Keras EfficientNet迁移学习代码示例不起作用
Keras EfficientNet迁移学习代码示例不起作用
提问于 2021-05-26 18:23:13
几个月来，我的代码一直运行得很好，但今天我意识到它不再工作了。在我的代码中，我只是复制-粘贴了这个keras代码示例：https://keras.io/examples/vision/image_classification_efficientnet_fine_tuning/#example-efficientnetb0-for-stanford-dogs
所以“我的”代码看起来像这样：
import tensorflow as tf
import keras
from keras.layers import *
from keras import Sequential
from keras.layers.experimental import preprocessing
from keras import layers
from tensorflow.keras.applications import EfficientNetB0
img_augmentation = Sequential(
[
preprocessing.RandomRotation(factor=0.15),
preprocessing.RandomTranslation(height_factor=0.1, width_factor=0.1),
preprocessing.RandomFlip(),
preprocessing.RandomContrast(factor=0.1),
],
name="img_augmentation",
)
inputs = layers.Input(shape=(224, 224, 3))
x = img_augmentation(inputs)
outputs = EfficientNetB0(include_top=True, weights=None, classes=5)(x)
model = tf.keras.Model(inputs, outputs)
model.compile(
optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"]
)然而，今天当我在我的colab中运行这个cell时，我收到了很多这样的警告：
WARNING:tensorflow:
The following Variables were used a Lambda layer's call (tf.compat.v1.nn.fused_batch_norm_422), but
are not present in its tracked objects:
<tf.Variable 'top_bn/gamma:0' shape=(1280,) dtype=float32>
<tf.Variable 'top_bn/beta:0' shape=(1280,) dtype=float32>
It is possible that this is intended behavior, but it is more likely
an omission. This is a strong indication that this layer should be
formulated as a subclassed Layer rather than a Lambda layer还有这个错误：
TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.我认为google colab更新了keras和tensorflow，现在它们都是2.5.0版本
我怎样才能让我的代码再次工作？
回答 2
Stack Overflow用户
回答已采纳
发布于 2021-05-26 19:52:13
您不应该将tf 2.x和独立的keras混用。你应该像下面这样导入你的库，这样你就不会有任何问题。
import tensorflow as tf
from tensorflow.keras.layers import *
from tensorflow.keras import Sequential
from tensorflow.keras.layers.experimental import preprocessing
from tensorflow.keras import layers
from tensorflow.keras.applications import EfficientNetB0
img_augmentation = Sequential(
[
preprocessing.RandomRotation(factor=0.15),
preprocessing.RandomTranslation(height_factor=0.1, width_factor=0.1),
preprocessing.RandomFlip(),
preprocessing.RandomContrast(factor=0.1),
],
name="img_augmentation",
)
inputs = layers.Input(shape=(224, 224, 3))
x = img_augmentation(inputs)
outputs = EfficientNetB0(include_top=True, weights=None, classes=5)(x)
model = tf.keras.Model(inputs, outputs)Stack Overflow用户
发布于 2021-05-26 19:41:36
所以经过一些研究，我意识到它来自于进口：
from tensorflow.keras.applications import EfficientNetB0我不知道为什么，但它没有抛出任何错误，而是破坏了整个代码。相反，我必须导入：
from keras.applications.efficientnet import EfficientNetB0而且它工作得很完美。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/67703023
复制相关文章
相似问题
腾讯云开发者
