【发布时间】：2021-05-12 22:55:13
【问题描述】：
我正在尝试实现一个自回归 seq-2-seq RNN 来预测时间序列数据，as shown in this TensorFlow tutorial。该模型由一个自定义模型类组成，继承自tf.keras.Model，其代码可以在下面找到。我已将此模型用于时间序列预测，输入数据为 (15, 108) 数据集（维度：（序列长度，输入单位）），输出数据为 (10, 108) 数据集。
虽然训练成功，但我未能成功保存并重新加载模型以在测试集上评估先前训练的模型。我曾尝试在互联网上寻找解决方案，但没有一个到目前为止似乎有效。这可能是因为它是使用 Eager Execution 训练的自定义模型，因为多个线程无法解决在这些条件下保存模型的问题。
谁能给我一些关于如何解决这个问题的提示。非常感谢任何帮助，谢谢！
到目前为止，我已经使用tf.keras.models.load_model(filepath) 加载了模型，并尝试了以下保存选项。这两个选项的代码可以在下面找到：
- 使用
keras.callbacks.ModelCheckpoint函数保存。但是，只返回了一个 .ckpt.data-00000-of-00001 和一个 .ckpt.index 文件（因此没有 .meta 或 .pb 文件），我无法打开它们 - 使用
tf.saved_model.save函数保存并加载导致以下错误的模型：
WARNING:tensorflow:Looks like there is an object (perhaps variable or layer) that is shared between different layers/models. This may cause issues when restoring the variable values. Object: <tensorflow.python.keras.layers.recurrent_v2.GRUCell object at 0x7fac1c052eb8>
WARNING:tensorflow:Inconsistent references when loading the checkpoint into this object graph. Either the Trackable object references in the Python program have changed in an incompatible way, or the checkpoint was generated in an incompatible program.
Two checkpoint references resolved to different objects (<tensorflow.python.keras.layers.recurrent_v2.GRUCell object at 0x7fac20648048> and <tensorflow.python.keras.layers.recurrent_v2.GRUCell object at 0x7fac1c052eb8>).
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-7-ac3fac428428> in <module>()
1 model = '/content/drive/My Drive/Colab Notebooks/Master thesis/NN_data/saved_model/s-20210208-194847'
----> 2 new_model = tf.keras.models.load_model(model)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/save.py in load_model(filepath, custom_objects, compile, options)
210 if isinstance(filepath, six.string_types):
211 loader_impl.parse_saved_model(filepath)
--> 212 return saved_model_load.load(filepath, compile, options)
213
214 raise IOError(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/saved_model/load.py in load(path, compile, options)
142 for node_id, loaded_node in keras_loader.loaded_nodes.items():
143 nodes_to_load[keras_loader.get_path(node_id)] = loaded_node
--> 144 loaded = tf_load.load_partial(path, nodes_to_load, options=options)
145
146 # Finalize the loaded layers and remove the extra tracked dependencies.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/saved_model/load.py in load_partial(export_dir, filters, tags, options)
763 A dictionary mapping node paths from the filter to loaded objects.
764 """
--> 765 return load_internal(export_dir, tags, options, filters=filters)
766
767
/usr/local/lib/python3.6/dist-packages/tensorflow/python/saved_model/load.py in load_internal(export_dir, tags, options, loader_cls, filters)
888 try:
889 loader = loader_cls(object_graph_proto, saved_model_proto, export_dir,
--> 890 ckpt_options, filters)
891 except errors.NotFoundError as err:
892 raise FileNotFoundError(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/saved_model/load.py in __init__(self, object_graph_proto, saved_model_proto, export_dir, ckpt_options, filters)
159
160 self._load_all()
--> 161 self._restore_checkpoint()
162
163 for node in self._nodes:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/saved_model/load.py in _restore_checkpoint(self)
486 else:
487 load_status = saver.restore(variables_path, self._checkpoint_options)
--> 488 load_status.assert_existing_objects_matched()
489 checkpoint = load_status._checkpoint
490
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/util.py in assert_existing_objects_matched(self)
806 ("Some Python objects were not bound to checkpointed values, likely "
807 "due to changes in the Python program: %s") %
--> 808 (list(unused_python_objects),))
809 return self
810
AssertionError: Some Python objects were not bound to checkpointed values, likely due to changes in the Python program: [<tf.Variable 'gru_cell_2/bias:0' shape=(2, 648) dtype=float32, numpy=
