我想從頭開始重新訓(xùn)練 Keras 模型 Inception_v3。該模型在這里定義： https ://github.com/keras-team/keras-applications/blob/master/keras_applications/inception_v3.py看了一些帖子，列出的解決方案是：凍結(jié)圖層（這不是我想要的......）for layer in model.layers:    layer.trainable = Falsehttps://stackoverflow.com/a/51727616/7748163通過檢查初始化器來重置所有層：def reset_weights(model):    session = K.get_session()    for layer in model.layers:         if hasattr(layer, 'kernel_initializer'):            layer.kernel_initializer.run(session=session)        if hasattr(layer, 'bias_initializer'):            layer.bias_initializer.run(session=session)     采用tf.variables_initializer  model = InceptionV3()  for layer in model.layers:      sess.run(tf.variables_initializer(layer.weights))參考：https ://stackoverflow.com/a/56634827/7748163我認(rèn)為最好的一個(gè)，但它引發(fā)了一個(gè)錯(cuò)誤。sess = tf.Session()for layer in model.layers:      for v in layer.__dict__:         v_arg = getattr(layer,v)         if hasattr(v_arg,'initializer'):             initializer_method = getattr(v_arg, 'initializer')             initializer_method.run(session=sess)             print('reinitializing layer {}.{}'.format(layer.name, v))但是，它們都不適用于 Inception_v3。錯(cuò)誤信息適用于 BatchNorm 層：tensorflow.python.framework.errors_impl.FailedPreconditionError: Error while reading resource variable batch_normalization_9/moving_mean from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/batch_normalization_9/moving_mean/N10tensorflow3VarE does not exist.     [[{{node batch_normalization_9_1/AssignMovingAvg/ReadVariableOp}}]]     [[metrics_1/categorical_accuracy/Identity/_469]]那么，如何重新訓(xùn)練現(xiàn)有的 Keras 模型，并初始化變量呢？從 Keras 應(yīng)用程序重新訓(xùn)練模型的最佳實(shí)踐是什么？進(jìn)一步討論：https://github.com/keras-team/keras/issues/341