pytorch-CycleGAN-and-pix2pix
bert
pytorch-CycleGAN-and-pix2pix | bert | |
---|---|---|
10 | 50 | |
22,029 | 37,036 | |
- | 0.7% | |
2.5 | 0.0 | |
5 days ago | 29 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pytorch-CycleGAN-and-pix2pix
-
List of AI-Models
Click to Learn more...
- I want an A.I. to learn my art style so I can keep making art in my art style despite not having the time to do it.
-
I'm looking for an AI Art generator from images
pix2pix (https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix) - This is a PyTorch implementation of the pix2pix algorithm for image-to-image translation. Given a set of images, the model can learn to generate a new image from a different domain that is similar to the input image.
-
Seamless textures with SD and PBR maps with a pix2pix cGAN
Using junyanz/pytorch-CycleGAN-and-pix2pix as a basis for pix2pix, I applied the same blending method to fix seams. It essentially takes an input image and generates an output. The results depend on the paired training data. In this case, each map (height, roughness, etc.) is a separate checkpoint and had to be trained on paired training data with the diffuse as the input and the respective map as the output.
- IA art
- Segmentation and clasification with UNET
-
Trying to understand PatchGAN discriminator
Code for https://arxiv.org/abs/1611.07004 found: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
-
I made a 3d topographic map based on my recent civ6 game
pix2pix algorithm is used for translating Civ6Maps to heightmaps. Synthesized terrain was rendered in blender.
-
This Wojak Does Not Exist
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
-
Training a neural net to generate Wojaks
I'm working on creating a face-to-wojak model using PyTorch CycleGan/Pix2Pix [0] and found some of my outputs to be outrageous yet somehow relatable. People are into it so thought I'd share on HN
[0] https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
bert
-
Zero Shot Text Classification Under the hood
In 2019, a new language representation called BERT (Bedirectional Encoder Representation from Transformers) was introduced. The main idea behind this paradigm is to first pre-train a language model using a massive amount of unlabeled data then fine-tune all the parameters using labeled data from the downstream tasks. This allows the model to generalize well to different NLP tasks. Moreover, it has been shown that this language representation model can be used to solve downstream tasks without being explicitly trained on, e.g classify a text without training phase.
-
OpenAI – Application for US trademark "GPT" has failed
task-specific parameters, and is trained on the downstream tasks by simply fine-tuning all pre-trained parameters.
[0] https://arxiv.org/abs/1810.04805
-
Integrate LLM Frameworks
The release of BERT in 2018 kicked off the language model revolution. The Transformers architecture succeeded RNNs and LSTMs to become the architecture of choice. Unbelievable progress was made in a number of areas: summarization, translation, text classification, entity classification and more. 2023 tooks things to another level with the rise of large language models (LLMs). Models with billions of parameters showed an amazing ability to generate coherent dialogue.
-
Embeddings: What they are and why they matter
The general idea is that you have a particular task & dataset, and you optimize these vectors to maximize that task. So the properties of these vectors - what information is retained and what is left out during the 'compression' - are effectively determined by that task.
In general, the core task for the various "LLM tools" involves prediction of a hidden word, trained on very large quantities of real text - thus also mirroring whatever structure (linguistic, syntactic, semantic, factual, social bias, etc) exists there.
If you want to see how the sausage is made and look at the actual algorithms, then the key two approaches to read up on would probably be Mikolov's word2vec (https://arxiv.org/abs/1301.3781) with the CBOW (Continuous Bag of Words) and Continuous Skip-Gram Model, which are based on relatively simple math optimization, and then on the BERT (https://arxiv.org/abs/1810.04805) structure which does a conceptually similar thing but with a large neural network that can learn more from the same data. For both of them, you can either read the original papers or look up blog posts or videos that explain them, different people have different preferences on how readable academic papers are.
- Ernie, China's ChatGPT, Cracks Under Pressure
-
Ask HN: How to Break into AI Engineering
Could you post a link to "the BERT paper"? I've read some, but would be interested reading anything that anyone considered definitive :) Is it this one? "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding" :https://arxiv.org/abs/1810.04805
-
How to leverage the state-of-the-art NLP models in Rust
Rust crate rust_bert implementation of the BERT language model (https://arxiv.org/abs/1810.04805 Devlin, Chang, Lee, Toutanova, 2018). The base model is implemented in the bert_model::BertModel struct. Several language model heads have also been implemented, including:
-
Notes on training BERT from scratch on an 8GB consumer GPU
The achievement of training a BERT model to 90% of the GLUE score on a single GPU in ~100 hours is indeed impressive. As for the original BERT pretraining run, the paper [1] mentions that the pretraining took 4 days on 16 TPU chips for the BERT-Base model and 4 days on 64 TPU chips for the BERT-Large model.
Regarding the translation of these techniques to the pretraining phase for a GPT model, it is possible that some of the optimizations and techniques used for BERT could be applied to GPT as well. However, the specific architecture and training objectives of GPT might require different approaches or additional optimizations.
As for the SOPHIA optimizer, it is designed to improve the training of deep learning models by adaptively adjusting the learning rate and momentum. According to the paper [2], SOPHIA has shown promising results in various deep learning tasks. It is possible that the SOPHIA optimizer could help improve the training of BERT and GPT models, but further research and experimentation would be needed to confirm its effectiveness in these specific cases.
[1] https://arxiv.org/abs/1810.04805
-
List of AI-Models
Click to Learn more...
- Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding
What are some alternatives?
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
NLTK - NLTK Source
generative-inpainting-pytorch - A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)
bert-sklearn - a sklearn wrapper for Google's BERT model
pytorch-grad-cam - Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
pysimilar - A python library for computing the similarity between two strings (text) based on cosine similarity
Deep-Fakes
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
AnimeGAN - Generating Anime Images by Implementing Deep Convolutional Generative Adversarial Networks paper
PURE - [NAACL 2021] A Frustratingly Easy Approach for Entity and Relation Extraction https://arxiv.org/abs/2010.12812
PaddleGAN - PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
NL_Parser_using_Spacy - NLP parser using NER and TDD