shenweichen/DeepCTR-Torch

View on GitHub

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

Stars: 3.5k
Forks: 733
Open beginner issues: 0
Indexed issues: 45

Dominant language: Python
License: Apache-2.0
Last GitHub push: Jul 9, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

45 open issues indexed

请问ctr lable列可以不为0和1，而是0～1之间的值吗？ Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#308 · Opened Jul 8, 2025
SparseFeat什么时候能支持user_hash Open

enhancement&feature request

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#307 · Opened Jul 7, 2025
How to ensure the consistency of the index， during training stage and prediction stage? Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#306 · 1 comment · Opened Mar 27, 2025
CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)` Open

question

Difficulty 4/5 3-5 days Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#302 · Opened Nov 22, 2024
Can't install dependencies Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#301 · 4 comments · Opened Nov 6, 2024
Understanding DCN Network Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#300 · 1 comment · Opened Nov 5, 2024
请问有Autodis或者DEER的代码吗 Open

question

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#298 · Opened Oct 28, 2024
support multiclass and multilabel Open

enhancement&feature request

Difficulty 5/5 Over a week Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#297 · Opened Jul 23, 2024
IndexError: index out of range in self Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#295 · 2 comments · Opened Jun 6, 2024
MMOE metric的代码有些问题，不适合分类+回归的任务 Open

question

Difficulty 4/5 3-5 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#287 · Opened Jul 20, 2023
Custom Loss Function within xDeepFM API Open

question

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#286 · Opened Jul 13, 2023
In the MOE method does expert have to learn and can the frozen model be used as an expert? Open

question

Difficulty 5/5 Over a week Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#285 · 1 comment · Opened Jun 14, 2023
How to use models or adjust parameters to reproduce approximate experimental results in a paper? Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#284 · 1 comment · Opened May 10, 2023
How could I get PT file with DCN? Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#280 · Opened Mar 30, 2023
Why manually manage L2 norm multiplication of model parameters ? Open

question

Difficulty 4/5 3-5 days Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#279 · 1 comment · Opened Mar 28, 2023
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. Open

question

Difficulty 4/5 3-5 days Newbie friendliness 30/100

shenweichen/DeepCTR-Torch#278 · Opened Mar 28, 2023
数据文件 criteo_sample.txt Open

question

Difficulty 5/5 Over a week Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#277 · 3 comments · Opened Mar 28, 2023
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 Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

shenweichen/DeepCTR-Torch#275 · 1 comment · Opened Mar 2, 2023
How to assign different weights to auxiliary task's loss in the whole loss function - multitask Open

question

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#270 · Opened Feb 4, 2023
训练过程中有一定概率因为label全为0而报错 Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

shenweichen/DeepCTR-Torch#266 · 1 comment · 1 reaction · Opened Dec 13, 2022
Issues installing deeptorch >0.2.2 for M1 macos Open

enhancement&feature request

Difficulty 4/5 3-5 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#265 · 2 comments · Opened Nov 28, 2022
Cannot restore best weights with DeepFM model Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#262 · 3 comments · 4 reactions · Opened Nov 3, 2022
deepFM 多gpu报错 Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 30/100

shenweichen/DeepCTR-Torch#261 · 3 comments · Opened Oct 29, 2022
Help Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#253 · Opened Aug 2, 2022
Any way to log the step artifacts ? Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#252 · 2 comments · Opened Jul 5, 2022
Error when running run_dien.py Open

Difficulty 3/5 1-2 days Newbie friendliness 30/100

shenweichen/DeepCTR-Torch#249 · 4 comments · Opened Jun 25, 2022
Adding sample weight to the fit function Open

enhancement&feature request

Difficulty 3/5 1-2 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#245 · Opened Jun 13, 2022
I dont see anywhere 'mask_feat_list' argument in embedding_lookup function. Open

question

Difficulty 3/5 1-2 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#239 · 1 comment · Opened Mar 16, 2022
Providing real dataset run_dien toy example. DIEN implementation questions. Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#238 · Opened Mar 14, 2022
Making DIEN dataset Open

question

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#237 · Opened Mar 14, 2022
How do people actually generate unseen new inference data? Open

question

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#233 · 1 comment · Opened Mar 1, 2022
pytorch版本是不支持预训练权重嵌入吗 Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#228 · Opened Feb 11, 2022
Issue with predict function from a saved model Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#217 · 2 comments · Opened Nov 22, 2021
当样本不均衡的时候，如何修改底层的loss函数呢？以deepfm为例 Open

question

Difficulty 5/5 Over a week Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#212 · Opened Nov 2, 2021
How to use pre training embedding in DIN and other models? Open

question

Difficulty 5/5 Over a week Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#211 · Opened Nov 1, 2021
Break Computational Graph When Needed Open

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

shenweichen/DeepCTR-Torch#208 · 1 reaction · Opened Oct 6, 2021
Planning to add DHAN - Deep Interest with Hierarchical Attention Network Open

enhancement&feature request

Difficulty 5/5 Over a week Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#207 · 1 comment · Opened Sep 30, 2021
DIEN Model: ValueError: not enough values to unpack (expected 2, got 1) Open

question

Difficulty 4/5 3-5 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#206 · 4 comments · Opened Sep 23, 2021
Addition of BST to DeepCTR-Torch Open

question

Difficulty 5/5 Over a week Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#178 · 3 comments · 1 reaction · Opened May 26, 2021
请问DIN模型中hist_igender如果是multi-value应该怎么处理呢？ Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

shenweichen/DeepCTR-Torch#148 · 2 comments · Opened Jan 12, 2021
希望model.fit中train和val的metric可以单独设置 Open

enhancement&feature request

Difficulty 4/5 3-5 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#147 · 3 comments · Opened Dec 27, 2020
a question about whether self.feature_index is in CPU or GPU Open

question

Difficulty 1/5 Under an hour Newbie friendliness 20/100

shenweichen/DeepCTR-Torch#92 · Opened Jun 3, 2020
How to export DeepCTR model to onnx ? Open

question

Difficulty 4/5 3-5 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#83 · 1 comment · Opened Mar 15, 2020
TensorDataset with DataLoader could lead bad performance Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

shenweichen/DeepCTR-Torch#70 · 1 reaction · Opened Dec 8, 2019
where is the QR code Open

question

Difficulty 2/5 1-3 hours Newbie friendliness 15/100

shenweichen/DeepCTR-Torch#45 · 1 comment · Opened Sep 21, 2019

shenweichen/DeepCTR-Torch

Get new issues in your inbox