-
Vijay Prakash Dwivedi. [Graph Transformer: A Generalization of Transformers to Graphs](https://towardsdatascience.com/graph-transformer-generalization-of-transformers-to-graphs-ead2448cff8b).
-
Hi! We're following your work and think it's a great job, but we may have found two errors in your project.
- The first error is:
We run your project and found that the `si` method in `splits-cifar…
zuael updated
2 years ago
-
### Bug Description
### Bug Reproduction
Code for reproducing the bug:
Installation:
```
conda create --name env python=3.9.13
conda activate env
conda install -c conda-forge cudatoolkit=…
-
Hi,
Congratulations on your work "Self-supervised learning of visual
features through embedding images into text topic spaces"!
We are trying to reproduce your experiments using your GitHub di…
-
Setup a task specific macro script so we can run:
1. Standard supervised learning (pretrain -> finetune)
2. Offline learning (pretrain -> sampling -> offline_rl)
With a single python command
…
AOS55 updated
2 years ago
-
Is it necessary to train a baseline student model before we start KD ? I ask this because I plan to use a custom small size backbone network and I kinda want to avoid pretraining it on ImageNet. My ef…
-
Hi! I want to train the model on NYUdataset. And I have written the own split as well as creating a new dataset subclassing from MonoDataset. For convenience, I just took 1000 pictures for training an…
-
Hi! Various `train_*` files include `from ssd import build_ssd`, but `ssd.py` is missing in this repo.
Is it a typo? Should it be instead `from csd import build_ssd_con`? Or are some files from `ss…
-
Edward Ma. [A Gentle Introduction to Meta-Learning](https://pub.towardsai.net/a-gentle-introduction-to-meta-learning-8e36f3d93f61).
-
### System Info
- `transformers` version: 4.22.2
- Platform: Linux-3.10.0-1160.31.1.el7.x86_64-x86_64-with-glibc2.10
- Python version: 3.8.8
- Huggingface_hub version: 0.10.0
- PyTorch version …