节点编号X(重塑)准备失败。使用Tflite v2.2调整张量大小 [英] Node number X (RESHAPE) failed to prepare. Tensor resize with tflite v2.2

问题描述

以下是重现该错误的简单代码：

import os
os.environ["CUDA_VISIBLE_DEVICES"]="-1"

import numpy as np
from keras.models import Sequential
from keras.layers import Conv1D, Flatten, Dense
import tensorflow as tf

model_path = 'test.h5'

model = Sequential()
model.add(Conv1D(8,(5,), input_shape=(100,1)))
model.add(Flatten())
model.add(Dense(1))
model.compile(loss='mse', optimizer='adam')
model.save(model_path)

model = tf.keras.models.load_model(model_path, compile=False)
converter = tf.lite.TFLiteConverter.from_keras_model(model)

tflite_model = converter.convert()

interpreter = tf.lite.Interpreter(model_content=tflite_model)

interpreter.resize_tensor_input(interpreter.get_input_details()[0]['index'], (2,100,1))
interpreter.resize_tensor_input(interpreter.get_output_details()[0]['index'], (2,1))

interpreter.allocate_tensors()

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-3-ad8e2eea467f> in <module>
     27 interpreter.resize_tensor_input(interpreter.get_output_details()[0]['index'], (2,1))
     28 
---> 29 interpreter.allocate_tensors()

<>/tensorflow/lite/python/interpreter.py in allocate_tensors(self)
    240   def allocate_tensors(self):
    241     self._ensure_safe()
--> 242     return self._interpreter.AllocateTensors()
    243 
    244   def _safe_to_run(self):

<>/tensorflow/lite/python/interpreter_wrapper/tensorflow_wrap_interpreter_wrapper.py in AllocateTensors(self)
    108 
    109     def AllocateTensors(self):
--> 110         return _tensorflow_wrap_interpreter_wrapper.InterpreterWrapper_AllocateTensors(self)
    111 
    112     def Invoke(self):

RuntimeError: tensorflow/lite/kernels/reshape.cc:66 num_input_elements != num_output_elements (1536 != 768)Node number 3 (RESHAPE) failed to prepare.

问题似乎来自于展平层中的重塑功能。我已经能够在TensorFlow 1.5中执行这种大小调整，但在2.2版本中无法执行。

以下是重塑层的信息：

 {'name': 'sequential_1/flatten_1/Reshape',
  'index': 8,
  'shape': array([  1, 768], dtype=int32),
  'shape_signature': array([  1, 768], dtype=int32),
  'dtype': numpy.float32,
  'quantization': (0.0, 0),
  'quantization_parameters': {'scales': array([], dtype=float32),
   'zero_points': array([], dtype=int32),
   'quantized_dimension': 0},
  'sparsity_parameters': {}},

我想也许我也应该调整这个层的大小，所以我添加了：

interpreter.resize_tensor_input(8, (2,768))

但我收到了完全相同的错误。

RuntimeError: tensorflow/lite/kernels/reshape.cc:66 num_input_elements != num_output_elements (1536 != 768)Node number 3 (RESHAPE) failed to prepare.

推荐答案

我已经想出了一个解决办法，可以在转换为Tflite之前重塑模型，方法是重塑Keras模型，然后将其转换为具体函数，并使用from_Contrate_Function而不是from_keras_Model。

import os
os.environ["CUDA_VISIBLE_DEVICES"]="-1"

import numpy as np
from keras.models import Sequential
from keras.layers import Conv1D, Flatten, Dense
import tensorflow as tf

model_path = 'test.h5'

model = Sequential()
model.add(Conv1D(8,(5,), input_shape=(100,1)))
model.add(Flatten())
model.add(Dense(1))
model.compile(loss='mse', optimizer='adam')
model.save(model_path)

model = tf.keras.models.load_model(model_path, compile=False)

batch_size = 2
input_shape = model.inputs[0].shape.as_list()
input_shape[0] = batch_size
func = tf.function(model).get_concrete_function(
    tf.TensorSpec(input_shape, model.inputs[0].dtype))
converter = tf.lite.TFLiteConverter.from_concrete_functions([func])

tflite_model = converter.convert()

interpreter = tf.lite.Interpreter(model_content=tflite_model)

interpreter.allocate_tensors()

这篇关于节点编号X(重塑)准备失败。使用Tflite v2.2调整张量大小的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！