All Projects → kevinzakka → clip_playground

kevinzakka / clip_playground

Licence: MIT license
An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities

Programming Languages

Jupyter Notebook
11667 projects

Projects that are alternatives of or similar to clip playground

Adaptive-Gradient-Clipping
Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.
Stars: ✭ 74 (-7.5%)
Mutual labels:  colab-notebook
Pytorch-RL-CPP
A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)
Stars: ✭ 73 (-8.75%)
Mutual labels:  openai
stanford-cs231n-assignments-2020
This repository contains my solutions to the assignments for Stanford's CS231n "Convolutional Neural Networks for Visual Recognition" (Spring 2020).
Stars: ✭ 84 (+5%)
Mutual labels:  vision-and-language
TRAR-VQA
[ICCV 2021] TRAR: Routing the Attention Spans in Transformers for Visual Question Answering -- Official Implementation
Stars: ✭ 49 (-38.75%)
Mutual labels:  vision-and-language
wikiHow paper list
A paper list of research conducted based on wikiHow
Stars: ✭ 25 (-68.75%)
Mutual labels:  vision-and-language
VidSitu
[CVPR21] Visual Semantic Role Labeling for Video Understanding (https://arxiv.org/abs/2104.00990)
Stars: ✭ 41 (-48.75%)
Mutual labels:  vision-and-language
X-VLM
X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)
Stars: ✭ 283 (+253.75%)
Mutual labels:  vision-and-language
Tensorflow2-ObjectDetectionAPI-Colab-Hands-On
Tensorflow2 Object Detection APIのハンズオン用資料です(Hands-on documentation for the Tensorflow2 Object Detection API)
Stars: ✭ 33 (-58.75%)
Mutual labels:  colab-notebook
QuantumSpeech-QCNN
IEEE ICASSP 21 - Quantum Convolution Neural Networks for Speech Processing and Automatic Speech Recognition
Stars: ✭ 71 (-11.25%)
Mutual labels:  colab-notebook
CartPole
Run OpenAI Gym on a Server
Stars: ✭ 16 (-80%)
Mutual labels:  openai
pyspark-ML-in-Colab
Pyspark in Google Colab: A simple machine learning (Linear Regression) model
Stars: ✭ 32 (-60%)
Mutual labels:  colab-notebook
learningspoons
nlp lecture-notes and source code
Stars: ✭ 29 (-63.75%)
Mutual labels:  colab-notebook
colabs
This repository holds the Google Colabs for the EdX TinyML Specialization
Stars: ✭ 73 (-8.75%)
Mutual labels:  colab-notebook
colab-ffmpeg-cuda
FFmpeg build with CUDA support for Linux (especially for Google Colab)
Stars: ✭ 40 (-50%)
Mutual labels:  colab-notebook
Voice-Conversion
No description or website provided.
Stars: ✭ 30 (-62.5%)
Mutual labels:  colab-notebook
calvin
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
Stars: ✭ 105 (+31.25%)
Mutual labels:  vision-and-language
CBP
Official Tensorflow Implementation of the AAAI-2020 paper "Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction"
Stars: ✭ 52 (-35%)
Mutual labels:  vision-and-language
aprenda-python
Aprendizado, dicas e projetos sobre Python
Stars: ✭ 22 (-72.5%)
Mutual labels:  colab-notebook
pen.el
Pen.el stands for Prompt Engineering in emacs. It facilitates the creation, discovery and usage of prompts to language models. Pen supports OpenAI, EleutherAI, Aleph-Alpha, HuggingFace and others. It's the engine for the LookingGlass imaginary web browser.
Stars: ✭ 376 (+370%)
Mutual labels:  openai
iMIX
A framework for Multimodal Intelligence research from Inspur HSSLAB.
Stars: ✭ 21 (-73.75%)
Mutual labels:  vision-and-language

Playground for CLIP-like models

Demo Colab Link
GradCAM Visualization Colab
Naive Zero-shot Detection Colab
Smarter Zero-shot Detection Colab
Captcha Solver Colab

If you find this playground useful, consider citing it:

@software{zakka2021clipplayground,
    author = {Zakka, Kevin},
    month = {7},
    title = {{A Playground for CLIP-like Models}},
    url = {https://github.com/kevinzakka/clip_playground},
    version = {0.0.1},
    year = {2021}
}

Changelog

2021-07-28

  • Better plotting for reCAPTCHA.

2021-07-27

  • Allow multiple captions in detection query, colon separated.
  • Allow the user to resize an image during selective search.
  • Tuned the rejection parameters of selective search.
  • Minor bugfix in naive patch detector.
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].