models

models copied to clipboard

[BUG] Fixing Dataparallel Training

4

### Bug description https://github.com/NVIDIA-Merlin/models/issues/964 demonstrated an issue with our data parallel training in Merlin Models. 1. What is the correct data loader to use? We have https://github.com/NVIDIA-Merlin/models/blob/main/merlin/models/tf/loader.py and then we...

bschifferer

### Description Example for https://github.com/NVIDIA-Merlin/Merlin/issues/407

bschifferer

[FEA] Functionality to add sparse_weights arg to the EmbeddingTable Class /EMbeddings function

2

# 🚀 Feature request We use `tf.nn.safe_embedding_lookup_sparse` api in our EmbeddingTable class for embeddings look up, when the input is tf.RaggedTensor or tf.SparseTensor. The original [api](https://www.tensorflow.org/api_docs/python/tf/nn/safe_embedding_lookup_sparse) has the `sparse_weights` arg...

rnyak

# 🚀 Feature request Currently, all ItemPrediction tasks transform the targets tensor to a one-hot representation (as required by the RankingMetrics or SampledSoftmax contrastive learning). This Feature request is related...

sararb

[QST] How to get candidate features after using pre-trained embedding tables?

3

# ❓ Questions & Help ## Details I am following the [tutorial here](https://github.com/NVIDIA-Merlin/models/blob/main/examples/usecases/entertainment-with-pretrained-embeddings.ipynb)to include pre-computed embeddings when I train a Two Tower Retrieval model. Specifically, I am using this method...

hkristof03

Fix issue #1226

1

Since the Ali-CCP datasets contains many null values, Int32 ( nullable integer ) should be used instead Fixes # 1226 see https://github.com/NVIDIA-Merlin/models/issues/1226#issuecomment-2094149845

ibraheemalayan

[QST] Questions about topk_model.evaluate()

1

# ❓ Questions & Help ## Details I was looking at [this tutorial](https://nvidia-merlin.github.io/models/stable/examples/05-Retrieval-Model.html) and came across these two lines of code. I'm curious about what evaluation and sampling methods are...

ZhanqiuHu

# ❓ Questions & Help I am experiencing a large degradation in the performance of the `Loader` when adding a transform with `EmbeddingOperator`, for loading data from a pretrained embeddings...

CarloNicolini

[QST] How to deploy model using Pretrain Embeddings with EmbeddingOperator in Triton

1

# ❓ Questions & Help ## Details I have trained both a Two Tower and DLRM model using PreTrained embeddings using a Loader with EmbeddingOperator following the approach from this...

jhnealand

[BUG] ModelCheckpoint Callback results in an error due to unsupported overwrite=True parameter

7

### Bug description The[ callback ModelCheckpoint calls](https://github.com/tensorflow/tensorflow/blob/d0228dc874ed4f19f750e5df7e8ac61827fa7332/tensorflow/python/keras/callbacks.py#L1434) the model's save method, which is overwritten by the [Merlin BaseModel implementation](https://github.com/NVIDIA-Merlin/models/blob/eb1e54196a64a70950b2a7e7744d2150e052d53e/merlin/models/tf/models/base.py#L1687). The callback passes the `overwrite=True` parameter to the save method, which...

hkristof03