勉強していること

Google Magentaによる自動作曲について勉強しています。

困っていること・サポートしてほしいこと

  1. 実現したい事
    PythonのAI自動作曲ライブラリ”Magenta”のImprov RNNというモデルを実行し、Improv RNNが受け付ける入力ファイル(MusicXMLファイル)を学習させることで、音楽を生成したい。
    https://magenta.tensorflow.org/
    https://github.com/tensorflow/magenta/tree/master/magenta/models/improv_rnn

  2. 問題点
    下記ページREADMEの”Train your own”の章通りにコマンドを実行すると、Train and Evaluate the Modelのパートのコマンドで、学習が進まない。
    https://github.com/tensorflow/magenta/tree/master/magenta/models/improv_rnn
    その前パートであるCreate SequenceExamplesパートでの”improv_rnn_create_dataset”の実行結果が以下のように”Produced 0 outputs”となっていることが原因と想定している。(正常に学習できる場合はoutputsが1以上の数値になる。)

  3. バージョン情報
    tensorflow 1.15.2
    magenta 1.3.0

  4. 実行結果
    MYPC:~ MYNAME$ improv_rnn_create_dataset \

    --config=attention_improv \
    --input=/tmp/notesequences.tfrecord \
    --output_dir=/tmp/improv_rnn/sequence_examples \
    --eval_ratio=0.10

WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/pipelines/pipeline.py:310: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version.
Instructions for updating:
Use eager execution and:
tf.data.TFRecordDataset(path)
W0413 19:40:32.087490 4673121728 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/pipelines/pipeline.py:310: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version.
Instructions for updating:
Use eager execution and:
tf.data.TFRecordDataset(path)
INFO:tensorflow:

Completed.

I0413 19:40:32.111129 4673121728 pipeline.py:386]

Completed.

INFO:tensorflow:Processed 1 inputs total. Produced 0 outputs.
I0413 19:40:32.111304 4673121728 pipeline.py:388] Processed 1 inputs total. Produced 0 outputs.
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_coincident_chords: 0
I0413 19:40:32.111388 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_coincident_chords: 0
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_empty_chord_progressions: 1
I0413 19:40:32.111450 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_empty_chord_progressions: 1
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_melodies_discarded_too_few_pitches: 0
I0413 19:40:32.111505 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_melodies_discarded_too_few_pitches: 0
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_melodies_discarded_too_long: 0
I0413 19:40:32.111561 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_melodies_discarded_too_long: 0
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_melodies_discarded_too_short: 0
I0413 19:40:32.111615 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_melodies_discarded_too_short: 0
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_melodies_truncated: 1
I0413 19:40:32.111669 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_melodies_truncated: 1
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_melody_lengths_in_bars:
[30,40): 1
I0413 19:40:32.111738 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_melody_lengths_in_bars:
[30,40): 1
INFO:tensorflow:DAGPipeline_LeadSheetExtractor_training_polyphonic_tracks_discarded: 1
I0413 19:40:32.111804 4673121728 statistics.py:141] DAGPipeline_LeadSheetExtractor_training_polyphonic_tracks_discarded: 1
INFO:tensorflow:DAGPipeline_RandomPartition_training_lead_sheets_count: 1
I0413 19:40:32.111857 4673121728 statistics.py:141] DAGPipeline_RandomPartition_training_lead_sheets_count: 1

