Ben Johnson
Ben Johnson
Are you able to add the training code so we can see relevant hyperparameters for getting results close to the ones reported in your paper? Thanks!
Hello -- I'm having trouble getting the code running w/ the newest versions of `fastai` and `pytorch` -- lots of warnings and errors. Are you able to share information about...
I see that you provide code for finetuning the pretrained models -- do you think that this code is also appropriate for training a model from scratch? Or are there...
Right now, `logloss` in `Network::ProcessInput` is just hardcoded to zero -- is there an easy way to actually compute and return this?
The current implementation seems to fail when the URLs in a `.txt` input file have commas in them. This modification seems to fix the bug. (Disclaimer: I am not 100%...
Hello -- I'm interested in trying to reproduce the Barlow Twins curve from Fig 2 in [the paper](https://arxiv.org/pdf/2104.13712.pdf). I'm running: ``` python main.py --lmbda 0.0078125 --corr_zero --batch_size 128 --feature_dim 128...
In the paper, your method is motivated by learning from multiple views of the same dataset. You've done experiments where you use data augmentation to create multiple synthetic views of...
Question: is this a single threaded implementation or are their options for multithreading?
Hi -- I see in your papers that you often discuss the importance of having good benchmark instance across a wide variety of graphs for benchmarking these kinds of algorithms....
If we run the three experiments from the README: ``` # Exp. 1 ./scripts/ptb_search.sh ./scripts/ptb_final.sh # Exp. 2 ./scripts/cifar10_macro_search.sh ./scripts/cifar10_macro_final.sh # Exp 3. ./scripts/cifar10_micro_search.sh ./scripts/cifar10_micro_final.sh ``` what should we expect...