Question

我在Ubuntu 16.04上使用TF 1.10.0。

我正在使用Estimator API构建语言模型，并希望保留最后的隐藏状态以初始化下一批的状态。看起来像这样（参考：https://stackoverflow.com/a/41240243/6948766）：

        init_state = get_state_variables(params.batch_size, lstm_cell)

        # list of [batch_size, max_steps, lstm_dim]
        with tf.variable_scope(direction):
            _lstm_output_unpacked, final_state = tf.nn.static_rnn(
                lstm_cell,
                tf.unstack(lstm_input, axis=1),
                initial_state=init_state,
                dtype=DTYPE)

        self.state_update_op.append(
            get_state_update_op(init_state, final_state))

培训代码如下：

dist_trategy = tf.contrib.distribute.MirroredStrategy()
run_config = tf.estimator.RunConfig(
    train_distribute=dist_trategy)
estimator = tf.estimator.Estimator(model_fn=model.model_fn,
                                   model_dir='model/',
                                   params=params,
                                   config=run_config)

但是我遇到以下错误：

Traceback (most recent call last):
File "src/train_eval.py", line 64, in <module>
    main()
File "src/train_eval.py", line 60, in main
    run(p, arg.mode)
File "src/train_eval.py", line 47, in run
    params, 'train'), max_steps=1000000)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 356, in train
    loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 1179, in _train_model
    return self._train_model_distributed(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 1290, in _train_model_distributed
    self.config)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/distribute.py", line 718, in call_for_each_tower
    return self._call_for_each_tower(fn, *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/distribute/python/mirrored_strategy.py", line 552, in _call_for_each_tower
    return _call_for_each_tower(self, fn, *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/distribute/python/mirrored_strategy.py", line 183, in _call_for_each_tower
    coord.join(threads)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/coordinator.py", line 389, in join
    six.reraise(*self._exc_info_to_raise)
File "/usr/local/lib/python3.5/dist-packages/six.py", line 693, in reraise
    raise value
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/coordinator.py", line 297, in stop_on_exception
    yield
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/distribute/python/mirrored_strategy.py", line 166, in _call_for_each_tower
    merge_args = values.regroup({t.device: t.merge_args for t in threads})
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/distribute/python/values.py", line 585, in regroup
    for i in range(len(v0)))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/distribute/python/values.py", line 585, in <genexpr>
    for i in range(len(v0)))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/distribute/python/values.py", line 576, in regroup
    (len(v), len(v0), v, v0))
AssertionError: len(v) == 33, len(v0) == 2, v: [(<tensorflow.python.framework.ops.IndexedSlices object at 0x7fe818e9c518>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'char_embed/replica_3:0' shape=(11204, 64) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'char_embed/replica_2:0' shape=(11204, 64) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'char_embed:0' shape=(11204, 64) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'char_embed/replica_1:0' shape=(11204, 64) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_1:0' shape=(1, 1, 64, 32) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_0/replica_3:0' shape=(1, 1, 64, 32) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_0/replica_2:0' shape=(1, 1, 64, 32) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_0:0' shape=(1, 1, 64, 32) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_0/replica_1:0' shape=(1, 1, 64, 32) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_2:0' shape=(32,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_0/replica_3:0' shape=(32,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_0/replica_2:0' shape=(32,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_0:0' shape=(32,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_0/replica_1:0' shape=(32,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_3:0' shape=(1, 2, 64, 32) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_1/replica_3:0' shape=(1, 2, 64, 32) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_1/replica_2:0' shape=(1, 2, 64, 32) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_1:0' shape=(1, 2, 64, 32) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_1/replica_1:0' shape=(1, 2, 64, 32) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_4:0' shape=(32,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_1/replica_3:0' shape=(32,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_1/replica_2:0' shape=(32,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_1:0' shape=(32,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_1/replica_1:0' shape=(32,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_5:0' shape=(1, 3, 64, 64) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_2/replica_3:0' shape=(1, 3, 64, 64) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_2/replica_2:0' shape=(1, 3, 64, 64) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_2:0' shape=(1, 3, 64, 64) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_2/replica_1:0' shape=(1, 3, 64, 64) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_6:0' shape=(64,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_2/replica_3:0' shape=(64,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_2/replica_2:0' shape=(64,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_2:0' shape=(64,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_2/replica_1:0' shape=(64,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_7:0' shape=(1, 4, 64, 128) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_3/replica_3:0' shape=(1, 