最近更新到tensorflow 2.0，将我的.h5模型添加到.onnx遇到了麻烦。曾经是一个非常简单的过程，但是现在我遇到了问题。当我运行以下代码时：
# onnx testing
import onnx
import keras2onnx
import os
import tensorflow as tf
from tensorflow.keras.models import load_model
folder = r'\\rdnas'
os.chdir(folder)
#os.environ["TF_KERAS"]='1'
model_loc = folder+'\\model.h5'
model = tf.keras.models.load_model(model_loc)
model.summary()
# Onnx covnersion
onnx_model = keras2onnx.convert_keras(model)
temp_model_file = 'model.onnx'
onnx.save_model(onnx_model, temp_model_file)
当我运行代码时，出现以下错误
Using TensorFlow backend.
Can't import tf2onnx module, so the conversion on a model with any custom/lambda layer will fail!
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
DVA_input (Dense) (None, 512) 670720
_________________________________________________________________
dropout_3 (Dropout) (None, 512) 0
_________________________________________________________________
dense_3 (Dense) (None, 256) 131328
_________________________________________________________________
dropout_4 (Dropout) (None, 256) 0
_________________________________________________________________
dense_4 (Dense) (None, 128) 32896
_________________________________________________________________
dropout_5 (Dropout) (None, 128) 0
_________________________________________________________________
dense_5 (Dense) (None, 10) 1290
_________________________________________________________________
Predicted_Volume (Dense) (None, 1) 11
=================================================================
Total params: 836,245
Trainable params: 836,245
Non-trainable params: 0
_________________________________________________________________
Traceback (most recent call last):
File "<ipython-input-1-f9d072fc6a73>", line 19, in <module>
onnx_model = keras2onnx.convert_keras(model)
File "C:\Users\JTBLONIGAN\AppData\Local\Continuum\anaconda3\envs\Keras-GPU\lib\site-packages\keras2onnx\main.py", line 67, in convert_keras
" Please set environment variable TF_KERAS = 1.")
Exception: This is a tensorflow keras model, but keras standalone converter is used. Please set environment variable TF_KERAS = 1.
我尝试使用带注释的行
os.environ["TF_KERAS"]='1' but nothing seemed to happen.
有没有人遇到过这个问题或知道如何更改该变量以转换模型？感谢任何帮助。
keras2onnx==1.6.0
Keras==2.2.4
onnx==1.6.0
tensorflow==2.0.0
应该在导入模块之前设置环境变量，因为模块会在import时检查变量：
import os
os.environ['TF_KERAS'] = '1'
import onnx
本文收集自互联网，转载请注明来源。
如有侵权，请联系[email protected] 删除。
我来说两句