简体繁体 English

验证损失和训练损失曲线，可以接受吗？

[英]Validation loss and training loss curve , is that acceptable?

原文 2020-06-26 22:06:55 1 1 python/ validation/ deep-learning/ conv-neural-network/ training-data

I applying epilepsy seizure prediction using CNN.我使用 CNN 应用癫痫发作预测。 This is a plot for validation loss and training loss.这是一个 plot 用于验证损失和训练损失。 I don't know whether this curve is acceptable or not.我不知道这条曲线是否可以接受。

Any help would be appreciated任何帮助，将不胜感激

1 个解决方案

Yes it's acceptable as long as increasing the number of epochs helps the validation loss to get lower beside there is no overfitting.是的，只要增加 epoch 的数量有助于验证损失在没有过度拟合的情况下降低，这是可以接受的。

训练和验证损失为零 - Training and validation loss is zero

训练损失高于验证损失 - Training loss higher than validation loss

计算验证损失与训练损失同时进行 - Compute validation loss in parallel with training loss

验证损失低于训练损失，并且 Keras 中的损失减少 - Validation loss being lower than training loss, and loss reduction in Keras

训练和验证损失和数据集大小 - Training & Validation loss and dataset size

训练和验证损失图含义 - Training and Validation Loss Graph Meaning

plot 训练和验证损失曲线？ - plot training and validation loss curves?

MLPRegressor 的训练和验证损失历史 - Training and validation loss history for MLPRegressor

在张量板上记录训练和验证损失 - Logging training and validation loss in tensorboard

绘制训练和验证的准确性和损失 - Plot training and validation accuracy and loss

暂无

暂无

声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 训练和验证损失为零 - Training and validation loss is zero 训练损失高于验证损失 - Training loss higher than validation loss 计算验证损失与训练损失同时进行 - Compute validation loss in parallel with training loss 验证损失低于训练损失，并且 Keras 中的损失减少 - Validation loss being lower than training loss, and loss reduction in Keras 训练和验证损失和数据集大小 - Training & Validation loss and dataset size 训练和验证损失图含义 - Training and Validation Loss Graph Meaning plot 训练和验证损失曲线？ - plot training and validation loss curves? MLPRegressor 的训练和验证损失历史 - Training and validation loss history for MLPRegressor 在张量板上记录训练和验证损失 - Logging training and validation loss in tensorboard 绘制训练和验证的准确性和损失 - Plot training and validation accuracy and loss

相关标签

粤ICP备18138465号 © 2020-2024 STACKOOM.COM