4, 64, 128) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_3/replica_2:0' shape=(1, 4, 64, 128) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_3:0' shape=(1, 4, 64, 128) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_3/replica_1:0' shape=(1, 4, 64, 128) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_8:0' shape=(128,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_3/replica_3:0' shape=(128,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_3/replica_2:0' shape=(128,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_3:0' shape=(128,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_3/replica_1:0' shape=(128,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_9:0' shape=(1, 5, 64, 256) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_4/replica_3:0' shape=(1, 5, 64, 256) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_4/replica_2:0' shape=(1, 5, 64, 256) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_4:0' shape=(1, 5, 64, 256) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_4/replica_1:0' shape=(1, 5, 64, 256) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_10:0' shape=(256,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_4/replica_3:0' shape=(256,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_4/replica_2:0' shape=(256,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_4:0' shape=(256,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_4/replica_1:0' shape=(256,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_11:0' shape=(1, 6, 64, 512) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_5/replica_3:0' shape=(1, 6, 64, 512) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_5/replica_2:0' shape=(1, 6, 64, 512) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_5:0' shape=(1, 6, 64, 512) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_5/replica_1:0' shape=(1, 6, 64, 512) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_12:0' shape=(512,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_5/replica_3:0' shape=(512,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_5/replica_2:0' shape=(512,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_5:0' shape=(512,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_5/replica_1:0' shape=(512,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_13:0' shape=(1, 7, 64, 1024) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/W_cnn_6/replica_3:0' shape=(1, 7, 64, 1024) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/W_cnn_6/replica_2:0' shape=(1, 7, 64, 1024) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/W_cnn_6:0' shape=(1, 7, 64, 1024) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/W_cnn_6/replica_1:0' shape=(1, 7, 64, 1024) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_14:0' shape=(1024,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN/b_cnn_6/replica_3:0' shape=(1024,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN/b_cnn_6/replica_2:0' shape=(1024,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN/b_cnn_6:0' shape=(1024,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN/b_cnn_6/replica_1:0' shape=(1024,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_15:0' shape=(2048, 512) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_proj/W_proj/replica_3:0' shape=(2048, 512) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_proj/W_proj/replica_2:0' shape=(2048, 512) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_proj/W_proj:0' shape=(2048, 512) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_proj/W_proj/replica_1:0' shape=(2048, 512) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_16:0' shape=(512,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_proj/b_proj/replica_3:0' shape=(512,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_proj/b_proj/replica_2:0' shape=(512,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_proj/b_proj:0' shape=(512,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_proj/b_proj/replica_1:0' shape=(512,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_17:0' shape=(2048, 2048) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_0/W_carry/replica_3:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_0/W_carry/replica_2:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_0/W_carry:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_0/W_carry/replica_1:0' shape=(2048, 2048) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_18:0' shape=(2048,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_0/b_carry/replica_3:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_0/b_carry/replica_2:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_0/b_carry:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_0/b_carry/replica_1:0' shape=(2048,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_19:0' shape=(2048, 2048) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_0/W_transform/replica_3:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_0/W_transform/replica_2:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_0/W_transform:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_0/W_transform/replica_1:0' shape=(2048, 2048) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_20:0' shape=(2048,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_0/b_transform/replica_3:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_0/b_transform/replica_2:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_0/b_transform:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_0/b_transform/replica_1:0' shape=(2048,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_21:0' shape=(2048, 2048) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_1/W_carry/replica_3:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_1/W_carry/replica_2:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_1/W_carry:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_1/W_carry/replica_1:0' shape=(2048, 