在Android中使用BI-LSTM-CTC-Tensorflow模型

TL；DR，我想知道如何在android应用程序中使用bi lstm ctc tensorflow模型

我已经成功地训练了我的bi lstm ctc tensorflow模型，现在我想将其用于我的手写识别android应用程序。下面是定义我使用的图形的代码部分：

self.inputs = tf.placeholder(tf.float32, [None, None, network_config.num_features], name="input")
self.labels = tf.sparse_placeholder(tf.int32, name="label")
self.seq_len = tf.placeholder(tf.int32, [None], name="seq_len_input")

logits = self._bidirectional_lstm_layers(
   network_config.num_hidden_units,
   network_config.num_layers,
   network_config.num_classes
)

self.global_step = tf.Variable(0, trainable=False)
self.loss = tf.nn.ctc_loss(labels=self.labels, inputs=logits, sequence_length=self.seq_len)
self.cost = tf.reduce_mean(self.loss)

self.optimizer = tf.train.AdamOptimizer(network_config.learning_rate).minimize(self.cost)
self.decoded, self.log_prob = tf.nn.ctc_beam_search_decoder(inputs=logits, sequence_length=self.seq_len, merge_repeated=False)
self.dense_decoded = tf.sparse_tensor_to_dense(self.decoded[0], default_value=-1, name="output")

我还成功地在冻结和优化图形代码之后冻结和优化了图形。下面是应该运行模型的代码部分：

bitmap = Bitmap.createScaledBitmap(bitmap, 1024, 128, true);
int[] intValues = new int[bitmap.getWidth() * bitmap.getHeight()];
bitmap.getPixels(intValues, 0, bitmap.getWidth(), 0, 0, bitmap.getWidth(), bitmap.getHeight());
float[] floatValues = new float[bitmap.getWidth() * bitmap.getHeight()];
for (int i = 0; i < intValues.length; ++i) {
    final int val = intValues[i];
    floatValues[i] = (((val >> 16) & 0xFF));
}
float[] result = new float[80];
long[] INPUT_SIZE = new long[]{1, bitmap.getHeight(), bitmap.getWidth()};
inferenceInterface.feed(config.getInputName(), floatValues, INPUT_SIZE);
inferenceInterface.feed("seq_len_input", new int[]{bitmap.getWidth()}, 1);
inferenceInterface.run(config.getOutputNames());
inferenceInterface.fetch(config.getOutputNames()[0], result);

return result.toString();

如果使用优化的冻结图，我会遇到以下错误：

Caused by: java.lang.IllegalArgumentException: No OpKernel was registered to support
Op 'SparseToDense' with these attrs.  Registered devices: [CPU], Registered kernels:
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT64]
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT32]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT64]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT32]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT64]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT32]

[[Node: output = SparseToDense[T=DT_INT64, Tindices=DT_INT64, validate_indices=true](CTCBeamSearchDecoder, CTCBeamSearchDecoder:2, CTCBeamSearchDecoder:1, output/default_value)]]

java.io.IOException: Not a valid TensorFlow Graph serialization: NodeDef expected inputs '' do not match 1 inputs 
specified; Op<name=Const; signature= -> output:dtype; attr=value:tensor; attr=dtype:type>; 
NodeDef: stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/add/y = Const[dtype=DT_INT32, 
value=Tensor<type: int32 shape: [] values: 1>](stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/Switch:1)

java.lang.IllegalArgumentException: Matrix size-incompatible: In[0]: [1,1056], In[1]: [160,128]
[[Node:stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/

MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/cpu:0"]

(stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/concat, 
stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/MatMul/Enter)]]

java.lang.IllegalArgumentException: cannot use java.nio.FloatArrayBuffer with Tensor of type INT32

java.io.IOException:不是有效的TensorFlow图序列化：NodeDef预期输入“”与1个输入不匹配
明确规定；Op输出：数据类型；attr=值：张量；attr=dtype:type>；
nodededef:stack\u bidirectional\u rnn/cell\u 0/bidirectional\u rnn/bw/bw/while/add/y=Const[dtype=DT\u INT32，
值=张量]（堆栈\u双向\u rnn/cell\u 0/双向\u rnn/bw/bw/while/Switch:1）

