Simple Python Package to Extract Deep Learning Features (chsasank.github.io) 91 points by chsasank 6y ago ↗ HN
[–] amelius 6y ago ↗ This blogpost makes it sound as if using a deep learning library for a task like image classification is difficult, while it is just a matter of copy+paste, annotate, and run. [–] craftinator 6y ago ↗ Please provide either an example or a source for this assertion. [–] la_fayette 6y ago ↗ https://github.com/fchollet/deep-learning-with-python-notebo... [–] rytill 6y ago ↗ The OP library specifically grabs the ImageNet model and uses transfer learning. That's just a general keras convolutional networks resource. [–] lopmotr 6y ago ↗ The entire library is only 100 lines of code, so you could copy and paste its own source. [–] kylek 6y ago ↗ Dunno, maybe you aren't the target for the article. As someone who has never played with deep learning, I thought it was presented just fine. [–] make3 6y ago ↗ it is a lot harder than what this library does.
[–] craftinator 6y ago ↗ Please provide either an example or a source for this assertion. [–] la_fayette 6y ago ↗ https://github.com/fchollet/deep-learning-with-python-notebo... [–] rytill 6y ago ↗ The OP library specifically grabs the ImageNet model and uses transfer learning. That's just a general keras convolutional networks resource. [–] lopmotr 6y ago ↗ The entire library is only 100 lines of code, so you could copy and paste its own source.
[–] la_fayette 6y ago ↗ https://github.com/fchollet/deep-learning-with-python-notebo... [–] rytill 6y ago ↗ The OP library specifically grabs the ImageNet model and uses transfer learning. That's just a general keras convolutional networks resource.
[–] rytill 6y ago ↗ The OP library specifically grabs the ImageNet model and uses transfer learning. That's just a general keras convolutional networks resource.
[–] lopmotr 6y ago ↗ The entire library is only 100 lines of code, so you could copy and paste its own source.
[–] kylek 6y ago ↗ Dunno, maybe you aren't the target for the article. As someone who has never played with deep learning, I thought it was presented just fine.
[–] make3 6y ago ↗ I wonder if there is a BERT equivalent for NLP. Is BERT part of Spacy now? [–] visarga 6y ago ↗ huggingface offers a whole family of pretrained transformers.https://github.com/huggingface/pytorch-transformers [–] make3 6y ago ↗ The Tf-Hub stuff is pretty close I guess https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1 [–] syllogism 6y ago ↗ We've been developing support for transformers in spaCy. See:https://explosion.ai/blog/spacy-pytorch-transformershttps://github.com/explosion/spacy-pytorch-transformers
[–] visarga 6y ago ↗ huggingface offers a whole family of pretrained transformers.https://github.com/huggingface/pytorch-transformers
[–] make3 6y ago ↗ The Tf-Hub stuff is pretty close I guess https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1
[–] syllogism 6y ago ↗ We've been developing support for transformers in spaCy. See:https://explosion.ai/blog/spacy-pytorch-transformershttps://github.com/explosion/spacy-pytorch-transformers
12 comments
[ 5.3 ms ] story [ 39.6 ms ] threadhttps://github.com/huggingface/pytorch-transformers
https://explosion.ai/blog/spacy-pytorch-transformers
https://github.com/explosion/spacy-pytorch-transformers