转换后的Tensorflow Lite对象检测模型在IOS演示上不起作用

时间:2019-04-30 15:00:20

标签: tensorflow machine-learning

我遵循了本文的说明:https://medium.com/tensorflow/training-and-serving-a-realtime-mobile-object-detector-in-30-minutes-with-cloud-tpus-b78971cf1193

在将tflige_graph.pb文件转换为detect.tflite之后,我无法在演示对象检测应用程序https://github.com/tensorflow/examples/blob/master/lite/examples/object_detection/ios/README.md

中加载tflite文件。

我使用了以下代码: 1

bazel run -c opt tensorflow/contrib/lite/toco:toco -- \
--input_file=$OUTPUT_DIR/tflite_graph.pb \
--output_file=$OUTPUT_DIR/detect.tflite \
--input_shapes=1,300,300,3 \
--input_arrays=normalized_input_image_tensor \
--output_arrays='TFLite_Detection_PostProcess','TFLite_Detection_PostProcess:1','TFLite_Detection_PostProcess:2','TFLite_Detection_PostProcess:3'  \
--inference_type=QUANTIZED_UINT8 \
--mean_values=128 \
--std_values=128 \
--change_concat_input_ranges=false \
--allow_custom_ops

2

tflite_convert \
--graph_def_file=$OUTPUT_DIR/tflite_graph.pb \
--output_file=$OUTPUT_DIR/detect.tflite \
--input_shapes=1,300,300,3 \
--input_arrays=normalized_input_image_tensor \
--output_arrays='TFLite_Detection_PostProcess','TFLite_Detection_PostProcess:1','TFLite_Detection_PostProcess:2','TFLite_Detection_PostProcess:3' \
--inference_type=QUANTIZED_UINT8 \
--mean_values=128 \
--std_dev_values=128 \
--change_concat_input_ranges=false \
--allow_custom_ops

错误提示:ObjectDetection [38040:9491919]在捆绑包中找不到“ detect.tflite”。

我尝试了示例演示文件,但也失败了:https://storage.googleapis.com/download.tensorflow.org/models/tflite/frozengraphs_ssd_mobilenet_v1_0.75_quant_pets_2018_06_29.zip

但是,示例tflite文件有效:https://storage.googleapis.com/download.tensorflow.org/models/tflite/pets_ssd_mobilenet_v1_0.75_quant_2018_06_29.zip

请帮助。

0 个答案:

没有答案