我嘗試為我的數(shù)據(jù)集訓(xùn)練 Keras R-FCN，我需要保存完整的模型，因為在完成之前我無法全部訓(xùn)練模型，所以當(dāng)我可以恢復(fù)訓(xùn)練時我需要恢復(fù)我的模型。但如果我減輕重量，我無法使用 modelCheckpoint 或 model.save 保存完整模型，只有代碼可以正常工作。我使用 TensorFlow-GPU 1.15.0 和 Keras 2.2.4File "/content/testing.py", line 130, in <module>    ses.run(main())  File "/content/testing.py", line 123, in main    layers='all')  File "/content/KerasRFCN/Model/Model.py", line 546, in train    use_multiprocessing=False,  File "/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py", line 91, in wrapper    return func(*args, **kwargs)  File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1418, in fit_generator    initial_epoch=initial_epoch)  File "/usr/local/lib/python3.6/dist-packages/keras/engine/training_generator.py", line 251, in fit_generator    callbacks.on_epoch_end(epoch, epoch_logs)  File "/usr/local/lib/python3.6/dist-packages/keras/callbacks.py", line 79, in on_epoch_end    callback.on_epoch_end(epoch, logs)  File "/usr/local/lib/python3.6/dist-packages/keras/callbacks.py", line 446, in on_epoch_end    self.model.save(filepath, overwrite=True)  File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 1090, in save    save_model(self, filepath, overwrite, include_optimizer)  File "/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py", line 382, in save_model    _serialize_model(model, f, include_optimizer)  File "/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py", line 83, in _serialize_model    model_config['config'] = model.get_config()  File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 931, in get_config    return copy.deepcopy(config)  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy    y = copier(x, memo)這是問題代碼：    h, w = K.shape(input_image)[1], K.shape(input_image)[2]    image_scale = K.cast(K.stack([h, w, h, w], axis=0), tf.float32)    gt_boxes = KL.Lambda(lambda x: x / image_scale)(input_gt_boxes)在我添加此代碼之前，我的模型工作正常并成功保存完整模型