问题描述
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 传递到 Tensorflow 的 Estimator.fit 的原因之一是能够使用 tensorflow ctc_loss.代码如下:
Is there a way to convert a dense tensor into a sparse tensor? Apparently, Tensorflow's Estimator.fit doesn't accept SparseTensors as labels. One reason I would like to pass SparseTensors into Tensorflow's Estimator.fit is to be able to use tensorflow ctc_loss. Here's the code:
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,这个解决方案来自 这里将密集张量转换为稀疏张量:
It turns out, this solution from here converts the dense tensor into a sparse one:
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,我现在遇到了 ctc_loss 引发的这个错误:
However, I encounter this error now raised by ctc_loss:
ValueError: Shape must be rank 1 but is rank 0 for 'CTCLoss' (op: 'CTCLoss') with input shapes: [?,?,80], [?,2], [?], [].
我有将密集标签转换为稀疏标签的代码:
I have this code that converts dense labels to sparse:
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
中:
I converted y_train
to sparse labels, and place the values inside a SparseTensor
:
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 内部创建的 SparseTensor
进行比较:
And compared it to the SparseTensor
created inside the grid_rnn_fn:
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:
对于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))
对于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))
这让我认为 ctc_loss 似乎无法将 SparseTensors
作为具有动态形状的标签处理.
Which leads me to think that ctc_loss can't seem to handle SparseTensors
as labels with dynamic shapes.
推荐答案
是的.可以将张量转换为稀疏张量并返回:
Yes. It is possible to convert a tensor to a sparse tensor and back:
设 sparse
为稀疏张量,dense
为稠密张量.
Let sparse
be a sparse tensor and dense
be a dense tensor.
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)
这篇关于将张量转换为 ctc_loss 的稀疏张量的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!