我尝试将冻结的SSD mobilenet v2模型转换为TFLITE格式以供Android使用。这是我所有的步骤:
我使用ssd_mobilenet_v2_coco_2018_03_29模型使用TF对象检测API的train.py文件进行重新训练。 ((确定)
也使用TF Object Detection API提供的export_inference_graph.p y将训练后的model.ckpt导出到冻结的模型文件。 ((确定)
在具有GPU且仅允许CPU的python中测试冻结的图。有用。 ((确定)
这是缺点,我尝试使用以下代码:
import tensorflow as tf
tf.enable_eager_execution()
saved_model_dir = 'inference_graph/saved_model/'
converter = tf.contrib.lite.TFLiteConverter.from_saved_model(saved_model_dir,input_arrays=input_arrays,output_arrays=output_arrays,input_shapes={"image_tensor": [1, 832, 832, 3]})
converter.post_training_quantize = True
首先,我尝试不向函数添加输入shapes参数,但是没有用。从那时起,我读到您可以在这里写任何无关紧要的内容。
直到此行的输出:
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
INFO:tensorflow:The specified SavedModel has no variables; no checkpoints were restored.
INFO:tensorflow:The given SavedModel MetaGraphDef contains SignatureDefs with the following keys: {'serving_default'}
INFO:tensorflow:input tensors info:
INFO:tensorflow:Tensor's key in saved_model's tensor_map: inputs
INFO:tensorflow: tensor name: image_tensor:0, shape: (-1, -1, -1, 3), type: DT_UINT8
INFO:tensorflow:output tensors info:
INFO:tensorflow:Tensor's key in saved_model's tensor_map: num_detections
INFO:tensorflow: tensor name: num_detections:0, shape: (-1), type: DT_FLOAT
INFO:tensorflow:Tensor's key in saved_model's tensor_map: detection_boxes
INFO:tensorflow: tensor name: detection_boxes:0, shape: (-1, 100, 4), type: DT_FLOAT
INFO:tensorflow:Tensor's key in saved_model's tensor_map: detection_scores
INFO:tensorflow: tensor name: detection_scores:0, shape: (-1, 100), type: DT_FLOAT
INFO:tensorflow:Tensor's key in saved_model's tensor_map: detection_classes
INFO:tensorflow: tensor name: detection_classes:0, shape: (-1, 100), type: DT_FLOAT
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
INFO:tensorflow:The specified SavedModel has no variables; no checkpoints were restored.
INFO:tensorflow:Froze 0 variables.
INFO:tensorflow:Converted 0 variables to const ops.
然后我想转换:
tflite_quantized_model = converter.convert()
这是输出:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-6-61a136476642> in <module>
----> 1 tflite_quantized_model = converter.convert()
~/.local/lib/python3.5/site-packages/tensorflow/contrib/lite/python/lite.py in convert(self)
451 input_tensors=self._input_tensors,
452 output_tensors=self._output_tensors,
--> 453 **converter_kwargs)
454 else:
455 # Graphs without valid tensors cannot be loaded into tf.Session since they
~/.local/lib/python3.5/site-packages/tensorflow/contrib/lite/python/convert.py in toco_convert_impl(input_data, input_tensors, output_tensors, *args, **kwargs)
340 data = toco_convert_protos(model_flags.SerializeToString(),
341 toco_flags.SerializeToString(),
--> 342 input_data.SerializeToString())
343 return data
344
~/.local/lib/python3.5/site-packages/tensorflow/contrib/lite/python/convert.py in toco_convert_protos(model_flags_str, toco_flags_str, input_data_str)
133 else:
134 raise RuntimeError("TOCO failed see console for info.\n%s\n%s\n" %
--> 135 (stdout, stderr))
136
137
RuntimeError: TOCO failed see console for info.
我无法在此处复制控制台输出,因此它超出了30000个字符的限制,但在这里您可以看到它:https://pastebin.com/UyT2x2Vk
[请在这一点上提供帮助,我应该怎么做才能使其工作:(
我的配置:Ubuntu 16.04,Tensorflow-GPU 1.12
感谢您!
上周遇到相同的问题,请按照here中所述的步骤解决。
基本上,问题在于它们的主脚本不支持SSD模型。我没有使用bazel
来执行此操作,而是使用了tflite_convert
实用程序。
请谨慎使用export_tflite_ssd_graph.py
脚本,使用前请先阅读其所有选项(主要是--max_detections挽救了我的性命。]
希望这会有所帮助。
编辑:您的步骤2无效。如果save_model包含SSD,则无法将其转换为tflite模型。您需要使用export_tflite_ssd_graph.py
脚本导出经过训练的model.ckpt,并使用通过.pb
工具创建的tflite_convert
文件将其转换为tflite。
您的.pb文件格式不正确。解决方法如下:https://github.com/peace195/tensorflow-lite-yolo-v3
我们需要执行2个步骤:
将权重转换为SavedModel。
使用tflite_convert从保存的模型转换为tflite格式。
请使用docker设置环境并仔细按照说明进行操作。