[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
这两周写代码遇到了一些问题，在训练深度学习模型时，出现损失不下降的问题。不同的state-of-art模型已经尝试很多种，损失一直维持在0.02～0.04；以下loss下降方法排除
model 影响。
<>损失下降方法原因
* 数据集不够，往往导致在此数据集上，不能很好的训练模型；或者训练样例特征太复杂，难以拟合。
* 学习率太高，loss肉眼可见的上下徘徊。
* batch size太大，导致loss上下徘徊，难以拟合。
* 尝试不同的优化器，SGD 、 Adam等。
* dropout用的太多了，适当减少。
* 训练时间不足。
<>个人心得：如果模型不能使得loss下降了。
第一反应应该是，要学习的特征太过复杂，简化要学习的特征。比如一张要训练矩阵为[16, 4, 64, 64, 64]的3D图像（batch
size、channel、width、height、depth），可以处理为4 * [16, 4, 64, 64, 16]
类似方法，还可以添加其他处理；也可以降低batch size。
第二反应是，学习率问题。给出一个初始学习率lr和lr_decay，在训练过程中进行学习率下降，下降方式也可以使用其他公式来代替。
''' lr = 0.01 lr_decay = 0.9 optimizer =
torch.optim.Adam(params=model.parameters(), lr=lr) ''' for epoch in range(
max_epoch): # training code... lr_ = lr * lr_decay for param_group in optimizer.
param_groups: param_group['lr'] = lr_ # code...
第三反应，batch size等问题，调参，不多说。
第四反应，还是看模型吧，dropout等问题，还是得看。
觉得有用就点个赞吧！
