Python 如何正确保存模型以继续培训keras中的VAE
我使用函数API在keras中构建了VAE。VAE有3种型号:Python 如何正确保存模型以继续培训keras中的VAE,python,keras,deep-learning,autoencoder,Python,Keras,Deep Learning,Autoencoder,我使用函数API在keras中构建了VAE。VAE有3种型号: 编码器 译码器 我使用ModelCheckpoint回调在每个历元之后保存整个模型 checkpoint_model = ModelCheckpoint(os.path.join(save_path, "model.h5"), verbose=1) 但是当我用load_模型加载模型时 def load_trained_model(self, load_path, r_loss_factor):
checkpoint_model = ModelCheckpoint(os.path.join(save_path, "model.h5"), verbose=1)
但是当我用load_模型加载模型时
def load_trained_model(self, load_path, r_loss_factor):
self.model = load_model(os.path.join(load_path, "model.h5"), custom_objects={"loss": self.penalized_loss(r_loss_factor),"sample_latent_space":self.sample_latent_space})
再次调用fit_generator继续培训,我发现以下错误:
InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: You must feed a value for placeholder tensor 'images' with dtype float and shape [?,128,128,3]
[[{{node images}}]]
[[metrics_1/loss_1/Identity/_1971]]
(1) Invalid argument: You must feed a value for placeholder tensor 'images' with dtype float and shape [?,128,128,3]
[[{{node images}}]]
可以找到代码您使用的是哪个版本的tensorflow?我使用的是1.15.2Hi,您链接的代码非常长,需要花费大量时间来详细查看。如果你能在你的问题文本中加入一个小的、可复制的例子,这将非常有帮助。当然,你链接的笔记本中没有问题,它不会产生与你在本帖中提到的相同的错误,是吗?你使用的是tensorflow的哪个版本?我使用的是1.15.2Hi,您链接的代码非常长,需要花费大量时间来详细查看。如果你能在你的问题文本中加入一个小的、可复制的例子,这将非常有帮助。当然,你链接的笔记本中没有问题,它不会产生与你在本帖中提到的相同的错误,是吗?
checkpoint_model = ModelCheckpoint(os.path.join(save_path, "model.h5"), verbose=1)
def load_trained_model(self, load_path, r_loss_factor):
self.model = load_model(os.path.join(load_path, "model.h5"), custom_objects={"loss": self.penalized_loss(r_loss_factor),"sample_latent_space":self.sample_latent_space})
InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: You must feed a value for placeholder tensor 'images' with dtype float and shape [?,128,128,3]
[[{{node images}}]]
[[metrics_1/loss_1/Identity/_1971]]
(1) Invalid argument: You must feed a value for placeholder tensor 'images' with dtype float and shape [?,128,128,3]
[[{{node images}}]]