MYPC:~ MYNAME$ improv_rnn_train \

--config=attention_improv \
--run_dir=/tmp/improv_rnn/logdir/run1 \
--sequence_example_file=/tmp/improv_rnn/sequence_examples/training_lead_sheets.tfrecord \
--hparams="batch_size=64,rnn_layer_sizes=[64,64]" \
--num_training_steps=20000
INFO:tensorflow:hparams = {'batch_size': 64, 'rnn_layer_sizes': [64, 64], 'dropout_keep_prob': 0.5, 'attn_length': 40, 'clip_norm': 3, 'learning_rate': 0.001, 'residual_connections': False, 'use_cudnn': False}
I0413 19:40:48.031682 4447403456 events_rnn_graph.py:226] hparams = {'batch_size': 64, 'rnn_layer_sizes': [64, 64], 'dropout_keep_prob': 0.5, 'attn_length': 40, 'clip_norm': 3, 'learning_rate': 0.001, 'residual_connections': False, 'use_cudnn': False}
INFO:tensorflow:Train dir: /tmp/improv_rnn/logdir/run1/train
I0413 19:40:48.031980 4447403456 improv_rnn_train.py:85] Train dir: /tmp/improv_rnn/logdir/run1/train
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:66: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
W0413 19:40:48.032958 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:66: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:277: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
W0413 19:40:48.037178 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:277: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...).
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:189: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensors(tensor).repeat(num_epochs).
W0413 19:40:48.037853 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:189: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensors(tensor).repeat(num_epochs).
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:198: QueueRunner.init (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
W0413 19:40:48.039085 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:198: QueueRunner.init (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:198: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
W0413 19:40:48.039930 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:198: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:67: TFRecordReader.init (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.TFRecordDataset.
W0413 19:40:48.042600 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:67: TFRecordReader.init (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.TFRecordDataset.
INFO:tensorflow:Counting records in /tmp/improv_rnn/sequence_examples/training_lead_sheets.tfrecord.
I0413 19:40:48.048157 4447403456 sequence_example_lib.py:121] Counting records in /tmp/improv_rnn/sequence_examples/training_lead_sheets.tfrecord.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:122: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version.
Instructions for updating:
Use eager execution and:
tf.data.TFRecordDataset(path)
W0413 19:40:48.048295 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:122: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version.
Instructions for updating:
Use eager execution and:
tf.data.TFRecordDataset(path)
INFO:tensorflow:Total records: 0
I0413 19:40:48.056303 4447403456 sequence_example_lib.py:127] Total records: 0
INFO:tensorflow:[<tf.Tensor 'random_shuffle_queue_Dequeue:0' shape=(?, 123) dtype=float32>, <tf.Tensor 'random_shuffle_queue_Dequeue:1' shape=(?,) dtype=int64>, <tf.Tensor 'random_shuffle_queue_Dequeue:2' shape=() dtype=int32>]
I0413 19:40:48.059307 4447403456 sequence_example_lib.py:99] [<tf.Tensor 'random_shuffle_queue_Dequeue:0' shape=(?, 123) dtype=float32>, <tf.Tensor 'random_shuffle_queue_Dequeue:1' shape=(?,) dtype=int64>, <tf.Tensor 'random_shuffle_queue_Dequeue:2' shape=() dtype=int32>]
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:106: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.batch(batch_size) (or padded_batch(...) if dynamic_pad=True).
W0413 19:40:48.059537 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/common/sequence_example_lib.py:106: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.batch(batch_size) (or padded_batch(...) if dynamic_pad=True).
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:57: BasicLSTMCell.init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
W0413 19:40:48.065620 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:57: BasicLSTMCell.init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:69: MultiRNNCell.init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.StackedRNNCells, and will be replaced by that in Tensorflow 2.0.
W0413 19:40:48.070829 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:69: MultiRNNCell.init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.StackedRNNCells, and will be replaced by that in Tensorflow 2.0.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:276: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use keras.layers.RNN(cell), which is equivalent to this API
W0413 19:40:48.093014 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:276: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use keras.layers.RNN(cell), which is equivalent to this API
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/contrib/rnn/python/ops/core_rnn_cell.py:104: calling Constant.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0413 19:40:48.266117 4447403456 deprecation.py:506] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/contrib/rnn/python/ops/core_rnn_cell.py:104: calling Constant.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:735: Layer.add_variable (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use layer.add_weight method instead.
W0413 19:40:48.272688 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:735: Layer.add_variable (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use layer.add_weight method instead.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:739: calling Zeros.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0413 19:40:48.279592 4447403456 deprecation.py:506] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:739: calling Zeros.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/ops/rnn.py:244: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0413 19:40:48.381036 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/ops/rnn.py:244: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/contrib/layers/python/layers/layers.py:1866: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use layer.__call__ method instead.
W0413 19:40:48.417146 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/contrib/layers/python/layers/layers.py:1866: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use layer.__call__ method instead.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:310: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
W0413 19:40:48.445690 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:310: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:323: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, there are two
options available in V2.

  • tf.py_function takes a python function which manipulates tf eager
    tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
    an ndarray (just call tensor.numpy()) but having access to eager tensors
    means tf.py_functions can use accelerators such as GPUs as well as
    being differentiable using a gradient tape.
  • tf.numpy_function maintains the semantics of the deprecated tf.py_func
    (it is not differentiable, and manipulates numpy arrays). It drops the
    stateful argument making all functions stateful.

W0413 19:40:48.449728 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/magenta/models/shared/events_rnn_graph.py:323: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, there are two
options available in V2.

  • tf.py_function takes a python function which manipulates tf eager
    tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
    an ndarray (just call tensor.numpy()) but having access to eager tensors
    means tf.py_functions can use accelerators such as GPUs as well as
    being differentiable using a gradient tape.
  • tf.numpy_function maintains the semantics of the deprecated tf.py_func
    (it is not differentiable, and manipulates numpy arrays). It drops the
    stateful argument making all functions stateful.

INFO:tensorflow:Starting training loop...
I0413 19:40:49.158061 4447403456 events_rnn_train.py:76] Starting training loop...
INFO:tensorflow:Create CheckpointSaverHook.
I0413 19:40:49.158285 4447403456 basic_session_run_hooks.py:541] Create CheckpointSaverHook.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
W0413 19:40:49.375016 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
INFO:tensorflow:Graph was finalized.
I0413 19:40:49.460250 4447403456 monitored_session.py:240] Graph was finalized.
2020-04-13 19:40:49.460742: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-04-13 19:40:49.473975: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9c2c8fb760 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-04-13 19:40:49.474014: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
INFO:tensorflow:Restoring parameters from /tmp/improv_rnn/logdir/run1/train/model.ckpt-20235
I0413 19:40:49.477298 4447403456 saver.py:1284] Restoring parameters from /tmp/improv_rnn/logdir/run1/train/model.ckpt-20235
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
W0413 19:40:49.603466 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
INFO:tensorflow:Running local_init_op.
I0413 19:40:49.692898 4447403456 session_manager.py:500] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I0413 19:40:49.730629 4447403456 session_manager.py:502] Done running local_init_op.
WARNING:tensorflow:From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/monitored_session.py:882: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
W0413 19:40:49.809328 4447403456 deprecation.py:323] From /Users/MYNAME/.pyenv/versions/miniconda3-4.3.30/envs/magenta/lib/python3.7/site-packages/tensorflow_core/python/training/monitored_session.py:882: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the tf.data module.
INFO:tensorflow:Saving checkpoints for 20235 into /tmp/improv_rnn/logdir/run1/train/model.ckpt.
I0413 19:40:50.742024 4447403456 basic_session_run_hooks.py:606] Saving checkpoints for 20235 into /tmp/improv_rnn/logdir/run1/train/model.ckpt.
= ここで処理が停止 =

予算

応相談
*音楽生成までにどの程度の時間を要するかご教示頂ければ予算をご連絡差し上げます。