Python ndarray.ones函数代码示例

 def check_binary_func(x, y):
     f_add      = lambda x, y: x+y
     f_add_grad = lambda x, y: [nd.ones(x.shape), nd.ones(y.shape)]
     autograd_assert(x, y, func=f_add, grad_func=f_add_grad)
     f_mul      = lambda x, y: x*y
     f_mul_grad = lambda x, y: [y, x]
     autograd_assert(x, y, func=f_mul, grad_func=f_mul_grad)
     f_compose  = lambda x, y: x+x*y
     f_compose_grad = lambda x, y: [nd.ones(x.shape) + y, x]
     autograd_assert(x, y, func=f_compose, grad_func=f_compose_grad)

def test_binary_func():
    x = nd.uniform(shape=(4, 5))
    y = nd.uniform(shape=(4, 5))
    f_add      = lambda x, y: x+y
    f_add_grad = lambda x, y: [nd.ones(x.shape), nd.ones(y.shape)]
    autograd_assert(x, y, func=f_add, grad_func=f_add_grad)
    f_mul      = lambda x, y: x*y
    f_mul_grad = lambda x, y: [y, x]
    autograd_assert(x, y, func=f_mul, grad_func=f_mul_grad)
    f_compose  = lambda x, y: x+x*y
    f_compose_grad = lambda x, y: [nd.ones(x.shape) + y, x]
    autograd_assert(x, y, func=f_compose, grad_func=f_compose_grad)

def test_argnum():
    def f_with_mode(a, b, mode):
        if mode:
            return a+b
        else:
            return a*b

    a = nd.uniform(shape=(3, 2))
    b = nd.uniform(shape=(3, 2))
    f_add_grad = lambda x, y, mode: [nd.ones(x.shape), nd.ones(y.shape)]
    f_mul_grad = lambda x, y, mode: [y, x]
    autograd_assert(a, b, True,
        argnum=[0, 1], func=f_with_mode, grad_func=f_add_grad)
    autograd_assert(a, b, False,
        argnum=[0, 1], func=f_with_mode, grad_func=f_mul_grad)

def test_detach_updated_grad():
    x = nd.ones((2, 2))
    dx = nd.zeros_like(x)
    y = nd.ones_like(x)
    dy = nd.zeros_like(x)
    mark_variables([x, y], [dx, dy])
    assert x._fresh_grad == False
    assert y._fresh_grad == False

    with train_section():
        x2 = x + 2
        y2  = x2 + y
        y2.backward()
    assert (dx.asnumpy() == 1).all()
    assert x._fresh_grad == True
    assert y._fresh_grad == True

    dx[:] = 0
    x._fresh_grad = False
    y._fresh_grad = False
    assert x._fresh_grad == False
    assert y._fresh_grad == False
    with train_section():
        x2 = x + 2
        x2 = x2.detach()
        y2  = x2 + y
        y2.backward()
    assert (dx.asnumpy() == 0).all()
    assert y._fresh_grad == True
    assert x._fresh_grad == False

 def gan_loss(input,target_is_real):
     if target_is_real:
         target = nd.ones(input.shape,ctx=input.context)
     else:
         target = nd.zeros(input.shape, ctx=input.context)
     #mse loss for lsgan
     e = ((input - target) ** 2).mean(axis=0, exclude=True)
     return e

def bilinear(x, W, y, input_size, seq_len, batch_size, num_outputs=1, bias_x=False, bias_y=False):
    """Do xWy

    Parameters
    ----------
    x : NDArray
        (input_size x seq_len) x batch_size
    W : NDArray
        (num_outputs x ny) x nx
    y : NDArray
        (input_size x seq_len) x batch_size
    input_size : int
        input dimension
    seq_len : int
        sequence length
    batch_size : int
        batch size
    num_outputs : int
        number of outputs
    bias_x : bool
        whether concat bias vector to input x
    bias_y : bool
        whether concat bias vector to input y

