altosaar / Food2vec
Licence: mit
π
Stars: β 199
Projects that are alternatives of or similar to Food2vec
Cofactor
CoFactor: Regularizing Matrix Factorization with Item Co-occurrence
Stars: β 160 (-19.6%)
Mutual labels: jupyter-notebook, embeddings
Decagon
Graph convolutional neural network for multirelational link prediction
Stars: β 268 (+34.67%)
Mutual labels: jupyter-notebook, embeddings
Snap N Eat
Food detection and recommendation with deep learning
Stars: β 229 (+15.08%)
Mutual labels: jupyter-notebook, food
Deeplearning Nlp Models
A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.
Stars: β 64 (-67.84%)
Mutual labels: jupyter-notebook, embeddings
Ml Ai Experiments
All my experiments with AI and ML
Stars: β 107 (-46.23%)
Mutual labels: jupyter-notebook, embeddings
Food 101 Mobile
Deep Learning Food Classifier for iOS using Keras and Tensorflow
Stars: β 97 (-51.26%)
Mutual labels: jupyter-notebook, food
Food Recipe Cnn
food image to recipe with deep convolutional neural networks.
Stars: β 448 (+125.13%)
Mutual labels: jupyter-notebook, food
Awesome Embedding Models
A curated list of awesome embedding models tutorials, projects and communities.
Stars: β 1,486 (+646.73%)
Mutual labels: jupyter-notebook, embeddings
Research2vec
Representing research papers as vectors / latent representations.
Stars: β 192 (-3.52%)
Mutual labels: jupyter-notebook, embeddings
Up Down Captioner
Automatic image captioning model based on Caffe, using features from bottom-up attention.
Stars: β 195 (-2.01%)
Mutual labels: jupyter-notebook
Nas fpn tensorflow
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
Stars: β 198 (-0.5%)
Mutual labels: jupyter-notebook
Data Science Projects With Python
A Case Study Approach to Successful Data Science Projects Using Python, Pandas, and Scikit-Learn
Stars: β 198 (-0.5%)
Mutual labels: jupyter-notebook
Integratedgradients
Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework.
Stars: β 197 (-1.01%)
Mutual labels: jupyter-notebook
Python For Finance Cookbook
Python for Finance Cookbook, published by Packt
Stars: β 199 (+0%)
Mutual labels: jupyter-notebook
Atari Model Zoo
A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.
Stars: β 198 (-0.5%)
Mutual labels: jupyter-notebook
Radio
RadIO is a library for data science research of computed tomography imaging
Stars: β 198 (-0.5%)
Mutual labels: jupyter-notebook
Text detector
Text detection model that combines Retinanet with textboxes++ for OCR
Stars: β 198 (-0.5%)
Mutual labels: jupyter-notebook
Datascience
μ±
) νμ΄μ¬μΌλ‘ λ°μ΄ν° 주무λ₯΄κΈ° - μμ€μ½λ λ° λ°μ΄ν° 곡κ°
Stars: β 199 (+0%)
Mutual labels: jupyter-notebook
Trading Gym
This trading-gym is the first trading for agent to train with episode of short term trading itself.
Stars: β 194 (-2.51%)
Mutual labels: jupyter-notebook
food2vec
Food vectors. Live demo at https://altosaar.github.io/food2vec/, blog post with more information and plots here: https://jaan.io/food2vec-augmented-cooking-machine-intelligence/
Usage
Train a model on the recipes dataset, replicate the results from the blog post:
conda env create -f environment.yml
conda activate food2vec
git clone [email protected]:altosaar/food2vec.git
echo "[submodule \"src/sentence_word2vec\"]
path = src/sentence_word2vec
url = https://github.com/altosaar/sentence_word2vec.git
git submodule update --init
cd food2vec/src
./run_fasttext.sh
Visualization & embedding exploration tools
# run t-sne and make the plots for the ingredient embeddings
jupyter notebook ./src/plot_ingredients_recipes.ipynb
Embedding plot.ly plots to host them yourself
https://gist.github.com/altosaar/67d8456ad28acd1abb497f1950d8de8a
Contributing
Pull requests and all feedback welcome! Please file an issue if you run into problems replicating the results.
Ideas on next steps
- get more data
- convert jupyter notebook for plotting into one python script
- write scripts to figure out the right vocabulary
- fit a better model (e.g. multi-class regression in pytorch) -- if you manage to get better results than the live demo at https://altosaar.github.io/food2vec/ just submit a pull request with the new
assets/data/wordVecs.js
and I'll happily update it :) - compare the above model embeddings to the current embeddings
- make the UI of the website more user-friendly and mobile-friendly
Acknowledgments
Thanks to Anthony for open-sourcing a javascript embedding browser -- the one here is heavily based on it.
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].