NingAnMe / Label-Smoothing-for-CrossEntropyLoss-PyTorch
add a Arg: label_smoothing for torch.nn.CrossEntropyLoss()
☆14Updated 3 years ago
Related projects: ⓘ
- Learning to Encode Position for Transformer with Continuous Dynamical Model☆59Updated 4 years ago
- code for EMNLP2018 paper 'Associative-multichannel-autoencoder for multimodal word representation'☆13Updated 6 years ago
- Implementation of Mogrifier LSTM in PyTorch☆35Updated 4 years ago
- ☆22Updated 2 years ago
- My implementation of the gMLP model from the paper "Pay Attention to MLPs".☆25Updated 3 years ago
- Official PyTorch implementation of Time-aware Large Kernel (TaLK) Convolutions (ICML 2020)☆29Updated 3 years ago
- code for Explicit Sparse Transformer☆57Updated last year
- ☆20Updated 4 years ago
- A metric learning method to learn a provably robust Mahalanobis distance☆10Updated 2 years ago
- Custom loss functions to use in (mainly) PyTorch.☆35Updated 3 years ago
- ☆22Updated last year
- Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch☆70Updated 4 years ago
- Official implementation of ICLR 2020 paper Unsupervised Clustering using Pseudo-semi-supervised Learning☆48Updated 3 years ago
- Code for the PAPA paper☆27Updated last year
- MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space☆40Updated 3 years ago
- Unofficial PyTorch implementation of the paper "cosFormer: Rethinking Softmax In Attention".☆43Updated 2 years ago
- Implementation of dynamic temporal pooling (DTP) for time series classification☆38Updated 2 years ago
- Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)☆69Updated 4 years ago
- A quick walk-through of the innards of LSTMs and a naive implementation of the Mogrifier LSTM paper in PyTorch☆73Updated 4 years ago
- Multimodal classification solution for the SIGIR eCOM using Co-attention and transformer language models☆19Updated 4 years ago
- A PyTorch implementation of the Compact Multi-Head Self-Attention Mechanism from the paper: "Low Rank Factorization for Compact Multi-Hea…☆23Updated 4 years ago
- A PyTorch implementation of the paper - "Synthesizer: Rethinking Self-Attention in Transformer Models"☆70Updated last year
- The official implementation of Triplet Attention.☆22Updated 2 years ago
- ☆12Updated 4 years ago
- How Does Selective Mechanism Improve Self-attention Networks?☆27Updated 3 years ago
- Multi-Source Domain Attention☆13Updated 3 years ago
- Code and data for the SIGIR'2021 paper "Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification"☆9Updated 3 years ago
- 🤗An unofficial PyTorch implementation of ConvBert based on huggingface/transformers.☆16Updated last year
- For paper《Gaussian Transformer: A Lightweight Approach for Natural Language Inference》☆27Updated 4 years ago
- ☆40Updated last year