Skip to contents

The quadrant (i.e., branch) is chosen so that arctan2(x1, x2) is the signed angle in radians between the ray ending at the origin and passing through the point (1, 0), and the ray ending at the origin and passing through the point (x2, x1). (Note the role reversal: the "y-coordinate" is the first function parameter, the "x-coordinate" is the second.) By IEEE convention, this function is defined for x2 = +/-0 and for either or both of x1 and x2 = +/-inf.

Usage

op_arctan2(x1, x2)

Arguments

x1

First input tensor.

x2

Second input tensor.

Value

Tensor of angles in radians, in the range [-pi, pi].

Examples

Consider four points in different quadrants:

x <- op_array(c(-1, 1, 1, -1))
y <- op_array(c(-1, -1, 1, 1))
op_arctan2(y, x) * 180 / pi

## tf.Tensor([-135.  -45.   45.  135.], shape=(4), dtype=float32)

Note the order of the parameters. arctan2 is defined also when x2 = 0 and at several other points, obtaining values in the range [-pi, pi]:

op_arctan2(
    op_array(c(1, -1)),
    op_array(c(0, 0))
)

## tf.Tensor([ 1.5707964 -1.5707964], shape=(2), dtype=float32)

op_arctan2(
    op_array(c(0, 0, Inf)),
    op_array(c(+0, -0, Inf))
)

## tf.Tensor([0.        3.1415927 0.7853982], shape=(3), dtype=float32)

See also

Other numpy ops:
op_abs()
op_add()
op_all()
op_any()
op_append()
op_arange()
op_arccos()
op_arccosh()
op_arcsin()
op_arcsinh()
op_arctan()
op_arctanh()
op_argmax()
op_argmin()
op_argsort()
op_array()
op_average()
op_bincount()
op_broadcast_to()
op_ceil()
op_clip()
op_concatenate()
op_conj()
op_copy()
op_cos()
op_cosh()
op_count_nonzero()
op_cross()
op_cumprod()
op_cumsum()
op_diag()
op_diagonal()
op_diff()
op_digitize()
op_divide()
op_divide_no_nan()
op_dot()
op_einsum()
op_empty()
op_equal()
op_exp()
op_expand_dims()
op_expm1()
op_eye()
op_flip()
op_floor()
op_floor_divide()
op_full()
op_full_like()
op_get_item()
op_greater()
op_greater_equal()
op_hstack()
op_identity()
op_imag()
op_isclose()
op_isfinite()
op_isinf()
op_isnan()
op_less()
op_less_equal()
op_linspace()
op_log()
op_log10()
op_log1p()
op_log2()
op_logaddexp()
op_logical_and()
op_logical_not()
op_logical_or()
op_logical_xor()
op_logspace()
op_matmul()
op_max()
op_maximum()
op_mean()
op_median()
op_meshgrid()
op_min()
op_minimum()
op_mod()
op_moveaxis()
op_multiply()
op_nan_to_num()
op_ndim()
op_negative()
op_nonzero()
op_not_equal()
op_ones()
op_ones_like()
op_outer()
op_pad()
op_power()
op_prod()
op_quantile()
op_ravel()
op_real()
op_reciprocal()
op_repeat()
op_reshape()
op_roll()
op_round()
op_sign()
op_sin()
op_sinh()
op_size()
op_sort()
op_split()
op_sqrt()
op_square()
op_squeeze()
op_stack()
op_std()
op_subtract()
op_sum()
op_swapaxes()
op_take()
op_take_along_axis()
op_tan()
op_tanh()
op_tensordot()
op_tile()
op_trace()
op_transpose()
op_tri()
op_tril()
op_triu()
op_var()
op_vdot()
op_vstack()
op_where()
op_zeros()
op_zeros_like()

Other ops:
op_abs()
op_add()
op_all()
op_any()
op_append()
op_arange()
op_arccos()
op_arccosh()
op_arcsin()
op_arcsinh()
op_arctan()
op_arctanh()
op_argmax()
op_argmin()
op_argsort()
op_array()
op_average()
op_average_pool()
op_batch_normalization()
op_binary_crossentropy()
op_bincount()
op_broadcast_to()
op_cast()
op_categorical_crossentropy()
op_ceil()
op_cholesky()
op_clip()
op_concatenate()
op_cond()
op_conj()
op_conv()
op_conv_transpose()
op_convert_to_numpy()
op_convert_to_tensor()
op_copy()
op_cos()
op_cosh()
op_count_nonzero()
op_cross()
op_ctc_loss()
op_cumprod()
op_cumsum()
op_depthwise_conv()
op_det()
op_diag()
op_diagonal()
op_diff()
op_digitize()
op_divide()
op_divide_no_nan()
op_dot()
op_eig()
op_einsum()
op_elu()
op_empty()
op_equal()
op_erf()
op_erfinv()
op_exp()
op_expand_dims()
op_expm1()
op_extract_sequences()
op_eye()
op_fft()
op_fft2()
op_flip()
op_floor()
op_floor_divide()
op_fori_loop()
op_full()
op_full_like()
op_gelu()
op_get_item()
op_greater()
op_greater_equal()
op_hard_sigmoid()
op_hard_silu()
op_hstack()
op_identity()
op_imag()
op_image_affine_transform()
op_image_extract_patches()
op_image_map_coordinates()
op_image_pad()
op_image_resize()
op_in_top_k()
op_inv()
op_irfft()
op_is_tensor()
op_isclose()
op_isfinite()
op_isinf()
op_isnan()
op_istft()
op_leaky_relu()
op_less()
op_less_equal()
op_linspace()
op_log()
op_log10()
op_log1p()
op_log2()
op_log_sigmoid()
op_log_softmax()
op_logaddexp()
op_logical_and()
op_logical_not()
op_logical_or()
op_logical_xor()
op_logspace()
op_logsumexp()
op_lu_factor()
op_matmul()
op_max()
op_max_pool()
op_maximum()
op_mean()
op_median()
op_meshgrid()
op_min()
op_minimum()
op_mod()
op_moments()
op_moveaxis()
op_multi_hot()
op_multiply()
op_nan_to_num()
op_ndim()
op_negative()
op_nonzero()
op_norm()
op_normalize()
op_not_equal()
op_one_hot()
op_ones()
op_ones_like()
op_outer()
op_pad()
op_power()
op_prod()
op_qr()
op_quantile()
op_ravel()
op_real()
op_reciprocal()
op_relu()
op_relu6()
op_repeat()
op_reshape()
op_rfft()
op_roll()
op_round()
op_rsqrt()
op_scatter()
op_scatter_update()
op_segment_max()
op_segment_sum()
op_selu()
op_separable_conv()
op_shape()
op_sigmoid()
op_sign()
op_silu()
op_sin()
op_sinh()
op_size()
op_slice()
op_slice_update()
op_softmax()
op_softplus()
op_softsign()
op_solve()
op_solve_triangular()
op_sort()
op_sparse_categorical_crossentropy()
op_split()
op_sqrt()
op_square()
op_squeeze()
op_stack()
op_std()
op_stft()
op_stop_gradient()
op_subtract()
op_sum()
op_svd()
op_swapaxes()
op_take()
op_take_along_axis()
op_tan()
op_tanh()
op_tensordot()
op_tile()
op_top_k()
op_trace()
op_transpose()
op_tri()
op_tril()
op_triu()
op_unstack()
op_var()
op_vdot()
op_vectorized_map()
op_vstack()
op_where()
op_while_loop()
op_zeros()
op_zeros_like()