Q&A
前提・実現したいこと
kerasでLambdaレイヤーを作成しています。
backend.switch中のbackend.concatenateでkeras.backend.zerosを使った行列を結合したmodelをgoogle colaboratory のtpuで実行する際に以下のエラーが発生します。
modelを作成する時点では発生しません。
発生している問題・エラーメッセージ
ERROR:tensorflow:================================== Object was never used (type <class 'tensorflow.python.framework.ops.Tensor'>): <tf.Tensor 'VarIsInitializedOp_2:0' shape=() dtype=bool> If you want to mark it as used call its "mark_used()" method. It was originally created here: File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/usr/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in <module> app.launch_new_instance() File "/usr/local/lib/python3.6/dist-packages/traitlets/config/application.py", line 658, in launch_instance app.start() File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelapp.py", line 477, in start ioloop.IOLoop.instance().start() File "/usr/local/lib/python3.6/dist-packages/tornado/ioloop.py", line 888, in start handler_func(fd_obj, events) File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper return fn(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events self._handle_recv() File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv self._run_callback(callback, msg) File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback callback(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper return fn(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher return self.dispatch_shell(stream, msg) File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell handler(stream, idents, msg) File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request user_expressions, allow_stdin) File "/usr/local/lib/python3.6/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute res = shell.run_cell(code, store_history=store_history, silent=silent) File "/usr/local/lib/python3.6/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell interactivity=interactivity, compiler=compiler, result=result) File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes if self.run_code(code, result): File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "<ipython-input-179-6b78e8192dae>", line 43, in <module> model = tf.contrib.tpu.keras_to_tpu_model(model, strategy=strategy) File "/usr/local/lib/python3.6/dist-packages/tensorflow/contrib/framework/python/framework/experimental.py", line 64, in new_func return func(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/contrib/tpu/python/tpu/keras_support.py", line 2221, in tpu_model model_weights = model.get_weights() File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/network.py", line 392, in get_weights return backend.batch_get_value(weights) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py", line 2819, in batch_get_value return get_session().run(tensors) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py", line 482, in get_session _initialize_variables(session) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py", line 758, in _initialize_variables [variables_module.is_variable_initialized(v) for v in candidate_vars]) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py", line 758, in <listcomp> [variables_module.is_variable_initialized(v) for v in candidate_vars]) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped return _add_should_use_warning(fn(*args, **kwargs))
tensorflowで置き換えた場合に発生している問題・エラーメッセージ
InvalidArgumentError: Combined status information from 9 operations: Status code: Invalid argument [9x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_0/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_1/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_2/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_3/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_4/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_5/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_6/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,128,128,3] [[{{node input_1}}]] [[{{node GroupCrossDeviceControlEdges_7/TPUReplicate/_compile/_6611770376868054350/_423}}]] [1x] (0 successful operations.)
該当のソースコード
batch_size = tf.shape(x)[0] #K.switchで実行する関数 lambda: K.concatenate([x,K.zeros((batch_size,1))], axis=-1), lambda: K.concatenate([x,K.ones((batch_size,1))], axis=-1)
試したこと
上記を
lambda: x
にした場合はエラーが発生しなかったので原因はzerosではないかと思いますが、それ以上はわかりませんでした。
補足情報（FW/ツールのバージョンなど）
tensowflowのバージョンは最新でした。
以下のようにtensowflowで置き換えた場合は二番目のエラーが発生しました。
lambda: tf.concat([x,tf.zeros((batch_size, 1))],1)
あなたの回答
tips
プレビュー
