Python sugartensor.sg_intx方法代码示例

# 需要导入模块: import sugartensor [as 别名]
# 或者: from sugartensor import sg_intx [as 别名]
def sg_ctc(tensor, opt):
    r"""Computes the CTC (Connectionist Temporal Classification) Loss between `tensor` and `target`.

    Args:
      tensor: A 3-D `float Tensor`.
      opt:
        target: A `Tensor` with the same length in the first dimension as the `tensor`. Labels. ( Dense tensor )
        name: A `string`. A name to display in the tensor board web UI.

    Returns:
      A 1-D `Tensor` with the same length in the first dimension of the `tensor`.

    For example,

    ```
    tensor = [[[2., -1., 3.], [3., 1., -2.]], [[1., -1., 2.], [3., 1., -2.]]]
    target = [[2., 1.], [2., 3.]]
    tensor.sg_ctc(target=target) => [ 4.45940781  2.43091154]
    ```
    """
    assert opt.target is not None, 'target is mandatory.'

    # default sequence length
    shape = tf.shape(tensor)
    opt += tf.sg_opt(seq_len=tf.ones((shape[0],), dtype=tf.sg_intx) * shape[1], merge=True)

    # ctc loss
    out = tf.nn.ctc_loss(opt.target.sg_to_sparse(), tensor, opt.seq_len,
                         ctc_merge_repeated=opt.merge, time_major=False)
    out = tf.identity(out, 'ctc')

    # add summary
    tf.sg_summary_loss(out, name=opt.name)

    return out 

# 需要导入模块: import sugartensor [as 别名]
# 或者: from sugartensor import sg_intx [as 别名]
def sg_int(tensor, opt):
    r"""Casts a tensor to intx.
    
    See `tf.cast()` in tensorflow.

    Args:
      tensor: A `Tensor` or `SparseTensor` (automatically given by chain).
      opt:
        name: If provided, it replaces current tensor's name.

    Returns:
      A `Tensor` or `SparseTensor` with same shape as `tensor`.
    """
    return tf.cast(tensor, tf.sg_intx, name=opt.name) 

# 需要导入模块: import sugartensor [as 别名]
# 或者: from sugartensor import sg_intx [as 别名]
def __init__(self, batch_size=16, set_name='train'):

        # load meta file
        label, mfcc_file = [], []
        with open(_data_path + 'preprocess/meta/%s.csv' % set_name) as csv_file:
            reader = csv.reader(csv_file, delimiter=',')
            for row in reader:
                # mfcc file
                mfcc_file.append(_data_path + 'preprocess/mfcc/' + row[0] + '.npy')
                # label info ( convert to string object for variable-length support )
                label.append(np.asarray(row[1:], dtype=np.int).tostring())

        # to constant tensor
        label_t = tf.convert_to_tensor(label)
        mfcc_file_t = tf.convert_to_tensor(mfcc_file)

        # create queue from constant tensor
        label_q, mfcc_file_q \
            = tf.train.slice_input_producer([label_t, mfcc_file_t], shuffle=True)

        # create label, mfcc queue
        label_q, mfcc_q = _load_mfcc(source=[label_q, mfcc_file_q],
                                     dtypes=[tf.sg_intx, tf.sg_floatx],
                                     capacity=256, num_threads=64)

        # create batch queue with dynamic pad
        batch_queue = tf.train.batch([label_q, mfcc_q], batch_size,
                                     shapes=[(None,), (20, None)],
                                     num_threads=64, capacity=batch_size*32,
                                     dynamic_pad=True)

        # split data
        self.label, self.mfcc = batch_queue
        # batch * time * dim
        self.mfcc = self.mfcc.sg_transpose(perm=[0, 2, 1])
        # calc total batch count
        self.num_batch = len(label) // batch_size

        # print info
        tf.sg_info('%s set loaded.(total data=%d, total batch=%d)'
                   % (set_name.upper(), len(label), self.num_batch))