ShaoTengLiu / Hyperbolic_zsl
Hyperbolic Visual Embedding Learning for Zero-Shot Recognition (CVPR 2020)
Stars: ✭ 39
Labels
Projects that are alternatives of or similar to Hyperbolic zsl
Vespcn Tensorflow
Tensorflow implementation of VESPCN
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Vietnamese Accent Model
A simple deep learning model to add accent to Vietnamese text.
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Stylegan2 Ada Google Colab Starter Notebook
A colab notebook for training Stylegan2-ada on colab, transfer learning onto your own dataset.
Stars: ✭ 39 (+0%)
Mutual labels: jupyter-notebook
Adventures In Ml Code
This repository holds all the code for the site http://www.adventuresinmachinelearning.com
Stars: ✭ 989 (+2435.9%)
Mutual labels: jupyter-notebook
Stock Market Prediction Using Natural Language Processing
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Flexx Notebooks
Jupyter notebooks with Flexx examples.
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Perfect Guide About Machine Learning Study
파이썬 머신러닝 완벽 가이드를 교재로 진행한 쏘카 데이터 그룹 사내 스터디 보완 자료
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Coursera Natural Language Processing Specialization
Programming assignments from all courses in the Coursera Natural Language Processing Specialization offered by deeplearning.ai.
Stars: ✭ 39 (+0%)
Mutual labels: jupyter-notebook
Pithermalcam
The PiThermalCam Project connects an MLX90640 Thermal IR Camera to a Raspberry Pi for viewing or web streaming.
Stars: ✭ 39 (+0%)
Mutual labels: jupyter-notebook
Bottom Up Attention
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
Stars: ✭ 989 (+2435.9%)
Mutual labels: jupyter-notebook
Deep Learning Coursera
Deep Learning Andrew Ng Coursera
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Optimal Transport
Optimal transport and generalizations
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Bdmi 2020a
Big Data and Machine Intelligence, Autumn 2020.
Stars: ✭ 39 (+0%)
Mutual labels: jupyter-notebook
Deeplearningwithpython
Machine Learning and Data Science study group starting Sep'2018
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Parsing Pdfs
Extracting tabular information from PDFs using python
Stars: ✭ 38 (-2.56%)
Mutual labels: jupyter-notebook
Dpcn
The official code implementation of "Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching", CoRL2020.
Stars: ✭ 39 (+0%)
Mutual labels: jupyter-notebook
Hyperbolic ZSL
This is the PyTorch implementation of paper: Hyperbolic Visual Embedding Learning for Zero-Shot Recognition (CVPR 2020)
Using Our Code
git clone [email protected]:ShaoTengLiu/Hyperbolic_ZSL.git
cd Hyperbolic_ZSL/code
Hyperbolic_ZSL/code is the default root directory.
Environment Requirements
- anaconda is recommended
- PyTorch version 1.0 or higher
- At least one GPU with adequate memory
- python 3.7 (python 2 may be possible with modifications)
Use environment.yml for quick start.
conda env create -f environment.yml
Data Preparation
Generate data and put them in these folders:
- ../data/train/img: pretrained feature from ResNet of ImageNet
- ../data/val/img: pretrained feature from ResNet of ImageNet
- ../data/train/label: pretrained word embedding from chosen word model
- ../data/val/label: pretrained word embedding from chosen word model
Quick Start
One can run our code via
CUDA_VISIBLE_DEVICES=1 python devise_hype.py \
--word_model poincare \
--model_folder model_path \
--loss_path loss_path \
--dimension 300
- model_path: the folder to save models
- loss_path: the .jpg tp save loss curve
To run DeViSE in Euclidean space via
CUDA_VISIBLE_DEVICES=2 python devise.py \
--word_model glove \
--model_folder model_path \
--loss_path loss_path \
--dimension 600
Acknowledgement
Tools for computation in Riemannian geometry are not developed by us. One can extend his model to hyperbolic space with these tools. Thanks to these good repos.
-
hyrnn can be found in hyrnn
-
geoopt can be found in geoopt
-
poincare_glove can be found in poincare_glove
-
poincare-embeddings can be found in poincare-embeddings
Code refactoring is still continuing
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].