我在视频游戏数据集上训练了CARCA(Context and Attribute-Aware Sequential Recommendation via Cross-Attention)。我保存了1个epoch后的会话，并尝试恢复会话，因为所有的架构都是使用会话的概念编写的。我使用tf.train.Saver().save()方法保存了会话。

session_saver = tf.train.Saver(save_relative_paths=True)
session_output_path = os.path.join(args.output_dir, "epochs_"+str(epoch))
if not os.path.isdir(session_output_path):
    os.makedirs(session_output_path)# make directory if not exists
session_saver.save(sess, session_output_path+"/carca_model")
print(f"[INFO]: Save the model after epochs: {epoch}")

字符串
然后，我使用以下命令恢复会话：

saver = tf.train.import_meta_graph(session_dir +"carca_model.meta")
saver.restore(sess, tf.train.latest_checkpoint(session_dir))

型
我尝试使用恢复的会话会话对新数据集进行预测，但我遇到了Attempting to use uninitialized value error。完整的错误是：

Traceback (most recent call last):
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1356, in _do_call
    return fn(*args)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1341, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value num_blocks_2/multihead_attention/conv1d_1/kernel_1
         [[{{node num_blocks_2/multihead_attention/conv1d_1/kernel_1/read}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "CARCA_train.py", line 1441, in <module>
    get_load_model_and_inference(dataset, usernum, itemnum, args, ItemFeatures, UserFeatures, CXTDict)
  File "CARCA_train.py", line 1317, in get_load_model_and_inference
    predictions = -model.predict(sess, np.ones(args.maxlen)*u, [seq], item_idx, [seqcxt], testitemscxt)
  File "CARCA_train.py", line 976, in predict
    {self.test_user: u, self.input_seq: seq, self.test_item: item_idx, self.is_training: False, self.seq_cxt:seqcxt, self.test_item_cxt:testitemcxt})
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 950, in run
    run_metadata_ptr)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1173, in _run
    feed_dict_tensor, options, run_metadata)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run
    run_metadata)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value num_blocks_2/multihead_attention/conv1d_1/kernel_1
         [[node num_blocks_2/multihead_attention/conv1d_1/kernel_1/read (defined at CARCA_train.py:670) ]]

Original stack trace for 'num_blocks_2/multihead_attention/conv1d_1/kernel_1/read':
  File "CARCA_train.py", line 1441, in <module>
    get_load_model_and_inference(dataset, usernum, itemnum, args, ItemFeatures, UserFeatures, CXTDict)
  File "CARCA_train.py", line 1266, in get_load_model_and_inference
    model = Model(usernum, itemnum, args, ItemFeatures, UserFeatures, cxt_size = cxt_size ,use_res = True)
  File "CARCA_train.py", line 768, in __init__
    dropout_rate=args.dropout_rate, is_training=self.is_training)
  File "CARCA_train.py", line 670, in feedforward
    outputs = tf.layers.conv1d(**params)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/layers/convolutional.py", line 218, in conv1d
    return layer.apply(inputs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1479, in apply
    return self.__call__(inputs, *args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/layers/base.py", line 537, in __call__
    outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 591, in __call__
    self._maybe_build(inputs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1881, in _maybe_build
    self.build(input_shapes)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/keras/layers/convolutional.py", line 165, in build
    dtype=self.dtype)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/layers/base.py", line 450, in add_weight
    **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 384, in add_weight
    aggregation=aggregation)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py", line 663, in _add_variable_with_custom_getter
    **kwargs_for_getter)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1496, in get_variable
    aggregation=aggregation)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1239, in get_variable
    aggregation=aggregation)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py", line 562, in get_variable
    aggregation=aggregation)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py", line 514, in _true_getter
    aggregation=aggregation)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py", line 929, in _get_single_variable
    aggregation=aggregation)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variables.py", line 259, in __call__
    return cls._variable_v1_call(*args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variables.py", line 220, in _variable_v1_call
    shape=shape)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variables.py", line 198, in <lambda>
    previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py", line 2511, in default_variable_creator
    shape=shape)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variables.py", line 263, in __call__
    return super(VariableMetaclass, cls).__call__(*args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variables.py", line 1568, in __init__
    shape=shape)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/variables.py", line 1755, in _init_from_args
    self._snapshot = array_ops.identity(self._variable, name="read")
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py", line 180, in wrapper
    return target(*args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/array_ops.py", line 86, in identity
    ret = gen_array_ops.identity(input, name=name)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 4253, in identity
    "Identity", input=input, name=name)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
    op_def=op_def)
  File "/home/zakipoint/miniconda3/envs/sequential_recommendation_carca/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 2005, in __init__
    self._traceback = tf_stack.extract_stack()

型
我还检查了存储会话和训练后会话中的变量。两个输出似乎相似。我被这个问题卡住了几天，也测试了使用tf.saved_model.builder.SavedModelBuilder()保存模型和使用tf.saved_model.loader.load()恢复模型，但没有解决这个问题。目前，我使用tensorflow 1.14。谢谢你，谢谢