Comments (2)
zanshuxun
commented on June 1, 2024
考虑到您提出此issue时的时间较早，我找到了当时的代码：
DeepCTR-Torch/deepctr_torch/layers/interaction.py
Lines 607 to 612 in 687a094
tanh激活层是有的，但顺序是在pooling之前。
不知代码作者@Zengai 当时是否是考虑到很多CNN模型的顺序都是卷积-激活-池化？
但按照CCPM论文中的描述，tanh应该是在pooling之后：
We apply a non-linear function for outputs of pooling layers.
from deepctr-torch.
zanshuxun
commented on June 1, 2024
啊……仔细想了一下，这里的max pooling跟tanh的先后顺序好像是无所谓的
from deepctr-torch.
Related Issues (20)
- Issues installing deeptorch >0.2.2 for M1 macos HOT 2
- 训练过程中有一定概率因为label全为0而报错 HOT 1
- import deepctr_torch error HOT 3
- How to assign different weights to auxiliary task's loss in the whole loss function - multitask
- When doing model prediction, how to get the next-to-last layer emeddings at the same time?
- can developer add change basemodel class device attribute? HOT 1
- How to use pre training embedding in DIN and other models for pytorch version?
- How to do hyperparameter tuning with DeepCTR? HOT 4
- I had this error" RuntimeError: 'lengths' argument should be a 1D CPU int64 tensor", when i try to add LSTM on the top of bert HOT 1
- 数据文件 criteo_sample.txt HOT 2
- RuntimeError: Output 0 of UnbindBackward0 is a view and its base or another view of its base has been modified inplace. This view is the output of a function that returns multiple views. Such functions do not allow the output views to be modified inplace. You should replace the inplace operation by an out-of-place one.
- Why manually manage L2 norm multiplication of model parameters ? HOT 1
- How could I get PT file with DCN?
- 为什么这个项目会依赖tensorflow？ HOT 2
- How to use models or adjust parameters to reproduce approximate experimental results in a paper? HOT 1
- In the MOE method does expert have to learn and can the frozen model be used as an expert? HOT 1
- Custom Loss Function within xDeepFM API
- MMOE metric的代码有些问题，不适合分类+回归的任务
- module 'tensorflow.python.distribute.input_lib' has no attribute 'DistributedDatasetInterface'
- 不是国人的仓库吗, 怎么从简介到注释都是英文😂
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepctr-torch.