本文讨论了在训练ImageNet数据集时遇到的问题及解决方案，包括如何选择合适的批次大小、调整随机梯度下降参数以优化模型训练过程，以及在有限内存条件下进行有效训练的方法。
- Implement the model that won the classification task of ImageNet 2013 #33
- choosing batch sizes and tuning sgd #218
- Training imagenet: loss does not decrease #401
- How to train imagenet with reduced memory and batch size? #430
- Again: Training imagenet: loss does not decrease #3243
Originally base_lr = 0.01 with batch_size=128, we have also used with batch_size=256 and still works. In theory when you reduce the batch_size by a factor of X then you should increase the base_lr by a factor of sqrt(X), but Alex have used a factor of X (see http://arxiv.org/abs/1404.5997)
by sguada
扫一扫
3545
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
