Deep Learning, NLP, NMT, AI, ML
A few scripts to draw art to you commit graph on github. The art to draw is defined in gendates.py, you likley want to edit it. Then clone an empty repo to repo: git clone [email protected]:you/somename.git repo Next run doit.sh to generate the commits, It will prompt you for the end date of the art (In ISO date format). Finaly cd into repo and git push –force. enjoy! Tips: If you have a large ammount of contributions, you may want […]
Read more
This downloader is console application targeted for Windows users and all fans of Coub. For now, this downloader is able to download: LIKED coubs from user’s profile (keyword liked) Bookmarked coubs (keyword bookmarks) Coubs from any channel Channel’s reposts Own list of Coub URLs How it works User will input names of what to download. Then the tool it will gather all the links with Coubs metadata. In the second phase it will download all gathered coubs one by one. […]
Read more
This is the official code release for our CVPR21 paper on unsupervised detection and tracking. It produces results slightly better than reported in the paper. [Paper] [Project Page] We use ensemble agreement between 2d and 3d models, as well as motion cues, to unsupervisedly learn object detectors from scratch. Top: 3d detections. Middle: 2d segmentation. Bottom-left: unprojected 2d segmentation, in a bird’s eye view. Bottom-right: 3d detections, in a bird’s eye view. Overview An EM approach to unsupervised tracking. We […]
Read more
A script that lists all current Bisq offers in the terminal Bisq is a decentralized bitcoin exchange that allows us to buy or sell bitcoin peer-to-peer. This script shows all current buy or sell offers in the Bisq network in our preferred fiat currency. We can indicate the following paramenters in our script header: avoid_methods: payment methods to hide in order to get a cleaner output lsbisq.py -t -f -d Where: : (string) BUY or SELL (example: -t BUY). Default […]
Read more
Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR2022)[paper] Authors: Chenhang He, Ruihuang Li, Shuai Li, Lei Zhang. This project is built on OpenPCDet. Introduction Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. To solve this issue, existing methods usually compute self-attention locally by grouping the points […]
Read more
Bloxs is a simple python package that helps you display information in an attractive way (formed in blocks). Perfect for building dashboards, reports and apps in the notebook. It works with: Jupyter Notebook, Google Colab, Deepnote, Kaggle Notebook, Mercury. Get started Install bloxs: Import and create a bloxs: from bloxs import B B(1234, “Bloxs in notebook!”) Exmaples Bloxs Code B(1234, “Bloxs in notebook!”) B(1999, “Percent change!”, percent_change=10)
Read more
When using this project in academic work, please consider citing: @article{stumberg22dmvio, author = {L. von Stumberg and D. Cremers}, title = {{DM-VIO}: Delayed Marginalization Visual-Inertial Odometry}, journal = {{IEEE} Robotics and Automation Letters ({RA-L})}, year = {2022}, volume = {7}, number = {2}, pages = {1408-1415}, doi = {10.1109/LRA.2021.3140129} } Dependencies: Install dependencies with: pip3 install tqdm ruamel.yaml pyquaternion matplotlib tabulate Step 0: Download and build
Read more
This addon exports Speakers data and Blender Object types into extra fields of a glTF. extras are custom fields you can write into the glTF. They will mean nothing for a official, standard glTF importer. To actually make use of those data, a parsing function must be coded in the importer, I’ll provide a sample method for three.js, that’s the environment this addon was built for. THOSE ARE NOT NATIVE glTF FUNCTIONALITIES, NOR THIS ADDON WILL ADD ANY FUNCTIONALITY TO […]
Read more
Ensembling Hugging Face Transformers made easy! Why Ensemble Transformers? Ensembling is a simple yet powerful way of combining predictions from different models to increase performance. Since multiple models are used to derive a prediction, ensembling offers a way of decreasing variance and increasing robustness. Ensemble Transformers provides an intuitive interface for ensembling pretrained models available in Hugging Face transformers. Installation Ensemble Transformers is available on PyPI and can easily be installed with the pip package manager. pip install -U pip […]
Read more
This is an implementation for mosaic image augmention with YOLO format Run code to perform mosaic augmentation: python main.py –width 800 –height 800 –scale_x 0.4 –scale_y 0.6 –min_area 500 –min_vi 0.3 You can change parameters to fit with your dataset. To know details about arguments in the command above, run –width: width of mosaic-augmented image –height: height of mosaic-augmented image –scale_x: scale_x – scale by width => define width of the top left image –scale_y: scale_y – scale by height […]
Read more