我在合作实验室制作了CNN，并在每个时期保存了模型。我导出了h5文件，现在尝试在一些测试图像上运行模型。这是主要错误：
ValueError: Unknown layer: Functional
这是我用来运行模型并在每个时期保存的代码：
epochs = 50
callbacks = [
tf.keras.callbacks.TensorBoard(log_dir='./logs'),
keras.callbacks.ModelCheckpoint("save_at_{epoch}.h5"),
]
model.compile(
optimizer=keras.optimizers.Adam(1e-3),
loss="binary_crossentropy",
metrics=["accuracy"],
)
model.fit(
train_ds, epochs=epochs, callbacks=callbacks, validation_data=val_ds,
)
模型运行后，我刚刚从colab侧边栏本地下载了h5文件。我从本地磁盘重新上传了文件，这是我尝试加载模型的方法：
# load and evaluate a saved model
from tensorflow.keras.models import load_model
# load model#
loaded_model = load_model('save_at_47.h5')
loaded_model.layers[0].input_shape
这是完整的追溯：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-4-6af7396280fa> in <module>()
3
4 # load model#
----> 5 loaded_model = load_model('save_at_47.h5')
6 loaded_model.layers[0].input_shape
5 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/save.py in load_model(filepath, custom_objects, compile)
182 if (h5py is not None and (
183 isinstance(filepath, h5py.File) or h5py.is_hdf5(filepath))):
--> 184 return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
185
186 if sys.version_info >= (3, 4) and isinstance(filepath, pathlib.Path):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/hdf5_format.py in load_model_from_hdf5(filepath, custom_objects, compile)
176 model_config = json.loads(model_config.decode('utf-8'))
177 model = model_config_lib.model_from_config(model_config,
--> 178 custom_objects=custom_objects)
179
180 # set weights
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/model_config.py in model_from_config(config, custom_objects)
53 '`Sequential.from_config(config)`?')
54 from tensorflow.python.keras.layers import deserialize # pylint: disable=g-import-not-at-top
---> 55 return deserialize(config, custom_objects=custom_objects)
56
57
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/serialization.py in deserialize(config, custom_objects)
107 module_objects=globs,
108 custom_objects=custom_objects,
--> 109 printable_module_name='layer')
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
360 config = identifier
361 (cls, cls_config) = class_and_config_for_serialized_keras_object(
--> 362 config, module_objects, custom_objects, printable_module_name)
363
364 if hasattr(cls, 'from_config'):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/generic_utils.py in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
319 cls = get_registered_object(class_name, custom_objects, module_objects)
320 if cls is None:
--> 321 raise ValueError('Unknown ' + printable_module_name + ': ' + class_name)
322
323 cls_config = config['config']
ValueError: Unknown layer: Functional
似乎有几个类似的questions here和here。更改导入方法仍无济于事，尝试创建一些kind of custom对象也没有任何作用。
答案 0 :(得分：6)
从头开始重建网络：
image_size = (212, 212)
batch_size = 32
data_augmentation = keras.Sequential(
[
layers.experimental.preprocessing.RandomFlip("horizontal_and_vertical"),
layers.experimental.preprocessing.RandomRotation(0.8),
]
)
def make_model(input_shape, num_classes):
inputs = keras.Input(shape=input_shape)
# Image augmentation block
x = data_augmentation(inputs)
# Entry block
x = layers.experimental.preprocessing.Rescaling(1.0 / 255)(x)
x = layers.Conv2D(32, 3, strides=2, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
x = layers.Conv2D(64, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
previous_block_activation = x # Set aside residual
for size in [128, 256, 512, 728]:
x = layers.Activation("relu")(x)
x = layers.SeparableConv2D(size, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
x = layers.SeparableConv2D(size, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.MaxPooling2D(3, strides=2, padding="same")(x)
# Project residual
residual = layers.Conv2D(size, 1, strides=2, padding="same")(
previous_block_activation
)
x = layers.add([x, residual]) # Add back residual
previous_block_activation = x # Set aside next residual
x = layers.SeparableConv2D(1024, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
x = layers.GlobalAveragePooling2D()(x)
if num_classes == 2:
activation = "sigmoid"
units = 1
else:
activation = "softmax"
units = num_classes
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(units, activation=activation)(x)
return keras.Model(inputs, outputs)
model = make_model(input_shape=image_size + (3,), num_classes=2)
keras.utils.plot_model(model, show_shapes=False)
加载权重：
model.load_weights('save_at_47.h5')
并对图像进行预测：
# Running inference on new data
img = keras.preprocessing.image.load_img(
"le_image.jpg", target_size=image_size
)
img_array = keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create batch axis
predictions = model.predict(img_array)
score = predictions[0]
print(
"This image is %.2f percent negative and %.2f percent positive."
% (100 * (1 - score), 100 * score)
)
答案 1 :(得分：3)
当我使用tf 2.3.0时，我遇到了同样的问题，我降级到tf 2.2.0，它可以正常工作
答案 2 :(得分：2)
在这里讨论救了我一些麻烦！我共享一个不同的解决方案，更容易为我做的。
和TF2.3之间TF2.2变化是相当轻微的。我用下T2.2下TF2.3我需要加载和火车书面model_config.yaml文件时有同样的错误。这两个版本用于与仅Conv2D层的模型结构中的差异是简单修复手动或使用的sed：
正如所看到的下面一个需要改变class_name: Functional {成{1}}，并除去配置class_name: Model是新在Conv2D和可能其他转化率的层。为了保持一致性我也末改变了keras版本。显然，这仅在组参数保留为 groups: 1 时才有效。
default: 1答案 3 :(得分：2)
如果您使用较旧的 TF（在我的情况下为 2.1.0）并尝试解压缩由较新的 TF（例如 2.4.1）打包的 h5 文件并遇到此错误，则以下技巧可能会很有用。
your_model = tf.keras.models.load_model(
path_to_h5,
custom_objects={'Functional':tf.keras.models.Model})
答案 4 :(得分：1)
在colab上使用tf 2.3训练模型并将tf 2.2加载到我的本地计算机中时，我遇到了同样的问题。解决方案是使用以下命令升级TensorFlow：
pip3 install --upgrade tensorflow
答案 5 :(得分：0)
例如，解决此错误的方法非常简单。原因是您已经在Tensorflow的“ 2.3.0”版本和Keras的“ 2.4.3”版本（在Colab或本地）上训练了模型。现在您可以通过Keras＆TensorFlow的另一个版本访问保存的模型（.h5）。它会给你错误。解决方案是重新训练带有升级版本的模型，或者将TF＆Keras降级为与训练模型相同的版本。