test_mlp.py 文件源码

def run_conv_nnet1(use_gpu):
    if use_gpu:
        shared_fn = tcn.shared_constructor
    else:
        shared_fn = shared
    n_batch = 16
    n_kern = 20
    shape_img = (n_batch, 1, 32, 32)
    shape_kern = (n_kern, 1, 5, 5)
    n_train = 10
    if config.mode == 'DEBUG_MODE':
        n_train = 1

    logical_hid_shape = tcn.blas.GpuConv.logical_output_shape_2d(
        shape_img[2:], shape_kern[2:], 'valid')
    n_hid = n_kern * logical_hid_shape[0] * logical_hid_shape[1]
    n_out = 10

    w = shared_fn(0.01 * (my_rand(*shape_kern) - 0.5), 'w')
    b = shared_fn(my_zeros((n_kern,)), 'b')
    v = shared_fn(my_zeros((n_hid, n_out)), 'c')
    c = shared_fn(my_zeros(n_out), 'c')

    x = tensor.Tensor(dtype='float32', broadcastable=(0, 1, 0, 0))('x')
    y = tensor.fmatrix('y')
    lr = tensor.fscalar('lr')

    conv_op = conv.ConvOp(shape_img[2:], shape_kern[2:], n_kern, n_batch, 1, 1)

    hid = tensor.tanh(conv_op(x, w) + b.dimshuffle((0, 'x', 'x')))
    hid_flat = hid.reshape((n_batch, n_hid))
    out = tensor.tanh(tensor.dot(hid_flat, v) + c)
    loss = tensor.sum(0.5 * (out - y) ** 2 * lr)
    # 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 zip(params, gparams)])

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

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

    for i in xrange(n_train):
        rval = train(xval, yval, lr)
    # print 'training done'
    return rval