【问题标题】:Getting the message 'Cleanup called...' repeatedly while training a model on kaggle. How can we get rid of this? (CNN model using Keras)在 kaggle 上训练模型时反复收到消息“清理调用...”。我们怎样才能摆脱这个? (使用 Keras 的 CNN 模型)
【发布时间】:2022-08-06 10:04:53
【问题描述】:
model.compile(optimizer=\'adam\',loss=\'categorical_crossentropy\', metrics=[\'accuracy\'])

history = model.fit(train_data,epochs = 1,validation_data = test_data,verbose=1, callbacks =[earlystopping, csv_logger])

9/87606 [..............................] - ETA: 20:44 - loss: 0.2311 - accuracy: 0.8889 

Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
Cleanup called...
  • 请澄清您的具体问题或提供其他详细信息以准确突出您的需求。正如它目前所写的那样,很难准确地说出你在问什么。

标签: tensorflow keras deep-learning conv-neural-network kaggle


【解决方案1】:

我在 Kaggle 上找到了this,它对我有用。 只需粘贴下面的代码,它也应该对您有用。

from IPython.display import clear_output

!pip install -q tensorflow==2.4.1

clear_output()

【讨论】:

    【解决方案2】:

    这实际上是在 TensorFlow 中显示的调试消息。尝试下面的代码来禁用它。

    import tensorflow as tf
    
    tf.get_logger().setLevel('INFO')*
    

    【讨论】:

      最近更新 更多