Question

我试图让KeithIto的Tacotron模型在带有NCS的Intel OpenVINO上运行。模型优化器无法将冻结的模型转换为IR格式。

在英特尔论坛上提问后，我被告知2018 R5版本不支持GRU，我将其更改为LSTM单元。但是模型经过训练后仍然可以在张量流中很好地运行。我也将OpenVINO更新为2019 R1版本。但是优化器仍然抛出错误。该模型主要有两个输入节点：input [N，T_in]和input_lengths [N];其中N是批处理大小，T_in是输入时间序列中的步数，值是字符ID，默认形状为[1 ,?]和[1]。问题出在[1 ,?]，因为模型优化器不允许使用动态形状。我尝试了不同的值，它总是会引发一些错误。

我尝试了冻结图，其中输出节点为“ model / griffinlim / Squeeze”，这是最终的解码器输出，还尝试了{https://github.com/keithito/tacotron/issues/95#issuecomment-362854371）中提到的“ model / inference / dense / BiasAdd”，它是Griffin-lim声码器，这样我就可以在模型外进行Spectrogram2Wav部分，并降低其复杂性。

C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer>python mo_tf.py --input_model "D:\Programming\LSTM\logs-tacotron\freezeinf.pb" --freeze_placeholder_with_value "input_lengths->[1]" --input inputs --input_shape [1,128] --output model/inference/dense/BiasAdd
Model Optimizer arguments:
Common parameters:
        - Path to the Input Model:      D:\Programming\Thesis\LSTM\logs-tacotron\freezeinf.pb
        - Path for generated IR:        C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\.
        - IR output name:       freezeinf
        - Log level:    ERROR
        - Batch:        Not specified, inherited from the model
        - Input layers:         inputs
        - Output layers:        model/inference/dense/BiasAdd
        - Input shapes:         [1,128]
        - Mean values:  Not specified
        - Scale values:         Not specified
        - Scale factor:         Not specified
        - Precision of IR:      FP32
        - Enable fusing:        True
        - Enable grouped convolutions fusing:   True
        - Move mean values to preprocess section:       False
        - Reverse input channels:       False
TensorFlow specific parameters:
        - Input model in text protobuf format:  False
        - Path to model dump for TensorBoard:   None
        - List of shared libraries with TensorFlow custom layers implementation:        None
        - Update the configuration file with input/output node names:   None
        - Use configuration file used to generate the model with Object Detection API:  None
        - Operations to offload:        None
        - Patterns to offload:  None
        - Use the config file:  None
Model Optimizer version:        2019.1.0-341-gc9b66a2
[ ERROR ]  Shape [  1  -1 128] is not fully defined for output 0 of "model/inference/post_cbhg/conv_bank/conv1d_8/batch_normalization/batchnorm/mul_1". Use --input_shape with positive integers to override model input shapes.
[ ERROR ]  Cannot infer shapes or values for node "model/inference/post_cbhg/conv_bank/conv1d_8/batch_normalization/batchnorm/mul_1".
[ ERROR ]  Not all output shapes were inferred or fully defined for node "model/inference/post_cbhg/conv_bank/conv1d_8/batch_normalization/batchnorm/mul_1".
 For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #40.
[ ERROR ]
[ ERROR ]  It can happen due to bug in custom shape infer function <function tf_eltwise_ext.<locals>.<lambda> at 0x000001F00598FE18>.
[ ERROR ]  Or because the node inputs have incorrect values/shapes.
[ ERROR ]  Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ]  Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "model/inference/post_cbhg/conv_bank/conv1d_8/batch_normalization/batchnorm/mul_1" node.
 For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #38.

我也尝试了不同的方法来冻结图形。

方法1： 转储图形后，使用Tensorflow中提供的freeze_graph.py：

tf.train.write_graph(self.session.graph.as_graph_def(), "models/", "graph.pb", as_text=True)

其次：

python freeze_graph.py --input_graph .\models\graph.pb  --output_node_names "model/griffinlim/Squeeze" --output_graph .\logs-tacotron\freezeinf.pb --input_checkpoint .\logs-tacotron\model.ckpt-33000 --input_binary=true

方法2： 加载模型后使用以下代码：

frozen = tf.graph_util.convert_variables_to_constants(self.session,self.session.graph_def, ["model/inference/dense/BiasAdd"]) #model/griffinlim/Squeeze
graph_io.write_graph(frozen, "models/", "freezeinf.pb", as_text=False)

我希望冻结后可以删除BatchNormalization和Dropout层，但查看错误似乎仍然存在。

环境

操作系统：Windows 10 Pro

Python 3.6.5

Tensorflow 1.12.0

OpenVINO 2019 R1版本

有人可以通过优化程序解决上述问题吗？

Answer 1

OpenVINO尚不支持此模型。我们会及时向您更新。

如何在Tacotron模型的OpenVINO中为模型优化器设置输入形状？

1 个答案: