Question

有没有办法将密集张量转换为稀疏张量？显然，Tensorflow的Estimator.fit不接受SparseTensors作为标签。我想将SparseTensors传递给Tensorflow的Estimator.fit的一个原因是能够使用tensorflow ctc_loss。这是代码：

import dataset_utils
import tensorflow as tf
import numpy as np

from tensorflow.contrib import grid_rnn, learn, layers, framework

def grid_rnn_fn(features, labels, mode):
    input_layer = tf.reshape(features["x"], [-1, 48, 1596])
    indices = tf.where(tf.not_equal(labels, tf.constant(0, dtype=tf.int32)))
    values = tf.gather_nd(labels, indices)
    sparse_labels = tf.SparseTensor(indices, values, dense_shape=tf.shape(labels, out_type=tf.int64))

    cell_fw = grid_rnn.Grid2LSTMCell(num_units=128)
    cell_bw = grid_rnn.Grid2LSTMCell(num_units=128)
    bidirectional_grid_rnn = tf.nn.bidirectional_dynamic_rnn(cell_fw, cell_bw, input_layer, dtype=tf.float32)
    outputs = tf.reshape(bidirectional_grid_rnn[0], [-1, 256])

    W = tf.Variable(tf.truncated_normal([256,
                                     80],
                                    stddev=0.1, dtype=tf.float32), name='W')
    b = tf.Variable(tf.constant(0., dtype=tf.float32, shape=[80], name='b'))

    logits = tf.matmul(outputs, W) + b
    logits = tf.reshape(logits, [tf.shape(input_layer)[0], -1, 80])
    logits = tf.transpose(logits, (1, 0, 2))

    loss = None
    train_op = None

    if mode != learn.ModeKeys.INFER:
        #Error occurs here
        loss = tf.nn.ctc_loss(inputs=logits, labels=sparse_labels, sequence_length=320)

    ... # returning ModelFnOps

def main(_):
    image_paths, labels = dataset_utils.read_dataset_list('../test/dummy_labels_file.txt')
    data_dir = "../test/dummy_data/"
    images = dataset_utils.read_images(data_dir=data_dir, image_paths=image_paths, image_extension='png')
    print('Done reading images')
    images = dataset_utils.resize(images, (1596, 48))
    images = dataset_utils.transpose(images)
    labels = dataset_utils.encode(labels)
    x_train, x_test, y_train, y_test = dataset_utils.split(features=images, test_size=0.5, labels=labels)

    train_input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"x": np.array(x_train)},
        y=np.array(y_train),
        num_epochs=1,
        shuffle=True,
        batch_size=1
    )

    classifier = learn.Estimator(model_fn=grid_rnn_fn, model_dir="/tmp/grid_rnn_ocr_model")
    classifier.fit(input_fn=train_input_fn)

更新：

事实证明，here的这个解决方案将密集张量转换为稀疏张量：

indices = tf.where(tf.not_equal(labels, tf.constant(0, dtype=tf.int32)))
values = tf.gather_nd(labels, indices)
sparse_labels = tf.SparseTensor(indices, values, dense_shape=tf.shape(labels, out_type=tf.int64))

但是，我遇到ctc_loss现在引发的这个错误：

ValueError: Shape must be rank 1 but is rank 0 for 'CTCLoss' (op: 'CTCLoss') with input shapes: [?,?,80], [?,2], [?], [].

我有这个代码将密集标签转换为稀疏标签：

def convert_to_sparse(labels, dtype=np.int32):
    indices = []
    values = []

    for n, seq in enumerate(labels):
        indices.extend(zip([n] * len(seq), range(len(seq))))
        values.extend(seq)

    indices = np.asarray(indices, dtype=dtype)
    values = np.asarray(values, dtype=dtype)
    shape = np.asarray([len(labels), np.asarray(indices).max(0)[1] + 1], dtype=dtype)

    return indices, values, shape

我将y_train转换为稀疏标签，并将值放在SparseTensor内：

sparse_y_train = convert_to_sparse(y_train)
print(tf.SparseTensor(
    indices=sparse_y_train[0],
    values=sparse_y_train[1],
    dense_shape=sparse_y_train
))

并将其与grid_rnn_fn中创建的SparseTensor进行比较：

indices = tf.where(tf.not_equal(labels, tf.constant(0, dtype=tf.int32)))
values = tf.gather_nd(labels, indices)
sparse_labels = tf.SparseTensor(indices, values, dense_shape=tf.shape(labels, out_type=tf.int64))

这是我得到的：

sparse_y_train：

SparseTensor(indices=Tensor("SparseTensor/indices:0", shape=(33, 2), dtype=int64), values=Tensor("SparseTensor/values:0", shape=(33,), dtype=int32), dense_shape=Tensor("SparseTensor/dense_shape:0", shape=(2,), dtype=int64))

sparse_labels：

SparseTensor(indices=Tensor("Where:0", shape=(?, 2), dtype=int64), values=Tensor("GatherNd:0", shape=(?,), dtype=int32), dense_shape=Tensor("Shape:0", shape=(2,), dtype=int64))

这让我觉得ctc_loss似乎无法处理SparseTensors作为动态形状的标签。

Answer 1

是。可以将张量转换为稀疏张量并返回：

让sparse成为稀疏张量，dense是一个密集的张量。

从稀疏到密集：

 dense = tf.sparse_to_dense(sparse.indices, sparse.shape, sparse.values)

从密集到稀疏：

zero = tf.constant(0, dtype=tf.float32)
where = tf.not_equal(dense, zero)
indices = tf.where(where)
values = tf.gather_nd(dense, indices)
sparse = tf.SparseTensor(indices, values, dense.shape)

将Tensor转换为用于ctc_loss的SparseTensor

1 个答案: