Comments (3)
zanshuxun
commented on June 7, 2024
1
Q1:
已修复，详见61b5775
参考了dien.py中获取历史序列长度的方式，输入数据需要增加behavior_length
暂未合并至master分支，可以先参考dev-zsx分支
Q2:
（1）【部分sparse fear特征取了两次】 您是指这两次吗：
DeepCTR-Torch/deepctr_torch/models/din.py
Lines 82 to 83 in bc881dc
DeepCTR-Torch/deepctr_torch/models/din.py
Line 90 in bc881dc
第一次取出来的sparse_embedding_list在后面确实没有用到，已优化。
（2）【lookup embedding中mask feature list不起作用】
embedding_lookup函数中的mask_feat_list参数是用于hash的，详见DeepCTR。目前torch版还未加入hash，所以还没有用到。
from deepctr-torch.
zanshuxun
commented on June 7, 2024
非常感谢您细致地排查问题，我们会在近期的版本中对该问题进行修复，祝好！
from deepctr-torch.
zanshuxun
commented on June 7, 2024
Hi, we have solved this issue in v0.2.4, please use pip install -U deepctr-torch to upgrade.
from deepctr-torch.
Related Issues (20)
- IndexError: too many indices for tensor of dimension 1
- 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'
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.