test_mlp.py 文件源码

def run_nnet(use_gpu, n_batch=60, n_in=1024, n_hid=2048, n_out=10,
             n_train=100):

    if config.mode == 'DEBUG_MODE':
        n_train = 1

    if use_gpu:
        w = tcn.shared_constructor(0.01 * (my_rand(n_in, n_hid) - 0.5), 'w')
        b = tcn.shared_constructor(my_zeros(n_hid), 'b')
        v = tcn.shared_constructor(my_zeros((n_hid, n_out)), 'c')
        c = tcn.shared_constructor(my_zeros(n_out), 'c')
    else:
        w = shared(0.01 * (my_rand(n_in, n_hid) - 0.5), 'w')
        b = shared(my_zeros(n_hid), 'b')
        v = shared(my_zeros((n_hid, n_out)), 'c')
        c = shared(my_zeros(n_out), 'c')

    x = tensor.fmatrix('x')
    y = tensor.fmatrix('y')
    lr = tensor.fscalar('lr')

    hid = tensor.tanh(tensor.dot(x, w) + b)
    out = tensor.tanh(tensor.dot(hid, v) + c)
    loss = tensor.sum(0.5 * (out - y) ** 2 * lr)
    if 0:
        print('loss type', loss.type)

    params = [w, b, v, c]
    gparams = tensor.grad(loss, params)

    mode = get_mode(use_gpu)

    # print 'building pfunc ...'
    train = pfunc([x, y, lr], [loss], mode=mode,
                  updates=[(p, p - g) for p, g in izip(params, gparams)])

    if 0:
        for i, n in enumerate(train.maker.fgraph.toposort()):
            print(i, n)

    xval = my_rand(n_batch, n_in)
    yval = my_rand(n_batch, n_out)
    lr = theano._asarray(0.01, dtype='float32')

    t0 = time.time()
    rval = []
    for i in xrange(n_train):
        rval.append(train(xval, yval, lr))
    dt = time.time() - t0

    return numpy.asarray(rval), dt