2048) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_22:0' shape=(2048,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_1/b_carry/replica_3:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_1/b_carry/replica_2:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_1/b_carry:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_1/b_carry/replica_1:0' shape=(2048,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_23:0' shape=(2048, 2048) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_1/W_transform/replica_3:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_1/W_transform/replica_2:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_1/W_transform:0' shape=(2048, 2048) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_1/W_transform/replica_1:0' shape=(2048, 2048) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_24:0' shape=(2048,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'CNN_high_1/b_transform/replica_3:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'CNN_high_1/b_transform/replica_2:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'CNN_high_1/b_transform:0' shape=(2048,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'CNN_high_1/b_transform/replica_1:0' shape=(2048,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_25:0' shape=(1024, 16384) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/kernel/replica_3:0' shape=(1024, 16384) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/kernel/replica_2:0' shape=(1024, 16384) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/kernel:0' shape=(1024, 16384) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/kernel/replica_1:0' shape=(1024, 16384) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_26:0' shape=(16384,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/bias/replica_3:0' shape=(16384,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/bias/replica_2:0' shape=(16384,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/bias:0' shape=(16384,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/bias/replica_1:0' shape=(16384,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_27:0' shape=(4096, 512) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/projection/kernel/replica_3:0' shape=(4096, 512) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/projection/kernel/replica_2:0' shape=(4096, 512) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/projection/kernel:0' shape=(4096, 512) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_0/lstm_cell/projection/kernel/replica_1:0' shape=(4096, 512) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_28:0' shape=(1024, 16384) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/kernel/replica_3:0' shape=(1024, 16384) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/kernel/replica_2:0' shape=(1024, 16384) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/kernel:0' shape=(1024, 16384) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/kernel/replica_1:0' shape=(1024, 16384) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_29:0' shape=(16384,) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/bias/replica_3:0' shape=(16384,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/bias/replica_2:0' shape=(16384,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/bias:0' shape=(16384,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/bias/replica_1:0' shape=(16384,) dtype=float32>})), (<tf.Tensor 'clip_by_global_norm/clip_by_global_norm/_30:0' shape=(4096, 512) dtype=float32>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/projection/kernel/replica_3:0' shape=(4096, 512) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/projection/kernel/replica_2:0' shape=(4096, 512) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/projection/kernel:0' shape=(4096, 512) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'fw/rnn/multi_rnn_cell/cell_1/lstm_cell/projection/kernel/replica_1:0' shape=(4096, 512) dtype=float32>})), (<tensorflow.python.framework.ops.IndexedSlices object at 0x7fe818e9c390>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'softmax/W/replica_3:0' shape=(556527, 512) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'softmax/W/replica_2:0' shape=(556527, 512) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'softmax/W:0' shape=(556527, 512) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'softmax/W/replica_1:0' shape=(556527, 512) dtype=float32>})), (<tensorflow.python.framework.ops.IndexedSlices object at 0x7fe818e9c0b8>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'softmax/b/replica_3:0' shape=(556527,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'softmax/b/replica_2:0' shape=(556527,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'softmax/b:0' shape=(556527,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'softmax/b/replica_1:0' shape=(556527,) dtype=float32>}))], v0: [(<tensorflow.python.framework.ops.IndexedSlices object at 0x7fe8127cfe10>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'softmax/W/replica_3:0' shape=(556527, 512) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'softmax/W/replica_2:0' shape=(556527, 512) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'softmax/W:0' shape=(556527, 512) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'softmax/W/replica_1:0' shape=(556527, 512) dtype=float32>})), (<tensorflow.python.framework.ops.IndexedSlices object at 0x7fe8127cfe80>, MirroredVariable({'/replica:0/task:0/device:GPU:3': <tf.Variable 'softmax/b/replica_3:0' shape=(556527,) dtype=float32>, '/replica:0/task:0/device:GPU:2': <tf.Variable 'softmax/b/replica_2:0' shape=(556527,) dtype=float32>, '/replica:0/task:0/device:GPU:0': <tf.Variable 'softmax/b:0' shape=(556527,) dtype=float32>, '/replica:0/task:0/device:GPU:1': <tf.Variable 'softmax/b/replica_1:0' shape=(556527,) dtype=float32>}))]

谢谢。

Tensorflow估算器MirrorStrategy断言错误

0 个答案: