我正在学习粗糙张量及其在粒子跟踪中的应用。我有下面这个最小的例子，它再现了我一直经历的错误。
import tensorflow as tf
from tensorflow.keras.layers import Dense, LSTM, Input, TimeDistributed
from tensorflow.keras.models import Sequential
n=10
data_n = 32
batch_size=8
window_length=8
splits = [n]*data_n
#### Create a ragged tensor with shape (32, None, 8)
t0 = tf.zeros([data_n * n, window_length])
t1 = tf.RaggedTensor.from_row_lengths(t0, splits)
max_seq = t1.bounding_shape()[-1]
#### Define Model
def create_model(batch_size, window_length, max_seq):
lstm_model = Sequential([
Input(
batch_shape=[batch_size, None, window_length],
batch_size=batch_size,
dtype=tf.float32,
ragged=True
),
LSTM(
max_seq,
return_sequences=True,
input_shape=(window_length, None)
),
TimeDistributed(Dense(units=1))
])
return lstm_model
lstm_model = create_model(batch_size=batch_size, window_length=window_length, max_seq=max_seq)
lstm_model(t1[0:8])
当我执行上面的代码时，我得到以下错误：
---------------------------------------------------------------------------
_FallbackException Traceback (most recent call last)
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/gen_cudnn_rnn_ops.py in cudnn_rnnv3(input, input_h, input_c, params, sequence_lengths, rnn_mode, input_mode, direction, dropout, seed, seed2, num_proj, is_training, time_major, name)
1889 try:
-> 1890 _result = pywrap_tfe.TFE_Py_FastPathExecute(
1891 _ctx._context_handle, tld.device_name, "CudnnRNNV3", name,
_FallbackException: Expecting float value for attr dropout, got int
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-19-7609e2877e20> in <module>
1 lstm_model = create_model(batch_size=batch_size, window_length=window_length, max_seq=max_seq)
----> 2 lstm_model(t1[0:8])
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
966 with base_layer_utils.autocast_context_manager(
967 self._compute_dtype):
--> 968 outputs = self.call(cast_inputs, *args, **kwargs)
969 self._handle_activity_regularization(inputs, outputs)
970 self._set_mask_metadata(inputs, outputs, input_masks)
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/sequential.py in call(self, inputs, training, mask)
275 if not self.built:
276 self._init_graph_network(self.inputs, self.outputs, name=self.name)
--> 277 return super(Sequential, self).call(inputs, training=training, mask=mask)
278
279 outputs = inputs # handle the corner case where self.layers is empty
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in call(self, inputs, training, mask)
715 ' implement a `call` method.')
716
--> 717 return self._run_internal_graph(
718 inputs, training=training, mask=mask,
719 convert_kwargs_to_constants=base_layer_utils.call_context().saving)
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in _run_internal_graph(self, inputs, training, mask, convert_kwargs_to_constants)
886
887 # Compute outputs.
--> 888 output_tensors = layer(computed_tensors, **kwargs)
889
890 # Update tensor_dict.
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/layers/recurrent.py in __call__(self, inputs, initial_state, constants, **kwargs)
652
653 if initial_state is None and constants is None:
--> 654 return super(RNN, self).__call__(inputs, **kwargs)
655
656 # If any of `initial_state` or `constants` are specified and are Keras
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
966 with base_layer_utils.autocast_context_manager(
967 self._compute_dtype):
--> 968 outputs = self.call(cast_inputs, *args, **kwargs)
969 self._handle_activity_regularization(inputs, outputs)
970 self._set_mask_metadata(inputs, outputs, input_masks)
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/layers/recurrent_v2.py in call(self, inputs, mask, training, initial_state)
1178 # GPU implementation when GPU is available.
1179 if can_use_gpu:
-> 1180 last_output, outputs, new_h, new_c, runtime = gpu_lstm(
1181 **gpu_lstm_kwargs)
1182 else:
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/layers/recurrent_v2.py in gpu_lstm(inputs, init_h, init_c, kernel, recurrent_kernel, bias, mask, time_major, go_backwards, sequence_lengths)
1404 inputs = array_ops.reverse_sequence_v2(
1405 inputs, sequence_lengths, seq_axis=seq_axis, batch_axis=batch_axis)
-> 1406 outputs, h, c, _, _ = gen_cudnn_rnn_ops.cudnn_rnnv3(
1407 inputs,
1408 input_h=init_h,
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/gen_cudnn_rnn_ops.py in cudnn_rnnv3(input, input_h, input_c, params, sequence_lengths, rnn_mode, input_mode, direction, dropout, seed, seed2, num_proj, is_training, time_major, name)
1899 except _core._FallbackException:
1900 try:
-> 1901 return cudnn_rnnv3_eager_fallback(
1902 input, input_h, input_c, params, sequence_lengths,
1903 rnn_mode=rnn_mode, input_mode=input_mode, direction=direction,
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/gen_cudnn_rnn_ops.py in cudnn_rnnv3_eager_fallback(input, input_h, input_c, params, sequence_lengths, rnn_mode, input_mode, direction, dropout, seed, seed2, num_proj, is_training, time_major, name, ctx)
1999 "direction", direction, "dropout", dropout, "seed", seed, "seed2", seed2,
2000 "num_proj", num_proj, "is_training", is_training, "time_major", time_major)
-> 2001 _result = _execute.execute(b"CudnnRNNV3", 5, inputs=_inputs_flat,
2002 attrs=_attrs, ctx=ctx, name=name)
2003 if _execute.must_record_gradient():
~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
57 try:
58 ctx.ensure_initialized()
---> 59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
InvalidArgumentError: Invalid input_h shape: [1,8,8] [10,8,8] [Op:CudnnRNNV3]
10是指LSTM-层中的单元数量，等于t1的边界形状。两个8是指batch_size和window_length。我认为1指的是输出形状，但事实并非如此，因为当我向Dense层添加更多单元时，它不会改变，所以数字保持不变。
使用具有可变大小序列的tf.RaggedTensor时，需要设置batch_size = 1，并确保传递给LSTM的sequence_length为None。
这是因为，即使tf.RaggedTensor是以numpy数组形式存储可变大小序列的好方法，LSTM仍然期望每个批次具有相同长度的序列。但是，您可以跨批次使用可变大小的序列。
做出这些改变应该可以解决你所面临的问题。
这也是我遇到的一个错误。它特定于以下的组合：
使用GPU和RaggedTensor 实现RNN/LSTM Tensorflow版本的Keras
错误的源代码是将RNN单元的输入隐藏状态的粗糙张量的形状与隐藏状态的形状进行比较
不规则尺寸在错误消息中显示为1。我能够使用您的代码和Tensorflow 2.2.0 复制相同的错误
更改代码以删除粗糙的张量或在cpu或不同的tensorflow版本上运行我能够使此代码工作