tensorflow - 使用 TF Lite Model Maker 创建的模型出现 TF.js 导入错误

Question

我已经使用 https://www.tensorflow.org/lite/tutorials/model_maker_image_classification 上的教程创建了一个模型。并以 TF.js 格式导出:

import os

import matplotlib.pyplot as plt
import tensorflow as tf
from tflite_model_maker import image_classifier, model_spec
from tflite_model_maker.config import ExportFormat, QuantizationConfig
from tflite_model_maker.image_classifier import DataLoader

image_path = tf.keras.utils.get_file(
      'flower_photos.tgz',
      'https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz',
      extract=True)
image_path = os.path.join(os.path.dirname(image_path), 'flower_photos')
data = DataLoader.from_folder(image_path)
train_data, test_data = data.split(0.9)
model = image_classifier.create(train_data)
loss, accuracy = model.evaluate(test_data)

# Export model to TF.js format
model.export(export_dir='.', export_format=ExportFormat.TFJS)

使用 tf.loadLayersModel 在 TF.js 中加载此模型时我收到以下错误:

Uncaught (in promise) Error: Unknown layer: HubKerasLayerV1V2. 
This may be due to one of the following reasons:
1. The layer is defined in Python, in which case it needs to be
ported to TensorFlow.js or your JavaScript code.
2. The custom layer is defined in JavaScript, but is not registered
properly with tf.serialization.registerClass()

我猜错误是由于原因 (1)，但我如何移植 HubKerasLayerV1V2层到 TF.js？

Answer 1

我相信这是模型转换器的问题，该模型转换器在层模型中存在部分 Graph 问题。
您可以通过将模型序列化为普通 SaveModel 来解决此问题。格式化并导出 HDF5。一旦您拥有 .h5输出，使用 TensorFlow.js 转换器 ( tensorflowjs_converter ) 创建一个纯图形模型。然后尝试加载 tf.loadGraphModel反而。