PyTorch Summer Hackathon at Menlo Park 2019
2019-08-08..2019-08-09
Menlo Park, United States
who it's for
deep learning engineers, research scientists, applied machine learning researchers, computer vision engineers, speech and audio researchers, ml infrastructure engineers
topics
PyTorch 1.2 features; PyTorch Hub model zoo; pretrained image models; transfer learning final-layer fine-tuning; torchtext supervised datasets; tokenizer and Transformer modules; torchaudio Kaldi compatibility; torchaudio resample and inverse STFT; torchvision video support; video dataset DataLoader integration; deployment with AWS and Flask
| title | author | length |
|---|---|---|
| Tips and Tricks on Hacking with PyTorch: A Quick Tutorial | Brad Heintz | 05m |
Less than two days means pick ready-made assets: use open datasets from torch vision torch text and torch audio (many download and cache with a single line)… | ||
| PyTorch 1.2 and PyTorch Hub: A Quick Introduction | Soumith Chintala, Ailing Zhang | 06m |
PyTorch 1.2 released and PyTorch Hub (Beta) provide concrete, usable pieces: a hub with 25+ models across image, language, audio and GANs, ready-to-load via… | ||
| Torchtext 0.4 with Supervised Learning Datasets: A Quick Introduction | George Zhang | 06m |
Torchtext 0.4 ships supervised datasets with one-command data loading, ready-made splits and an N‑gram option so text classification experiments run from a… | ||
| Torchaudio 0.3 with Kaldi Compatibility, New Transforms: A Quick Introduction | Jason Lian | 05m |
Torchaudio 0.3 claims concrete additions: Kaldi compatibility by matching Kaldi binary parameters, a new resample transform, and inverse STFT implemented in… | ||
| Torchvision 0.4 with Support for Video: A Quick Introduction | Francisco Massa | 09m |
torchvision 0.4 adds first‑class video support: efficient IO primitives that read/write video (and audio) on the fly so no pre‑conversion is needed, standard… | ||
| nothing matches | ||