    Returns
    -------
    output : NDArray
        [seq_len_y x seq_len_x if output_size == 1 else seq_len_y x num_outputs x seq_len_x] x batch_size
    """
    if bias_x:
        x = nd.concat(x, nd.ones((1, seq_len, batch_size)), dim=0)
    if bias_y:
        y = nd.concat(y, nd.ones((1, seq_len, batch_size)), dim=0)

    nx, ny = input_size + bias_x, input_size + bias_y
    # W: (num_outputs x ny) x nx
    lin = nd.dot(W, x)
    if num_outputs > 1:
        lin = reshape_fortran(lin, (ny, num_outputs * seq_len, batch_size))
    y = y.transpose([2, 1, 0])  # May cause performance issues
    lin = lin.transpose([2, 1, 0])
    blin = nd.batch_dot(lin, y, transpose_b=True)
    blin = blin.transpose([2, 1, 0])
    if num_outputs > 1:
        blin = reshape_fortran(blin, (seq_len, num_outputs, seq_len, batch_size))
    return blin

def test_training():
    x = nd.ones((10, 10))
    with train_section():
        y = nd.Dropout(x, p=0.5)
        assert not (y.asnumpy() == x.asnumpy()).all()
        with test_section():
            y = nd.Dropout(x, p=0.5)
            assert (y.asnumpy() == x.asnumpy()).all()

def test_training():
    x = nd.ones((10, 10))
    with record():
        y = nd.Dropout(x, p=0.5)
        assert not (y.asnumpy() == x.asnumpy()).all()
        with pause():
            y = nd.Dropout(x, p=0.5)
            assert (y.asnumpy() == x.asnumpy()).all()

 def forward(self, x):
     if  isinstance(x, np.ndarray):
         x = nd.array(x)
     if self._max_len > x.size:
         pad = nd.ones((self._max_len - x.size,)) * self._fill_value
         x = nd.concat(x, pad, dim=0)
     elif self._max_len < x.size:
         x = x[:self._max_len]
     return x

def dumpR(data_set, mx_model, batch_size, name='', data_extra = None, label_shape = None):
  print('dump verification embedding..')
  data_list = data_set[0]
  issame_list = data_set[1]
  model = mx_model
  embeddings_list = []
  if data_extra is not None:
    _data_extra = nd.array(data_extra)
  time_consumed = 0.0
  if label_shape is None:
    _label = nd.ones( (batch_size,) )
  else:
    _label = nd.ones( label_shape )
  for i in xrange( len(data_list) ):
    data = data_list[i]
    embeddings = None
    ba = 0
    while ba<data.shape[0]:
      bb = min(ba+batch_size, data.shape[0])
      count = bb-ba
      _data = nd.slice_axis(data, axis=0, begin=bb-batch_size, end=bb)
      #print(_data.shape, _label.shape)
      time0 = datetime.datetime.now()
      if data_extra is None:
        db = mx.io.DataBatch(data=(_data,), label=(_label,))
      else:
        db = mx.io.DataBatch(data=(_data,_data_extra), label=(_label,))
      model.forward(db, is_train=False)
      net_out = model.get_outputs()
      _embeddings = net_out[0].asnumpy()
      time_now = datetime.datetime.now()
      diff = time_now - time0
      time_consumed+=diff.total_seconds()
      if embeddings is None:
        embeddings = np.zeros( (data.shape[0], _embeddings.shape[1]) )
      embeddings[ba:bb,:] = _embeddings[(batch_size-count):,:]
      ba = bb
    embeddings_list.append(embeddings)
  embeddings = embeddings_list[0] + embeddings_list[1]
  embeddings = sklearn.preprocessing.normalize(embeddings)
  actual_issame = np.asarray(issame_list)
  outname = os.path.join('temp.bin')
  with open(outname, 'wb') as f:
    pickle.dump((embeddings, issame_list), f, protocol=pickle.HIGHEST_PROTOCOL)

 def check_unary_func(x):
     f_exp         = lambda x: nd.exp(x)
     f_exp_grad    = lambda x: [nd.exp(x)]
     autograd_assert(x, func=f_exp, grad_func=f_exp_grad)
     f_half        = lambda x: x/2
     f_half_grad   = lambda x: [nd.ones(x.shape) * 0.5]
     autograd_assert(x, func=f_half, grad_func=f_half_grad)
     f_square      = lambda x: x**2
     f_square_grad = lambda x: [2*x]
     autograd_assert(x, func=f_square, grad_func=f_square_grad)

