home.social

#cnns — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #cnns, aggregated by home.social.

  1. He has a TROVE of DESPICABLE online statements that he went out of his way to wipe from X, according to #CNN’s #KFile. He also tried to delete his posts from the archival website #TheWaybackMachine, though posts from his previous username can STILL be found. newrepublic.com/post/200965/...

    Trump Nominee Quietly Deletes ...

  2. He has a TROVE of DESPICABLE online statements that he went out of his way to wipe from X, according to #CNN’s #KFile. He also tried to delete his posts from the archival website #TheWaybackMachine, though posts from his previous username can STILL be found. newrepublic.com/post/200965/...

    Trump Nominee Quietly Deletes ...

  3. "Ah, the riveting showdown between #ViTs and #CNNs, where you get a convoluted explanation on how images are turned into a mush of pixels and self-attention. 😴 But don't worry, you won't be distracted by any tracking or analytics, because apparently, nobody cares to watch this spectacle. 🤷‍♂️ If you can't read code without JavaScript, that's your problem, not ours. 🖼️🔍"
    lucasb.eyer.be/articles/vit_cn #imageprocessing #selfattention #techhumor #HackerNews #ngated

  4. "Ah, the riveting showdown between #ViTs and #CNNs, where you get a convoluted explanation on how images are turned into a mush of pixels and self-attention. 😴 But don't worry, you won't be distracted by any tracking or analytics, because apparently, nobody cares to watch this spectacle. 🤷‍♂️ If you can't read code without JavaScript, that's your problem, not ours. 🖼️🔍"
    lucasb.eyer.be/articles/vit_cn #imageprocessing #selfattention #techhumor #HackerNews #ngated

  5. Today I tried out #AMD #Instinct #MI300a for my existing Deep Learning pipeline. Good news: It worked out of the box. Bad news: For some reason it could not beat my local #Nvidia #1080ti...
    After trying all sorts of #ROCM installation methods via prebuild wheels, #apptainer images etc I tried #nanogpt by @karpathy and sure enought: The gpt code ran approx 2x faster than on a #a100 ... I hope that this is due to my programming skills. Not AMD prefering #transformers over #CNNs ...

  6. Today I tried out #AMD #Instinct #MI300a for my existing Deep Learning pipeline. Good news: It worked out of the box. Bad news: For some reason it could not beat my local #Nvidia #1080ti...
    After trying all sorts of #ROCM installation methods via prebuild wheels, #apptainer images etc I tried #nanogpt by @karpathy and sure enought: The gpt code ran approx 2x faster than on a #a100 ... I hope that this is due to my programming skills. Not AMD prefering #transformers over #CNNs ...

  7. Today I tried out #AMD #Instinct #MI300a for my existing Deep Learning pipeline. Good news: It worked out of the box. Bad news: For some reason it could not beat my local #Nvidia #1080ti...
    After trying all sorts of #ROCM installation methods via prebuild wheels, #apptainer images etc I tried #nanogpt by @karpathy and sure enought: The gpt code ran approx 2x faster than on a #a100 ... I hope that this is due to my programming skills. Not AMD prefering #transformers over #CNNs ...