Tool

A tool to create pixel-accurate energy diagrams as ChemDraw object

A tool to create pixel-accurate energy diagrams as ChemDraw object. A Chinese version of this article is available. Execution If you don’t have Python environment, there is an executable version (packed by cx_freeze on Windows 10) in the release. Run Draw_Energy_Diagram_XML.exe in the folder. Alternatively, if you have a Python environment with PyQt, openpyxl and matplotlib, call the main script by first cd / dir to the project folder and call: python Draw_Energy_Diagram_XML.py. (On windows, you can also just double […]

Read more
Translation

Maximum Spatial Perturbation for Image-to-Image Translation (Official Implementation)

This repository is by Yanwu Xu and contains the PyTorch source code to reproduce the experiments in our CVPR2022 paper Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation by Yanwu Xu, Shaoan Xie, Wenhao Wu, Kun Zhang, Mingming Gong* and Kayhan Batmanghelich* (* Equal Advising) Purturbation Consistency Spatial Alignment Face Pose Transfer data can be downloaded here Experiments on real data To run the code on the face pose transfer data. 1. download the data from above link 2. unzip […]

Read more
Wrapper

A multi-lingual approach to AllenNLP CoReference Resolution using along with a wrapper for spaCy

Coreference is amazing but the data required for training a model is very scarce. In our case, the available training for non-English languages also proved to be poorly annotated. Crosslingual Coreference, therefore, uses the assumption a trained model with English data and cross-lingual embeddings should work for languages with similar sentence structures. pip install crosslingual-coreference

Read more
eink

eInk Display for the PiHole

eInk Display for the PiHole Inspired by: https://github.com/neauoire/inky-hole Display statistics including the number of blocked requests, and filtered traffic, from Pi-Hole, on Pimoroni’s Inky pHAT. Default display / Simple display (using –simple option): LCARS display (using –lcars option) / LCARS + Simple: Installation Setup Pi-Hole, follow the installation instructions. Setup Inky pHAT, follow the installation instructions. Clone this repo on your Raspberry Pi Zero W. git clone https://github.com/doublehelix/inky-pihole.git Test your setup Executing the following command will run the script   […]

Read more
Simulator

Small numerical simulator example

This is a small example of the kind of small numerical simulator I often write as I explore the dynamics of different kinds of systems. It’s not sophisticated, or advanced, but it is powerful. Usage python3 ski_sim.py | tee results.png This type of code runs multiple times faster with Pypy than it does with standard python. Exercises (Simple) Replace the normal distributions with distributions with other shapes, especially heavy tails. (Simple) Measure queue wait latency directly, calculating percentiles or other […]

Read more
Terminal

A very impractical 3D rendering engine that runs in the python terminal

A very impractical 3D rendering engine that runs in the python terminal. do NOT try to run this program using the standard python IDE as it does not use ANSI escape codes. If your terminal of choice does not support ANSI escape codes it will also break in the same way. ONLY ON VERSIONS BEFORE 0.1.3: Due to the time it takes to use the print command, sometimes the screen will refresh while the program is in the process of […]

Read more
Generator

Bailando: 3D dance generation via Actor-Critic GPT with Choreographic Memory

Code for CVPR 2022 (oral) paper “Bailando: 3D dance generation via Actor-Critic GPT with Choreographic Memory” [Paper] | [Project Page] | [Video Demo] Driving 3D characters to dance following a piece of music is highly challenging due to the spatial constraints applied to poses by choreography norms. In addition, the generated dance sequence also needs to maintain temporal coherency with different music genres. To tackle these challenges, we propose a novel music-to-dance framework, Bailando, with two powerful components: 1) a […]

Read more
JAX

CLOOB training (JAX) and inference (JAX and PyTorch)

Pretrained models PyTorch from cloob_training import model_pt, pretrained pretrained.list_configs() returns: [‘cloob_laion_400m_vit_b_16_16_epochs’, ‘cloob_laion_400m_vit_b_16_32_epochs’] The models can be used by: config = pretrained.get_config(‘cloob_laion_400m_vit_b_16_16_epochs’) model = model_pt.get_pt_model(config) checkpoint = pretrained.download_checkpoint(config) model.load_state_dict(model_pt.get_pt_params(config, checkpoint)) model.eval().requires_grad_(False).to(‘cuda’) Model class attributes: model.config: the model config dict. model.image_encoder: the image encoder, which expects NCHW batches of normalized images (preprocessed by model.normalize), where C    

Read more
1 … 188 189 190 191 192 … 935