Structured-Self-Attention
Self attention model
A deep learning model that generates sentence embeddings using structured self-attention and is used for binary and multiclass classification tasks.
A Structured Self-attentive Sentence Embedding
494 stars
13 watching
106 forks
Language: Python
last commit: about 5 years ago attentionattention-mechanismattention-modelattention-weightsclassificationdeep-learningpython3pytorchself-attentionself-attentive-rnnsentence-embeddingsvisualization
Related projects:
| Repository | Description | Stars |
|---|---|---|
 javeywang/pyramid-attention-networks-pytorch | An implementation of a deep learning model using PyTorch for semantic segmentation tasks. | 235 |
 peteanderson80/bottom-up-attention | Trains a bottom-up attention model using Faster R-CNN and Visual Genome annotations for image captioning and VQA tasks | 1,433 |
 sinashish/multi-scale-attention | A deep learning framework for medical image segmentation using multi-scale guided attention mechanisms to improve accuracy and reduce irrelevant information. | 460 |
 openai/sparse_attention | Provides primitives for sparse attention mechanisms used in transformer models to improve computational efficiency and scalability | 1,524 |
 speedinghzl/ccnet | An implementation of a deep learning model for semantic segmentation using a novel attention mechanism to capture long-range dependencies in images. | 1,426 |
 koichiro11/residual-attention-network | An image classification neural network implementation using attention mechanisms and residual learning | 94 |
 emedvedev/attention-ocr | A TensorFlow model for recognizing text in images using visual attention and a sequence-to-sequence architecture. | 1,077 |
 akosiorek/attend_infer_repeat | An implementation of Attend, Infer, Repeat, a method for fast scene understanding using generative models. | 82 |
 hszhao/psanet | A deep learning framework for semantic segmentation with spatial attention mechanisms | 216 |
 nikitakit/self-attentive-parser | An NLP parser with high accuracy models for multiple languages | 871 |
 lxtgh/omg-seg | Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,300 |
 jiasenlu/adaptiveattention | Adaptive attention mechanism for image captioning using visual sentinels | 334 |
 stared/keras-sequential-ascii | A tool for displaying detailed ASCII summaries of Keras sequential models. | 126 |
 szagoruyko/attention-transfer | Improves performance of convolutional neural networks by transferring knowledge from teacher models to student models using attention mechanisms. | 1,444 |
 pistony/residualattentionnetwork | A Gluon implementation of Residual Attention Network for image classification tasks | 107 |