fkodom / fft-conv-pytorch
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
☆494Updated last year
Alternatives and similar repositories for fft-conv-pytorch:
Users that are interested in fft-conv-pytorch are comparing it to the libraries listed below
- DCT (discrete cosine transform) functions for pytorch☆608Updated 2 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆577Updated 5 months ago
- An All-MLP solution for Vision, from Google AI☆1,020Updated 7 months ago
- Implementation of a U-net complete with efficient attention as well as the latest research findings☆278Updated last year
- This is an official pytorch implementation of Fast Fourier Convolution.☆372Updated 11 months ago
- Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet☆1,057Updated last year
- Tiny PyTorch library for maintaining a moving average of a collection of parameters.☆428Updated 7 months ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆763Updated last year
- Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision☆217Updated 4 years ago
- An implementation of local windowed attention for language modeling☆445Updated 3 months ago
- [NeurIPS 2021] [T-PAMI] Global Filter Networks for Image Classification☆473Updated last year
- Escaping the Big Data Paradigm with Compact Transformers, 2021 (Train your Vision Transformers in 30 mins on CIFAR-10 with a single GPU!)☆526Updated 6 months ago
- Learning Rate Warmup in PyTorch☆410Updated last month
- Implementation of Axial attention - attending to multi-dimensional data efficiently☆377Updated 3 years ago
- Compute CNN receptive field size in pytorch in one line☆360Updated 11 months ago
- Code repository of the paper "Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN" https://arxiv.org/abs…☆183Updated 2 years ago
- Implementation of ConvMixer for "Patches Are All You Need? 🤷"☆1,071Updated 2 years ago
- An implementation of the efficient attention module.☆309Updated 4 years ago
- Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)☆218Updated last month
- [ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?☆331Updated 2 years ago
- Implementation of Linformer for Pytorch☆282Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆213Updated 2 years ago
- The correct way to resize images or tensors. For Numpy or Pytorch (differentiable).☆559Updated last year
- ☆458Updated 2 years ago
- Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022☆1,115Updated 11 months ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆377Updated last year
- optimizer & lr scheduler & loss function collections in PyTorch☆293Updated this week
- Estimate/count FLOPS for a given neural network using pytorch☆303Updated 2 years ago
- Code repository for the ICLR 2022 paper "FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes" https://openreview.ne…☆115Updated 2 years ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆259Updated 3 years ago