Python tensorflow.ifft2d() Examples

The following are 8 code examples of tensorflow.ifft2d(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow , or try the search function .
Example #1
Source File: layers.py    From neuron with GNU General Public License v3.0 6 votes vote down vote up 
def call(self, inputx):
        
        if not inputx.dtype in [tf.complex64, tf.complex128]:
            print('Warning: inputx is not complex. Converting.', file=sys.stderr)
        
            # if inputx is float, this will assume 0 imag channel
            inputx = tf.cast(inputx, tf.complex64)
        
        # get the right fft
        if self.ndims == 1:
            ifft = tf.ifft
        elif self.ndims == 2:
            ifft = tf.ifft2d
        else:
            ifft = tf.ifft3d

        perm_dims = [0, self.ndims + 1] + list(range(1, self.ndims + 1))
        invert_perm_ndims = [0] + list(range(2, self.ndims + 2)) + [1]
        
        perm_inputx = K.permute_dimensions(inputx, perm_dims)  # [batch_size, nb_features, *vol_size]
        ifft_inputx = ifft(perm_inputx)
        return K.permute_dimensions(ifft_inputx, invert_perm_ndims)
Example #2
Source File: scattering.py    From DeepLearningImplementations with MIT License 6 votes vote down vote up 
def compute_fft(x, direction="C2C", inverse=False):

    if direction == 'C2R':
        inverse = True

    x_shape = x.get_shape().as_list()
    h, w = x_shape[-2], x_shape[-3]

    x_complex = tf.complex(x[..., 0], x[..., 1])

    if direction == 'C2R':
        out = tf.real(tf.ifft2d(x_complex)) * h * w
        return out

    else:
        if inverse:
            out = stack_real_imag(tf.ifft2d(x_complex)) * h * w
        else:
            out = stack_real_imag(tf.fft2d(x_complex))
        return out
Example #3
Source File: models.py    From DeepLearningImplementations with MIT License 6 votes vote down vote up 
def compute_fft(x, direction="C2C", inverse=False):

    if direction == 'C2R':
        inverse = True

    x_shape = x.get_shape().as_list()
    h, w = x_shape[-2], x_shape[-3]

    x_complex = tf.complex(x[..., 0], x[..., 1])

    if direction == 'C2R':
        out = tf.real(tf.ifft2d(x_complex)) * h * w
        return out

    else:
        if inverse:
            out = stack_real_imag(tf.ifft2d(x_complex)) * h * w
        else:
            out = stack_real_imag(tf.fft2d(x_complex))
        return out
Example #4
Source File: ops.py    From tfdeploy with MIT License 5 votes vote down vote up 
def test_IFFT2D(self):
        # only defined for gpu
        if DEVICE == GPU:
            t = tf.ifft2d(self.random(3, 4, complex=True))
            self.check(t)
Example #5
Source File: fft_ops_test.py    From deep_image_model with Apache License 2.0 5 votes vote down vote up 
def _tfIFFTForRank(self, rank):
    if rank == 1:
      return tf.ifft
    elif rank == 2:
      return tf.ifft2d
    elif rank == 3:
      return tf.ifft3d
    else:
      raise ValueError("invalid rank")
Example #6
Source File: tfmri.py    From dl-cs with MIT License 5 votes vote down vote up 
def fft2c(im,
          data_format='channels_last',
          orthonorm=True,
          transpose=False,
          name='fft2c'):
    """Centered FFT2 on last two non-channel dimensions."""
    with tf.name_scope(name):
        im_out = im
        if data_format == 'channels_last':
            permute_orig = np.arange(len(im.shape))
            permute = permute_orig.copy()
            permute[-3] = permute_orig[-1]
            permute[-2:] = permute_orig[-3:-1]
            im_out = tf.transpose(im_out, permute)

        if orthonorm:
            fftscale = tf.sqrt(
                tf.cast(im_out.shape[-1], tf.float32) * tf.cast(
                    im_out.shape[-2], tf.float32))
        else:
            fftscale = 1.0
        fftscale = tf.cast(fftscale, dtype=tf.complex64)

        im_out = fftshift(im_out, axis=(-2, -1))
        if transpose:
            im_out = tf.ifft2d(im_out) * fftscale
        else:
            im_out = tf.fft2d(im_out) / fftscale
        im_out = fftshift(im_out, axis=(-2, -1))

        if data_format == 'channels_last':
            permute[-3:-1] = permute_orig[-2:]
            permute[-1] = permute_orig[-3]
            im_out = tf.transpose(im_out, permute)

    return im_out
Example #7
Source File: model.py    From DeepMRI with GNU General Public License v3.0 5 votes vote down vote up 
def dc(generated, X_k, mask):
    gene_complex = real2complex(generated)
    gene_complex = tf.transpose(gene_complex,[0, 3, 1, 2])
    mask = tf.transpose(mask,[0, 3, 1, 2])
    X_k = tf.transpose(X_k,[0, 3, 1, 2])
    gene_fft = tf.fft2d(gene_complex)
    out_fft = X_k + gene_fft * (1.0 - mask)
    output_complex = tf.ifft2d(out_fft)
    output_complex = tf.transpose(output_complex, [0, 2, 3, 1])
    output_real = tf.cast(tf.real(output_complex), dtype=tf.float32)
    output_imag = tf.cast(tf.imag(output_complex), dtype=tf.float32)
    output = tf.concat([output_real,output_imag], axis=-1)
    return output
Example #8
Source File: data.py    From DeepMRI with GNU General Public License v3.0 5 votes vote down vote up 
def setup_inputs(x, mask, batch_size):

    channel = x.shape[-1].value // 2
    mask = np.tile(mask, (channel, 1, 1))
    mask_tf = tf.cast(tf.constant(mask), tf.float32)
    mask_tf_c = tf.cast(mask_tf, tf.complex64)
    x_complex = real2complex(x)
    x_complex = tf.cast(x_complex, tf.complex64)
    x_complex = tf.transpose(x_complex, [2, 0, 1])
    kx = tf.fft2d(x_complex)
    kx_mask = kx * mask_tf_c
    x_u = tf.ifft2d(kx_mask)
    x_u = tf.transpose(x_u, [1, 2, 0])
    kx_mask = tf.transpose(kx_mask, [1, 2, 0])

    x_u_cat = complex2real(x_u)
    x_cat = tf.cast(x, tf.float32)
    mask_tf_c = tf.transpose(mask_tf_c, [1, 2, 0])

    features, labels, kx_mask, masks = tf.train.shuffle_batch([x_u_cat,x_cat, kx_mask, mask_tf_c],
                                                     batch_size=batch_size,
                                                     num_threads=64,
                                                     capacity=50,
                                                     min_after_dequeue=10)

    return features, labels, kx_mask, masks