[英]Missing layer in TFLite model after conversion
So I trained a model using tensorflow and python and now I'm trying to use it in a C++ program.因此,我使用 tensorflow 和 python 训练了 model,现在我正在尝试在 ZF6F87C9FDCF18B3C3FC9Z77F3 程序中使用它。 I use this code to convert my model to tflite (I don't have any error during the conversion):我使用此代码将我的 model 转换为 tflite(我在转换过程中没有任何错误):
model.load_weights('training_weights.h5', by_name=True)
model.save('saved_model/model')
converter = tf.lite.TFLiteConverter.from_saved_model("saved_model/model")
tflite_model = converter.convert()
with tf.io.gfile.GFile('model.tflite', 'wb') as f:
f.write(tflite_model)
Then I load the model in C++ and I try to use it but the output doesn't match the output of my network.然后我将 model 加载到 C++ 中并尝试使用它,但是 output 与 myDB31 的 Z78E6221F639ZF41 网络不匹配。 The last layers of the network, in python, are:网络的最后一层,在 python 中,是:
X = Lambda(lambda x: K.expand_dims(x, axis=2), name='deconv_expand_dim')(input_tensor)
X = Conv2DTranspose(filters, (kernel_size, 1), strides=(strides, 1), padding=padding,
activation=activation, kernel_initializer=kernel_initializer,
bias_initializer=bias_initializer, name='deconv')(X)
X = Lambda(lambda x: K.squeeze(x, axis=2), name='deconv_reduce_dim')(X)
and the last layers of the model loaded, in C++, are:在 C++ 中加载的 model 的最后一层是:
1227 model/deconv_expand_dim/ExpandDims;StatefulPartitionedCall/model/deconv_expand_dim/ExpandDims
1228 model/deconv/Shape;StatefulPartitionedCall/model/deconv/Shape
1229 model/deconv/strided_slice;StatefulPartitionedCall/model/deconv/strided_slice1
1230 model/deconv/strided_slice_1;StatefulPartitionedCall/model/deconv/strided_slice_1
1231 model/deconv/strided_slice_2;StatefulPartitionedCall/model/deconv/strided_slice_22
1232 model/deconv/stack;StatefulPartitionedCall/model/deconv/stack
1233 model/deconv/conv2d_transpose;StatefulPartitionedCall/model/deconv/conv2d_transpose1
1234 model/deconv/BiasAdd;StatefulPartitionedCall/model/deconv/BiasAdd
1235 Identity
I just did a for loop to interpreter->tensors_size() to list the layers.我刚刚做了一个 for 循环解释器->tensors_size()来列出图层。 Problems:问题:
Any help is greatly appreciated, thanks.非常感谢任何帮助,谢谢。
I think I found the reason why it doesn't work.我想我找到了它不起作用的原因。 As you can see in the last layer I use the operator:正如您在最后一层中看到的那样,我使用了运算符:
K.squeeze(x, axis=2)
which seems to not be supported yet with a specified axis ("tf.squeeze — As long as axis is not provided.", last-accessed:28 July 2020, link ).似乎尚不支持指定的轴(“tf.squeeze - 只要未提供轴。”,上次访问时间:2020 年 7 月 28 日, 链接)。
That is why I don't have the same output in C++ as in Python, Tensorflow Lite doesn't support my network for the moment. That is why I don't have the same output in C++ as in Python, Tensorflow Lite doesn't support my network for the moment.
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.