我已经用Model.save()
训练并保存了模型,它工作正常,并将模型保存在我的设备上。
然后我试着把它装上
siamese_model = tf.keras.models.load_model('siamesemodelv2.h5',custom_objects={'L1Dist':L1Dist,'BinaryCrossentropy':tf.losses.BinaryCrossentropy})
我必须通过L1Dist
课程
这是我们的课堂
class L1Dist(Layer):
# Init method - inheritance
def __init__(self, **kwargs):
super().__init__()
# similarity calculation
def call(self, input_embedding, validation_embedding):
return tf.math.abs(input_embedding - validation_embedding)
当我运行代码时,它显示此错误
> File "c:/Users/xa3/Desktop/face-recogntion.py", line 383, in <module>
siamese_model = tf.keras.models.load_model('siamesemodelv2.h5',custom_objects={'L1Dist':L1Dist,'BinaryCrossentropy':tf.losses.BinaryCrossentropy})
File "C:\Users\xa3\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\xa3\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\keras\engine\functional.py", line 1392, in process_node
inbound_node = inbound_layer._inbound_nodes[inbound_node_index]
IndexError: list index out of range
有什么想法吗?非常感谢
1条答案
按热度按时间zqry0prt1#
我通过将Tenserflow版本降级到2.4.1修复了它