Я добавляю этот код на этот . Это модель
resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='grpc://' + os.environ['COLAB_TPU_ADDR'])
tf.config.experimental_connect_to_cluster(resolver)
tf.tpu.experimental.initialize_tpu_system(resolver)
strategy = tf.distribute.experimental.TPUStrategy(resolver)
with strategy.scope():
model = Model(inputs=[encoder_input, decoder_input], outputs=[output])
model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
Ошибка:
ValueError Traceback (most recent call last)
<ipython-input-6-66476e79d8c4> in <module>()
501 build_params(input_data = input_data, output_data = output_data, params_path = 'params', max_lenghts=(10, 10))
502
--> 503 model, params = build_model(params_path='params')
504
505 input_data, output_data = convert_training_data(input_data, output_data, params)
2 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, distribute, **kwargs)
398 'with strategy.scope():\n'
399 ' model=_create_model()\n'
--> 400 ' model.compile(...)'% (v, strategy))
401
402 @trackable.no_automatic_dependency_tracking
ValueError: Variable (<tf.Variable 'embedding_2_1/embeddings:0' shape=(39, 128) dtype=float32>) was not created in the distribution strategy scope of (<tensorflow.python.distribute.tpu_strategy.TPUStrategyV1 object at 0x7f9e623bef98>). It is most likely due to not all layers or the model or optimizer being created outside the distribution strategy scope. Try to make sure your code looks similar to the following.
with strategy.scope():
model=_create_model()
model.compile(...)
Я добавляю код ТПУ после. Это порядковый код: