Backprop Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models. Solve a variety of tasks with pre-trained models or finetune them in one line for your own tasks. Out of the box tasks you can solve with Backprop: Conversational question answering in English Text Classification in 100+ languages Image Classification Text Vectorisation in 50+ languages Image Vectorisation Summarisation in English Emotion detection in English Text Generation For more specific use cases, you can adapt a task with […]

Torchsort Pure PyTorch implementation of Fast Differentiable Sorting and Ranking (Blondel et al.). Much of the code is copied from the original Numpy implementation at google-research/fast-soft-sort, with the isotonic regression solver rewritten as a PyTorch C++ and CUDA extension. Install pip install torchsort To build the CUDA extension you will need the CUDA toolchain installed. If youwant to build in an environment without a CUDA runtime (e.g. docker), you willneed to export the environment variableTORCH_CUDA_ARCH_LIST=”Pascal;Volta;Turing” before installing. Usage torchsort exposes […]

focal-frequency-loss This repository will provide the official code for the following paper: Focal Frequency Loss for Generative ModelsLiming Jiang, Bo Dai, Wayne Wu and Chen Change LoyarXiv preprint, 2020. Abstract: Despite the remarkable success of generative models in creating photorealistic images using deep neural networks, gaps could still exist between the real and generated images, especially in the frequency domain. In this study, we find that narrowing the frequency domain gap can ameliorate the image synthesis quality further. To this […]

ParallelStencil.jl ParallelStencil empowers domain scientists to write architecture-agnostic high-level code for parallel high-performance stencil computations on GPUs and CPUs. Performance similar to CUDA C can be achieved, which is typically a large improvement over the performance reached when using only CUDA.jl Array programming. For example, a 2-D shallow ice solver presented at JuliaCon 2020 [1] achieved a nearly 20 times better performance than a corresponding CUDA.jl Array programming implementation; in absolute terms, it reached 70% of the theoretical upper performance […]