Input tensors to a Functional must come from `tf.keras.Input`.


attention_vector = np.mean(get_activations(m,
testing_inputs_1,
print_shape_only=True,
layer_name='attention_vec')[0], axis=2).squeeze()

funcs = [K.function([inp] + [K.learning_phase()], [out]) for out in outputs] # evaluation functions


ValueError: Input tensors to a Functional must come from `tf.keras.Input`. Received: 0 (missing previous layer metadata).








免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM