Question

我遇到了问题。我正在尝试做的是建立一个深度学习神经网络。我创建了模型并对其进行了学习，但是训练完模型后我想做的是：我想加载最后一个模型（训练有素的模型）。

所以我尝试了这个：

# unique file name that will include the epoch and the validation acc for that epoch
filepath = "RNN_Final-{epoch:02d}-{val_acc:.3f}"

# saves only the best ones
checkpoint = ModelCheckpoint("/var/www/test.nl/models/{}.model".format(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max'))
last_model = "/var/www/test.nl/models/{}.model".format(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')

# Train model
history = model.fit(
    train_x, train_y,
    batch_size=BATCH_SIZE,
    epochs=EPOCHS,
    validation_data=(validation_x, validation_y),
    callbacks=[tensorboard, checkpoint])

new_model = tf.keras.models.load_model(last_model)
predictions = new.model.predict([train_x])

print(np.argmax(predictions[0]))

但这会尝试打开此文件：

Unable to open file (unable to open file: name = '/var/www/test.nl/models/RNN_Final-{epoch:02d}-{val_acc:.3f}.model', errno = 2, error message = 'No such file or directory'

我要打开的模型称为：

RNN_Final-30-0.555.model

那我在做什么错了？

Tensorflow将变量分配给最后保存的模型名称

0 个答案: