Celso França

Graphml-classification notebook import error

2

Trying to reproduce the [Graph Classification with Transformers](https://github.com/huggingface/blog/blob/main/notebooks/graphml-classification.ipynb), I am getting the following error even with all required lib installed. ```python ImportError Traceback (most recent call last) [](https://localhost:8080/#) in ()...

Trying to reproduce the [Graph Classification with Transformers](https://github.com/huggingface/blog/blob/main/notebooks/graphml-classification.ipynb), I am getting a series of the following error even with all required lib installed. ```python ImportError Traceback (most recent call last)...

Failing to install apex

8

```python LightXML/apex$ pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./ WARNING: Disabling all use of wheels due to the use of --build-option / --global-option / --install-option. Using pip 22.0.2 from...

I could not find the `qrels.dev.small.tsv` on linked [MSMARCO](https://microsoft.github.io/msmarco/Datasets#passage-ranking-dataset) dataset page as pointed in [Data](https://github.com/stanford-futuredata/ColBERT#data) section on this repo [README.md](https://github.com/stanford-futuredata/ColBERT/blob/main/README.md).

Why does the XR-Transformer require exceptional RAM on Amazon-670k (and in other large datasets)?

3

Hello, Reading the XR-Transformer paper, I would like to know the Multi-resolution learning time complexity considering the N(number of text instances) and the number of labels (L). Is the Multi-resolution...

Propensity scored nDCG

1

Hello, Could you give me directions on the Propensity scored nDCG loss function implementation?

How do we compare different runs with multiple folds per run?

1

How do we compare different runs with multiple folds per run? For instance, assume we have 10-folds for `run_1`, ... `run_5`? ```python from ranx import compare # Compare different runs...

[Feature Request] Propensity-scored Metrics

1

**Is your feature request related to a problem? Please describe.** In some extremely challenging scenarios for information retrieval, items relevant to a query follow a long tail distribution. Thus, there...

I am using the Sagemaker [Pytorch Estimator][1] based on a custom docker image stored in AWS ECR. ```python from sagemaker.pytorch.estimator import PyTorch role = "arn:..." estimator = PyTorch( image_uri="1...ecr...amazonaws.com/...:prototype", git_config={"repo":...

The input to an LTR loss function comprises three tensors: `scores`: a tensor of size (batch_size, number of scores) `relevance`: a tensor of size (batch_size, number of relevance scores) `n`:...