Skip to content

Bag of Tricks in Machine Learning

Public Personal Notebook

Search
  • Home
  • random
  • paper
  • list
  • nlp
  • reinforcementlearning
  • gan
  • cv
  • Search

PyTorch fast

August 26, 2019August 26, 2019 by admin
[D] Why is PyTorch as fast as (and sometimes faster than) TensorFlow? from MachineLearning
Categories Uncategorized
Post navigation
To Review Deep Learning
Image Classification Papers

Best practice to follow this website

  1. In Feedly, click “add content”
  2. Input the url “bagoftricks.ml” and follow

ShujianFollow

Shujian
Retweet on TwitterShujian Retweeted
geoffreyhintonGeoffrey Hinton@geoffreyhinton·
26 Feb

I have a new paper on how to represent part-whole hierarchies in neural networks.

http://arxiv.org/abs/2102.12627

Reply on Twitter 1365311399287808002Retweet on Twitter 1365311399287808002596Like on Twitter 13653113992878080022927Twitter 1365311399287808002
Retweet on TwitterShujian Retweeted
PapersTrendingTrending Papers@PapersTrending·
28 Feb

[1/10] 📈 - Zero-Shot Text-to-Image Generation - 1,492 ⭐ - 📄 https://arxiv.org/pdf/2102.12092v1.pdf - 🔗 https://github.com/openai/DALL-E/blob/master/notebooks/usage.ipynb

Reply on Twitter 1365980578118586370Retweet on Twitter 13659805781185863701Like on Twitter 13659805781185863701Twitter 1365980578118586370
Retweet on TwitterShujian Retweeted
taolei15949106taolei@taolei15949106·
25 Feb

Excited to share our work of SRU++: https://arxiv.org/pdf/2102.12459.pdf

We show that fast RNNs with little attention not only achieve top results but also reduce the training cost greatly. This reaffirms previous work such as SHA-LSTM and shares an orthogonal idea to accelerating attention. https://twitter.com/asapp/status/1364947408916914176

ASAPP@asapp

The size of #NLP models have increased enormously, growing to millions, or even billions, of parameters, along with a significant increase in the financial cost and carbon emissions.

Reply on Twitter 1364980529007845381Retweet on Twitter 136498052900784538125Like on Twitter 136498052900784538174Twitter 1364980529007845381
Shujian_LiuShujian@Shujian_Liu·
22 Feb

This is the first time I saw a wax statue of Steve Jobs inside a Apple Store 😮

Reply on Twitter 1363836535267713026Retweet on Twitter 1363836535267713026Like on Twitter 13638365352677130262Twitter 1363836535267713026
Retweet on TwitterShujian Retweeted
jcjohnssJustin Johnson@jcjohnss·
13 Feb

I'll be back on Clubhouse tonight with @karpathy for a technical deep dive on large-scale vision+language work https://twitter.com/karpathy/status/1360729950362300416

Andrej Karpathy@karpathy

Tonight at 7pm @jcjohnss and I will hang out on Clubhouse for a quasi-CS231n-like reading group going through technical details of paper/code of

1 OpenAI's CLIP https://openai.com/blog/clip/
2 Google's ALIGN https://arxiv.org/abs/2102.05918
3 related image+text friends

https://www.joinclubhouse.com/event/Pb7Y1pJR

Reply on Twitter 1360731229750984712Retweet on Twitter 136073122975098471210Like on Twitter 1360731229750984712173Twitter 1360731229750984712
Load More...

Categories

  • ml (2)
  • nlp (9)
  • papers (1)
  • random (8)
  • reinforcementlearning (1)
  • Uncategorized (57)

Tags

anomaly (1) automl (1) ctr (1) cv (2) data (1) distributedtraining (1) gan (1) kaggle (1) list (2) ml (2) nlp (9) nn (1) paper (1) random (3) reinforcementlearning (1) sql (1)

Recent Posts

  • Data Augmentation in NLP
  • PyTorch nn.DistributedDataParallel
  • Unsupervised Pre-Training of Image Features on Non-Curated Data (by FAIR)
  • Image Classification Papers
  • PyTorch fast

Archives

  • May 2020 (1)
  • October 2019 (1)
  • August 2019 (11)
  • July 2019 (8)
  • June 2019 (6)
  • May 2019 (1)
  • April 2019 (11)
  • March 2019 (4)
  • February 2019 (2)
  • January 2019 (32)

Recent Comments

    August 2019
    M T W T F S S
     1234
    567891011
    12131415161718
    19202122232425
    262728293031  
    « Jul   Oct »

    • 0
    • 56
    • 37,916
    • 18,789
    • 77
    • 0

    Recent Posts

    • Data Augmentation in NLP
    • PyTorch nn.DistributedDataParallel
    • Unsupervised Pre-Training of Image Features on Non-Curated Data (by FAIR)
    • Image Classification Papers
    • PyTorch fast

    Categories

    • ml (2)
    • nlp (9)
    • papers (1)
    • random (8)
    • reinforcementlearning (1)
    • Uncategorized (57)

    Meta

    • Log in
    • Entries feed
    • Comments feed
    • WordPress.org
    © 2021 Bag of Tricks in Machine Learning • Powered by GeneratePress
    Scroll back to top