def test_unary_func():
    x = nd.uniform(shape=(4, 5))
    f_exp         = lambda x: nd.exp(x)
    f_exp_grad    = lambda x: [nd.exp(x)]
    autograd_assert(x, func=f_exp, grad_func=f_exp_grad)
    f_half        = lambda x: x/2
    f_half_grad   = lambda x: [nd.ones(x.shape) * 0.5]
    autograd_assert(x, func=f_half, grad_func=f_half_grad)
    f_square      = lambda x: x**2
    f_square_grad = lambda x: [2*x]
    autograd_assert(x, func=f_square, grad_func=f_square_grad)

def test_module_input_grads():
    a = mx.sym.Variable('a', __layout__='NC')
    b = mx.sym.Variable('b', __layout__='NC')
    c = mx.sym.Variable('c', __layout__='NC')

    c = a + 2 * b + 3 * c
    net = mx.mod.Module(c, data_names=['b', 'c', 'a'], label_names=None,
                        context=[mx.cpu(0), mx.cpu(1)])
    net.bind(data_shapes=[['b', (5, 5)], ['c', (5, 5)], ['a', (5, 5)]],
             label_shapes=None, inputs_need_grad=True)
    net.init_params()

    net.forward(data_batch=mx.io.DataBatch(data=[nd.ones((5, 5)),
                                                 nd.ones((5, 5)),
                                                 nd.ones((5, 5))]))
    net.backward(out_grads=[nd.ones((5, 5))])
    input_grads = net.get_input_grads()
    b_grad = input_grads[0].asnumpy()
    c_grad = input_grads[1].asnumpy()
    a_grad = input_grads[2].asnumpy()
    assert np.all(a_grad == 1), a_grad
    assert np.all(b_grad == 2), b_grad
    assert np.all(c_grad == 3), c_grad

def test_out_grads():
    x = nd.ones((3, 5))
    dx = nd.zeros_like(x)
    mark_variables([x], [dx])
    da = None
    db = nd.array([1,2,3,4,5])
    dc = nd.array([5,4,3,2,1])

    with train_section():
        a, b, c = nd.split(x, axis=0, num_outputs=3, squeeze_axis=True)
        backward([a, b, c], [da, db, dc])

    assert (dx.asnumpy() == np.array(
        [[1,1,1,1,1],
         [1,2,3,4,5],
         [5,4,3,2,1]])).all()

    def lfw_test(nbatch):
      print('testing lfw..')
      embeddings_list = []
      for i in xrange( len(lfw_data_list) ):
        lfw_data = lfw_data_list[i]
        embeddings = None
        ba = 0
        while ba<lfw_data.shape[0]:
          bb = min(ba+args.batch_size, lfw_data.shape[0])
          _data = nd.slice_axis(lfw_data, axis=0, begin=ba, end=bb)
          _label = nd.ones( (bb-ba,) )
          db = mx.io.DataBatch(data=(_data,), label=(_label,))
          model.forward(db, is_train=False)
          net_out = model.get_outputs()
          _embeddings = net_out[0].asnumpy()
          if embeddings is None:
            embeddings = np.zeros( (lfw_data.shape[0], _embeddings.shape[1]) )
          embeddings[ba:bb,:] = _embeddings
          ba = bb
        embeddings_list.append(embeddings)

      acc_list = []
      embeddings = embeddings_list[0]
      _, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, issame_list, nrof_folds=10)
      acc_list.append(np.mean(accuracy))
      print('[%d]Accuracy: %1.3f+-%1.3f' % (nbatch, np.mean(accuracy), np.std(accuracy)))
      print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
      embeddings = np.concatenate(embeddings_list, axis=1)
      embeddings = sklearn.preprocessing.normalize(embeddings)
      print(embeddings.shape)
      _, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, issame_list, nrof_folds=10)
      acc_list.append(np.mean(accuracy))
      print('[%d]Accuracy-Flip: %1.3f+-%1.3f' % (nbatch, np.mean(accuracy), np.std(accuracy)))
      print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
      pca = PCA(n_components=128)
      embeddings = pca.fit_transform(embeddings)
      embeddings = sklearn.preprocessing.normalize(embeddings)
      print(embeddings.shape)
      _, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, issame_list, nrof_folds=10)
      acc_list.append(np.mean(accuracy))
      print('[%d]Accuracy-PCA: %1.3f+-%1.3f' % (nbatch, np.mean(accuracy), np.std(accuracy)))
      print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
      return max(*acc_list)