# How to determine the sample weights for the loss function **URL:** \ **Category:** Structuring Machine Learning Projects\ **Tags:** coursera-platform\ **Created:** [July 19, 2021, 8:23am UTC](https://community.deeplearning.ai/t/how-to-determine-the-sample-weights-for-the-loss-function/21968 "2021-07-19T08:23:21Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![andree](https://avatars.discourse-cdn.com/v4/letter/a/b4bc9f/32.png) [@andree](https://community.deeplearning.ai/u/andree)\ **Post date:** [July 19, 2021, 8:23am UTC](https://community.deeplearning.ai/t/how-to-determine-the-sample-weights-for-the-loss-function/21968/1 "2021-07-19T08:23:21Z")
In the video ’ When to Change Dev/Test Sets and Metrics?’ A.N. talks about weighting the samples by a factor of w(i). For example giving porn images weight 1 and normal 10. Then using these weights in training within the loss function. But how to determine these weights? Are you suggesting to train a porn/not-porn classifier a priori? ---
**Author:** ![manifest](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/manifest/32/62_2.png) [@manifest](https://community.deeplearning.ai/u/manifest)\ **Post date:** [July 19, 2021, 12:56pm UTC](https://community.deeplearning.ai/t/how-to-determine-the-sample-weights-for-the-loss-function/21968/2 "2021-07-19T12:56:27Z")
> [@andree](#): > > Are you suggesting to train a porn/not-porn classifier a priori? Hey @andree, welcome to the DLS discussion forums 🙂 The assumption is that you already have some intuition about the data distribution of your training set, so you may assign some weight to each target label. ---
**Author:** ![andree](https://avatars.discourse-cdn.com/v4/letter/a/b4bc9f/32.png) [@andree](https://community.deeplearning.ai/u/andree)\ **Post date:** [July 19, 2021, 4:36pm UTC](https://community.deeplearning.ai/t/how-to-determine-the-sample-weights-for-the-loss-function/21968/3 "2021-07-19T16:36:57Z")
Ok, thanks, makes sense.