterministic, binary, L):
    layer_outputs = nn.layers.get_output([l_z_mu, l_z_ls] + l_x_mu_list + l_x_ls_list
            + l_x_list + [l_x], deterministic=deterministic)
    z_mu =  layer_outputs[0]
    z_ls =  layer_outputs[1]
    x_mu =  [] if binary else layer_outputs[2:2+L]
    x_ls =  [] if binary else layer_outputs[2+L:2+2*L]
    x_list =  layer_outputs[2:2+L] if binary else layer_outputs[2+2*L:2+3*L]
    x = layer_outputs[-1]
    kl_div = 0.5 * T.sum(1 + 2*z_ls - T.sqr(z_mu) - T.exp(2 * z_ls))
    if binary:
        logpxz = sum(nn.objectives.binary_crossentropy(x, input_var).sum()
                for x in x_list) * (-1./L)
        prediction = x_list[0] if deterministic else x
    else:
        logpxz = sum(log_likelihood(input_var.flatten(2), mu, ls)
            for mu, ls in zip(x_mu, x_ls))/L
        prediction = x_mu[0] if deterministic else T.sum(x_mu, axis=0)/L
    loss = -1 * (logpxz + kl_div)
    return loss, prediction