Posts

Photo Credit Preamble Jigsaw hosted a toxic comment classification competition[2] in 2018, and has also created an API service for detecting toxic comments[3]. However, it has been shown that the model trained on this kind of datasets tend to have some biases against minority groups. For example, a simple sentence “I am a black woman” would be classified as toxic, and also more toxic than the sentence “I am a woman"[4]. This year’s Jigsaw Unintended Bias in Toxicity Classification competition[1] introduces an innovative metric that aims to reduce such biases and challenges Kagglers to find out the best score we can get under this year’s new dataset. ...

Photo Credit Overview Preamble I started doing this competition (iMet Collection 2019 - FGVC6) seriously after hitting a wall doing the Freesound competition. It was really late (only about one week until the competition ends), but by re-using a lot of code from the Freesound competition and using Kaggle Kernels to train models, I managed to get a decent submission with F2 score of 0.622 on the private leaderboard (the top 1 solution got 0.672, but used a hell lot more resources to train). ...

Photo Credit Overview Kaggle recently hosted a competition (Instant Gratification) to test their new “synchronous Kernel-only competition” format. It features a synthetic dataset, and the best way to achieve high score on this dataset is to reverse-engineer the dataset creation algorithm. I did not really spend time into this competition, but after the competition was over I went back checked the discussion forum for solutions and insights shared, and found it actually quite interesting. There are quite a few of lessons to be learned about how to create or deal with synthetic data. ...

Photo Credit Why Use Mutli-Stage Build? Starting from Docker 17.05, users can utilize this new “multi-stage build” feature [1] to simplify their workflow and make the final Docker images smaller. It basically streamlines the “Builder pattern”, which means using a “builder” image to build the binary files, and copying those binary files to another runtime/production image. Despite being an interpreted programming language, many of Python libraries, especially the ones doing scientific computing and machine learning, are built upon pieces written in compiled languages (mostly C/C++). Therefore, the “Builder pattern” can still be applied. ...

Photo Credit tl;dr: the power of Tensor Cores is real. Also, make sure the CPU does not become the bottleneck. Motivation I’ve written about Apex in this previous post: Use NVIDIA Apex for Easy Mixed Precision Training in PyTorch. At that time I only have my GTX 1070 to experiment on. And as we’ve learned in that post, pre-Volta nVidia cards does not benefit from half-precision arithmetic in terms of speed. It only saves some GPU memory. Therefore, I wasn’t able to personally evaluate how much speed boost we can get from mixed precision with Tensor Cores. ...