除了解决这些错误的方法外，我还有其他问题/澄清：

---

如何解决这些错误？

我已经让它工作了。解决方案也可以在这方面找到

显然，问题在于所使用的类型。我通过的是int64，这里只接受int32

self.dense_decoded = tf.sparse_tensor_to_dense(self.decoded[0], default_value=-1, name="output")

为了解决这个问题，我将稀疏张量元素转换为int32：

self.dense_decoded = tf.sparse_to_dense(tf.to_int32(self.decoded[0].indices),
               tf.to_int32(self.decoded[0].dense_shape),
               tf.to_int32(self.decoded[0].values),
               name="output")

在此之后运行应用程序时出现以下错误：

Caused by: java.lang.IllegalArgumentException: No OpKernel was registered to support
Op 'SparseToDense' with these attrs.  Registered devices: [CPU], Registered kernels:
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT64]
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT32]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT64]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT32]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT64]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT32]

[[Node: output = SparseToDense[T=DT_INT64, Tindices=DT_INT64, validate_indices=true](CTCBeamSearchDecoder, CTCBeamSearchDecoder:2, CTCBeamSearchDecoder:1, output/default_value)]]

java.io.IOException: Not a valid TensorFlow Graph serialization: NodeDef expected inputs '' do not match 1 inputs 
specified; Op<name=Const; signature= -> output:dtype; attr=value:tensor; attr=dtype:type>; 
NodeDef: stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/add/y = Const[dtype=DT_INT32, 
value=Tensor<type: int32 shape: [] values: 1>](stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/Switch:1)

java.lang.IllegalArgumentException: Matrix size-incompatible: In[0]: [1,1056], In[1]: [160,128]
[[Node:stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/

MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/cpu:0"]

(stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/concat, 
stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/MatMul/Enter)]]

java.lang.IllegalArgumentException: cannot use java.nio.FloatArrayBuffer with Tensor of type INT32

出于某种奇怪的原因，在java代码中将图像宽度从1024更改为128修复了该错误。再次运行应用程序时出现以下错误：

Caused by: java.lang.IllegalArgumentException: No OpKernel was registered to support
Op 'SparseToDense' with these attrs.  Registered devices: [CPU], Registered kernels:
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT64]
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT32]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT64]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT32]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT64]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT32]

[[Node: output = SparseToDense[T=DT_INT64, Tindices=DT_INT64, validate_indices=true](CTCBeamSearchDecoder, CTCBeamSearchDecoder:2, CTCBeamSearchDecoder:1, output/default_value)]]

java.io.IOException: Not a valid TensorFlow Graph serialization: NodeDef expected inputs '' do not match 1 inputs 
specified; Op<name=Const; signature= -> output:dtype; attr=value:tensor; attr=dtype:type>; 
NodeDef: stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/add/y = Const[dtype=DT_INT32, 
value=Tensor<type: int32 shape: [] values: 1>](stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/Switch:1)

java.lang.IllegalArgumentException: Matrix size-incompatible: In[0]: [1,1056], In[1]: [160,128]
[[Node:stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/

MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/cpu:0"]

(stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/concat, 
stack_bidirectional_rnn/cell_0/bidirectional_rnn/bw/bw/while/bw/basic_lstm_cell/basic_lstm_cell/MatMul/Enter)]]

java.lang.IllegalArgumentException: cannot use java.nio.FloatArrayBuffer with Tensor of type INT32

获取输出时出现了问题。这样，我知道模型运行成功，但应用程序无法获取结果

inferenceInterface.run(outputs);
inferenceInterface.fetch(outputs[0], result); //where the error happens

愚蠢的我忘记了输出是一个整数数组，而不是浮点数组。因此，我将结果数组的类型更改为int数组：

//float[] result = new float[80];
int[] result = new int[80];

从而使应用程序工作。模型的准确性不好，因为它没有经过适当的训练。我只是想让它在应用程序中工作。是时候进行认真的训练了