March 31, 2022 OBJECT DETECTION

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR2022)

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 […]

March 31, 2022 Helper

Display your data in an attractive way in your notebook

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)

March 31, 2022 Uncategorized Leave a comment

Jigsaw fixes bugs in machine-written software

Large pre-trained language models such as GPT-3, Codex, and others can be tuned to generate code from natural language specifications of programmer intent. Such automated models have the potential to improve productivity for every programmer in the world. But since the models can struggle to understand program semantics, the quality of the resulting code can’t be guaranteed. In our research paper, Jigsaw:

March 31, 2022 Uncategorized Leave a comment

Just Tech: Centering Community-Driven Innovation at the Margins episode 2 with Dr. Tawanna Dillahunt, Zachary Rowe, and Joanna Velazquez

Episode 134 | March 31, 2022 In “Just Tech: Centering Community-Driven Innovation at the Margins,” Senior Principal Researcher Mary L. Gray explores how technology and community intertwine and the role technology can play in supporting community-driven innovation and community-based organizations. Dr. Gray and her team are working to bring computer science, engineering, social science,

March 30, 2022 Tool

Python tools for running and evaluating DM-VIO

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

March 30, 2022 Blender

glTF extras: Speakers and Blender Object Types addon

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 […]

March 30, 2022 Transformer

Ensembling Hugging Face transformers made easy

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 […]

March 30, 2022 YOLO

Implement mosaic image augmentation with YOLO format

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 […]

March 30, 2022 OBJECT DETECTION

Expanding Low-Density Latent Regions for Open-Set Object Detection

OpenDet Expanding Low-Density Latent Regions for Open-Set Object Detection (CVPR2022) Jiaming Han, Yuqiang Ren, Jian Ding, Xingjia Pan, Ke Yan, Gui-Song Xia. arXiv preprint. OpenDet2: OpenDet is implemented based on detectron2. Setup The code is based on detectron2 v0.5. Here is a from-scratch setup script. conda create -n opendet2 python=3.8 -y conda activate opendet2 conda install pytorch=1.8.1 torchvision cudatoolkit=10.1 -c pytorch -y pip install detectron2==0.5 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.8/index.html git clone

March 30, 2022 Adaptation

Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution

Paper Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution Jie Liang*, Hui Zeng*, and Lei Zhang. In arxiv preprint. Abstract Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task due to the unknown complex degradation of real-world images and the limited computation resources in practical applications. Recent research on Real-ISR has achieved significant progress by modeling the image degradation space; however, these methods largely rely on heavy backbone networks and they are inflexible to handle images of different […]

« 1 … 229 230 231 232 233 … 989 »