array([[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.]], dtype=float32)>, <tf.Variable 'gru_cell_2/kernel:0' shape=(108, 648) dtype=float32, numpy=
array([[ 0.01252341, -0.08176371, -0.00800528, ..., 0.00473534,
-0.05456369, 0.00294461],
[-0.02453795, 0.018851 , 0.07198527, ..., 0.05603079,
-0.01973856, 0.06883802],
[-0.06897871, -0.05892187, 0.08031332, ..., 0.07844239,
-0.06783205, -0.04394536],
...,
[ 0.02367028, 0.07758808, -0.04011653, ..., -0.04074041,
-0.00352754, -0.03324065],
[ 0.08708382, -0.0113907 , -0.08592559, ..., -0.07780273,
-0.07923603, 0.0435034 ],
[-0.04890796, 0.03626117, 0.01753877, ..., -0.06336015,
-0.07234246, -0.05076948]], dtype=float32)>, <tf.Variable 'gru_cell_2/recurrent_kernel:0' shape=(216, 648) dtype=float32, numpy=
array([[ 0.03453588, 0.01778516, -0.0326081 , ..., -0.02686813,
0.05017178, 0.01470701],
[ 0.05364531, -0.02074206, -0.06292176, ..., -0.04883411,
-0.03006711, 0.03091787],
[ 0.03928262, 0.01209829, 0.01992464, ..., -0.01726807,
-0.04125096, 0.00977487],
...,
[ 0.03076804, 0.00477963, -0.03565286, ..., -0.00938745,
-0.06442262, -0.0124091 ],
[ 0.03680094, -0.04894238, 0.01765203, ..., -0.11990541,
-0.01906408, 0.10198548],
[ 0.00818893, -0.03801145, 0.10376499, ..., -0.01700275,
-0.02600842, -0.0169891 ]], dtype=float32)>]
用于（成功）训练和保存模型的缩短代码：
model = FeedBack(units=neurons, out_steps=output_len, num_features=108, act_dense=output_activation)
model.compile(loss=loss,optimizer=tf.optimizers.Adam(lr=lr), metrics=['mean_absolute_error', 'mean_absolute_percentage_error', keras.metrics.RootMeanSquaredError()])
cp_callback = keras.callbacks.ModelCheckpoint(filepath=checkpoint_path, save_best_only=True, verbose=0)
earlyStopping = keras.callbacks.EarlyStopping(monitor='val_loss', patience=6, verbose=0, min_delta=1e-9, mode='auto')
# OPTION 1: USE ModelCheckpoint
r = model.fit(x=train_x, y=train_y, batch_size=32, shuffle=False, epochs=1,validation_data = (test_x, test_y), callbacks=[earlyStopping, cp_callback], verbose=0)
# OPTION 2: USE tf.saved_model.save()
!mkdir -p saved_model
model.save('/content/drive/My Drive/Colab Notebooks/Master thesis/NN_data/saved_model/s-%s' % timestring)
tf.saved_model.save(model, '/content/drive/My Drive/Colab Notebooks/Master thesis/NN_data/saved_model/s-%s' % timestring)
这是构建模型时使用的代码：
class FeedBack(tf.keras.Model):
def __init__(self, units, out_steps, num_features, act_dense):
super().__init__()
self.out_steps = out_steps
self.units = units
self.num_features = num_features
self.act_dense = act_dense
self.gru_cell = tf.keras.layers.GRUCell(units)
# Also wrap the LSTMCell in an RNN to simplify the `warmup` method.
self.gru_rnn = tf.keras.layers.RNN(self.gru_cell, return_state=True)
self.dense = tf.keras.layers.Dense(num_features, activation=act_dense) #self.num_features?
def warmup(self, inputs):
# inputs.shape => (batch, time, features)
# x.shape => (batch, lstm_units)
x, state = self.gru_rnn(inputs)
# predictions.shape => (batch, features)
prediction = self.dense(x)
return prediction, state
def call(self, inputs, training=None):
# Use a TensorArray to capture dynamically unrolled outputs.
predictions = []
# Initialize the lstm state
prediction, state = self.warmup(inputs)
# Insert the first prediction
predictions.append(prediction)
# Run the rest of the prediction steps
for _ in range(1, self.out_steps):
# Use the last prediction as input.
x = prediction
# Execute one gru step.
x, state = self.gru_cell(x, states=state,
training=training)
# Convert the gru output to a prediction.
prediction = self.dense(x)
# Add the prediction to the output
predictions.append(prediction)
# predictions.shape => (time, batch, features)
predictions = tf.stack(predictions)
# predictions.shape => (batch, time, features)
predictions = tf.transpose(predictions, [1, 0, 2])
return predictions
【问题讨论】：
标签： python-3.x tensorflow keras deep-learning recurrent-neural-network