Python Paper

Open-source Python projects categorized as Paper

Top 23 Python Paper Projects

  • gpt-2

    Code for the paper "Language Models are Unsupervised Multitask Learners"

    Project mention: BING IS NOW THE DEFAULT SEARCH FOR CHATGPT | | 2023-05-24

    They did release GPT-2 under the MIT License.

  • transferlearning

    Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

    Project mention: [D] Medium Article: Adaptive Learning for Time Series Forecasting | | 2022-10-02

    The src is available in I'll also publish about how to code the model for time series

  • Sonar

    Write Clean Python Code. Always.. Sonar helps you commit clean code every time. With over 225 unique rules to find Python bugs, code smells & vulnerabilities, Sonar finds the issues while you focus on the work.

  • qlib

    Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.

    Project mention: qlib: NEW Other Models - star count:10947.0 | | 2023-05-27
  • jukebox

    Code for the paper "Jukebox: A Generative Model for Music"

    Project mention: Best model for music generation? | | 2023-05-20 The demo code is there.

  • ALAE

    [CVPR2020] Adversarial Latent Autoencoders

  • Tacotron-2

    DeepMind's Tacotron-2 Tensorflow implementation

    Project mention: [D] How to Create a Fixed-Length, Binary, Sequence of Tokens Embedding? | | 2022-09-26

    This reminds me a lot of the problem of predicting an integer-valued output for an image or audio sequence, where you want to predict a value between 0 and 255, or even say 65536, but you want to help the model understand that the result is categorical, but some categories are closer to each other. I learned recently that one approach to this used in Tacotron 2 (speech synthesis) is called a Mixture of Logistics. There is a not very good blog post that goes over it, but links to a very in-depth explanation in a github issue of all places.. might be interesting for you.

  • multiagent-particle-envs

    Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

    Project mention: Why is Q-learning always presented in such a math-heavy fashion? I just spent an hour dissecting this formula with a student -- only to strongly suspect there is a typo. Are there any good Q-Learning tutorials out there that *explain* the math instead of dropping it from the sky? | | 2022-10-12

    ONLYOFFICE Docs — document collaboration in your environment. Powerful document editing and collaboration in your app or environment. Ultimate security, API and 30+ ready connectors, SaaS or on-premises

  • FSL-Mate

    FSL-Mate: A collection of resources for few-shot learning (FSL).

  • maddpg

    Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

    Project mention: How is the backward pass performed in MADDPG algorithm from MARL | | 2022-10-05

    I'm using the MADDPG algorithm from I understood the forward pass for both the actor and critic networks. I'm not able to understand how the actor and critic networks are updates. Like at line 188 and 191 the authors compute the critic loss and actor loss. But can anyone explain how the critic and actor networks are updated. Also, as far as I understand, when the number of agents increases from 3 to 6 for a simple spread policy in MADDPG, the computation time for Q loss and P loss at lines 188 and 191 increase super-linearly. I'm assuming this might be because both the Q loss and P loss utilize the Q values and the dimension to calculate the Q values increases with the number of increasing linearly. It would be great if anyone can help me to understand this back propagation phase much better and why does the computation time grow super-linearly. I also put a time counter to track the computation time of Q loss and P loss for 60,000 episodes with simple spread policy (3 agents, 3 landmarks, 0 adversaries). Thanks for the help, in advance! **Q loss** 3 agents 74.31 sec 6 agents 243.31 sec (3X) **P loss** 3 agents 114.86 sec 6 agents 321.76 sec (3x)

  • research-contributions

    Implementations of recent research prototypes/demonstrations using MONAI.

    Project mention: Pretrained Resnet50 for kidney detection (Kits19) | | 2023-01-11

    You can find a pretrained Resnet, but probably not one that's been trained on a kidney object detection dataset. The only kidney CT dataset I know of is for segmentation, not object detection. So you'll have to convert the segmentations to bounding boxes and train your own. Take a look at for potential resources.

  • diffwave

    DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

  • rpg_timelens

    Repository relating to the CVPR21 paper TimeLens: Event-based Video Frame Interpolation

  • awesome-systematic-trading

    A curated list of awesome libraries, packages, strategies, books, blogs, tutorials for systematic trading. (by edarchimbaud)

    Project mention: awesome-systematic-trading: NEW Alternative Finance - star count:213.0 | | 2023-05-13
  • SingleViewReconstruction

    Official Code: 3D Scene Reconstruction from a Single Viewport

  • wavegrad

    A fast, high-quality neural vocoder.

  • pubs

    Your bibliography on the command line

    Project mention: Minimalist way of managing academic papers? | | 2022-10-05
  • efficient-attention

    An implementation of the efficient attention module.

  • deep-kernel-transfer

    Official pytorch implementation of the paper "Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels" (NeurIPS 2020)

    Project mention: What approach to take predicting a simple data stream? | | 2022-10-03

    Interesting approach to small datasets. Here is an implementation I'll look at:

  • cam_board

    Turn web cam into a black / white board

  • tabular-dl-num-embeddings

    (NeurIPS 2022) The official implementation of the paper "On Embeddings for Numerical Features in Tabular Deep Learning"

  • Efficient-VDVAE

    Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more"

  • train-procgen

    Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"

    Project mention: Procgen environments "easy" vs "hard" difficulty - what are they? | | 2022-12-26

    Found relevant code at + all code implementations here

  • heinsen_routing

    Reference implementation of "An Algorithm for Routing Vectors in Sequences" (Heinsen, 2022) and "An Algorithm for Routing Capsules in All Domains" (Heinsen, 2019), for composing deep neural networks.

    Project mention: Unlimiformer: Long-Range Transformers with Unlimited Length Input | | 2023-05-05

    After a very quick read, that's my understanding too: It's just KNN search. So I agree on points 1-3. When something works well, I don't care much about point 4.

    I've had only mixed success with KNN search. Maybe I haven't done it right? Nothing seems to work quite as well for me as explicit token-token interactions by some form of attention, which as we all know is too costly for long sequences (O(n²)). Lately I've been playing with , which uses a lot less compute and seems promising. Otherwise, for long sequences I've yet to find something better than for n×n interactions and for n×m interactions. If anyone here has other suggestions, I'd love to hear about them.

  • CodiumAI

    TestGPT | Generating meaningful tests for busy devs. Get non-trivial tests (and trivial, too!) suggested right inside your IDE, so you can code smart, create more value, and stay confident when you push.

NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020). The latest post mention was on 2023-05-27.

Python Paper related posts


What are some of the best open-source Paper projects in Python? This list will help you:

Project Stars
1 gpt-2 19,120
2 transferlearning 11,481
3 qlib 10,955
4 jukebox 6,914
5 ALAE 3,399
6 Tacotron-2 2,157
7 multiagent-particle-envs 1,849
8 FSL-Mate 1,508
9 maddpg 1,267
10 research-contributions 707
11 diffwave 601
12 rpg_timelens 556
13 awesome-systematic-trading 455
14 SingleViewReconstruction 253
15 wavegrad 236
16 pubs 235
17 efficient-attention 225
18 deep-kernel-transfer 177
19 cam_board 176
20 tabular-dl-num-embeddings 164
21 Efficient-VDVAE 159
22 train-procgen 154
23 heinsen_routing 139
Access the most powerful time series database as a service
Ingest, store, & analyze all types of time series data in a fully-managed, purpose-built database. Keep data forever with low-cost storage and superior data compression.