Tianji Cong

Number of queries in attack_classification.py etc.

1

Thank you for open-sourcing the code! I would like to double-check the following concerns 1. Does `num_queries` in `attack_classification.py` reflect how many queries were made to the classifier for each...

**Is your feature request related to a problem? Please describe.** Fine-tuning on CIFAR-100 **Describe the solution you'd like** Could you please provide hyper-parameters for fine-tuning CIFAR-100? Particularly, could you give...

Loading DenseNet Checkpoints for CIFAR-10/100

2

Thank you for open sourcing this great project. [The way you saved the Cifar10/100 checkpoints](https://github.com/pokaxpoka/deep_Mahalanobis_detector/blob/90c2105e78c6f76a2801fc4c1cb1b84f4ff9af63/OOD_Baseline_and_ODIN.py#L52) makes it hard to reuse the pre-trained Densenets in another project. Could you please release...

Key Error in MPLP Inference over Markov Network

1

### Subject of the issue Hi, thank you for open-sourcing this great library, which is very valuable to my project! I was running MPLP approximate inference for a Markov Network...

* fibber version: 0.2.5 * Python version: 3.7 * Operating System: Linux ### Description I wanted to train a Bert classifier on the IMDB dataset with the setup in [fibber.metrics.bert_classifier](https://dai-lab.github.io/fibber/_modules/fibber/metrics/bert_classifier.html)....

Package not Self-Contained

9

Thank you for open-sourcing this handy tool! I was trying to install the package from pip and source, but neither works out-of-the-box. From my end (Ubuntu with Python 3.10), running...

Empty Results

5

Thank you for open-sourcing this package! I was wondering if the following behavior is expected when running `metacrafter scan-file --format short world+City.csv `: > Processing file /data/bird_sql/train_csv/world+City.csv > > 2024-07-03...

NaN in Generated Embeddings

4

Thank you for open-sourcing this amazing work! I followed the instructions in README to generate embeddings for my use case. However, I found there are vectors consisting of NaNs. Do...

Pretraining Datasets

5

Thank you for open-sourcing the code! I didn't find descriptions about pretraining datasets in the paper. Was Starmie pertained on benchmark datasets?