models icon indicating copy to clipboard operation
models copied to clipboard

Merlin Models is a collection of deep learning recommender system model reference implementations

Results 205 models issues
Sort by recently updated
recently updated
newest added

Let's create an FAQ highlighting: - What does Merlin models do? - Why should I use Merlin models? - What are blocks? - What is a block context? etc @karlhigley...

documentation
status/needs-triage
epic?

Modules with missing docstrings: - [ ] config, data - [ ] loader - [ ] tf/blocks - [ ] tf/features, tf/losses, tf/metrics - [ ] tf/prediction_tasks - [ ]...

documentation
status/needs-triage

We want to add CI/unittest for notebooks, that they are tested for each PR. Notebooks from: - [ ] https://github.com/NVIDIA-Merlin/models/pull/253 - [ ] https://github.com/NVIDIA-Merlin/models/pull/256 - [ ] https://github.com/NVIDIA-Merlin/models/tree/main/examples/usecases

examples

# 🌟 New model addition ## Model description The youtube-dnn [paper](https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/45530.pdf) defined a two-stage recommender and proposed two architectures for retrieval and ranking steps. The purpose of this request is...

area/tensorflow
area/api
examples

Issue | Reported By | Impact | Owner | Status -- | -- | -- | -- | -- Address TODO comments in retrieval.py and ranking.py. | Marc | L...

documentation

- [ ] Dealing with overfitting - [ ] Stabilizing training (Batchnorm and layernorm) - [ ] Learning rate scheduling

documentation
status/needs-triage

### Description NVIDIA won the WSDM 2021 competition. As we added new features and libraries, we want to add the solution as Merlin (Models) example: https://github.com/NVIDIA-Merlin/competitions/tree/main/WSDM_WebTour2021_Challenge/02_Models/GRU_MS_SMF

examples

### Description Add the KDD tutorial notebooks to merlin models repository + add units tests for them

examples

### Description The notebooks currently include code like ```python import os os.environ["TF_GPU_ALLOCATOR"]="cuda_malloc_async" import merlin.models.tf as mm ``` This causes a segfault in TF 2.6. We should add a note to...

bug
P1
examples