3

问题

我开发了一个简单的 NodeJS 应用程序，用于使用@tensorflow/tfjs-node. 在我的开发 PC (Windows 10 Pro) 上一切正常，但尝试在我的 Raspberry Pi 2B (Raspbian 10) 上执行时，出现以下错误：

Overriding the gradient for 'Max'
Overriding the gradient for 'OneHot'
Overriding the gradient for 'PadV2'
Overriding the gradient for 'SpaceToBatchND'
Overriding the gradient for 'SplitV'
2020-07-31 11:25:12.068892: I tensorflow/cc/saved_model/reader.cc:31] Reading SavedModel from: ./assets/saved_model
2020-07-31 11:25:12.643852: I tensorflow/cc/saved_model/reader.cc:54] Reading meta graph with tags { serve }
2020-07-31 11:25:13.206821: I tensorflow/cc/saved_model/loader.cc:311] SavedModel load for tags { serve }; Status: fail. Took 1137915 microseconds.
Error: Failed to load SavedModel: Op type not registered 'NonMaxSuppressionV5' in binary running on raspberrypi. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
    at NodeJSKernelBackend.loadSavedModelMetaGraph (/home/pi/storage/tensorflow-test-node/node_modules/@tensorflow/tfjs-node/dist/nodejs_kernel_backend.js:1588:29)
    at Object.<anonymous> (/home/pi/storage/tensorflow-test-node/node_modules/@tensorflow/tfjs-node/dist/saved_model.js:429:45)
    at step (/home/pi/storage/tensorflow-test-node/node_modules/@tensorflow/tfjs-node/dist/saved_model.js:48:23)
    at Object.next (/home/pi/storage/tensorflow-test-node/node_modules/@tensorflow/tfjs-node/dist/saved_model.js:29:53)
    at fulfilled (/home/pi/storage/tensorflow-test-node/node_modules/@tensorflow/tfjs-node/dist/saved_model.js:20:58)

我可以用以下几行重现它：

const tf = require('@tensorflow/tfjs-node');

// Native SavedModel: ./assets/saved_model/saved_model.pb
const objectDetectionModel = await tf.node.loadSavedModel('./assets/saved_model'); // Error

// ...

我认为该错误与 SavedModel 版本有关，但我不知道如何将其转换为在 Rapsberry Pi 中使用，或者如果我在 Windows 或 Raspbian 中执行 NodeJS 应用程序需要不同的 SavedModel。

细节

环境

  • 发展：
    • 操作系统：Windows 10 专业版
    • 节点JS：v12.16.2
    • 新PM：6.11.3
  • 目标（树莓派）：
    • 操作系统：Raspbian 10
    • 节点JS：v12.18.3
    • 新PM：6.14.6

NodeJS 应用程序

@tensorflow/tfjs-node@2.0.1是在package.json.

训练

该模型是按照本指南在 Python 上训练的（使用的 TensorFlow 版本是1.15.2）。

保存模型

SavedModel 的详细信息（执行的命令saved_model_cli show --dir saved_model --tag_set serve --signature_def serving_default）：

The given SavedModel SignatureDef contains the following input(s):
  inputs['inputs'] tensor_info:
      dtype: DT_INT32
      shape: (-1, -1, -1, 3)
      name: image_tensor:0
The given SavedModel SignatureDef contains the following output(s):
  outputs['detection_boxes'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 300, 4)
      name: detection_boxes:0
  outputs['detection_classes'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 300)
      name: detection_classes:0
  outputs['detection_multiclass_scores'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 300, 37)
      name: detection_multiclass_scores:0
  outputs['detection_scores'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 300)
      name: detection_scores:0
  outputs['num_detections'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1)
      name: num_detections:0
  outputs['raw_detection_boxes'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 300, 4)
      name: raw_detection_boxes:0
  outputs['raw_detection_scores'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 300, 37)
      name: raw_detection_scores:0
Method name is: tensorflow/serving/predict
4

1 回答 1

2

您需要将模型转换为 Tensorflow Lite（减少操作）。收到的错误是由于在加载桌面编译模型时树莓派上缺少可用的操作（有更高的操作可用）。在此处阅读有关操作的更多信息：https ://www.tensorflow.org/lite/guide/ops_select

已经有一个将模型导出到 TF Lite 的构建脚本，类似于您正在使用的那个（官方示例 repo 中的相同文件夹）。功能相同，但输入格式略有不同。看看：https ://www.github.com/tensorflow/models/tree/master/research%2Fobject_detection%2Fexport_tflite_ssd_graph.py

于 2020-08-09T03:04:29.020 回答