Keras documentaion에 올라온 코드를 Pytorch로 코드 이전하는 스터디 입니다.

keras documentaion examples

Original github address: https://github.com/keras-team/keras-io

시작 일자: 2021.03.04(목)

수료생(Previous members)

Hyeongwon	Subin	Yonggi	Yookyung
Github	Github	Github	Github

참여자(Current members)

Jeongsub	Jaehyuk	Sunwoo	Suzie
Github	Github	Github	Github

• Image segmentation with a U-Net-like architecture [Jeongseob Kim]
• 3D image classification from CT scans
• Semi-supervision and domain adaptation with AdaMatch
• Classification using Attention-based Deep Multiple Instance Learning (MIL).
• Convolutional autoencoder for image denoising [Jeongseob Kim]
• Barlow Twins for Contrastive SSL
• Image Classification using BigTransfer (BiT)
• OCR model for reading Captchas [Subin Kim]
• Compact Convolutional Transformers
• Consistency training with supervision
• Next-Frame Video Prediction with Convolutional
• Image classification with ConvMixer
• CutMix data augmentation for image classification [Jaehyuk Heo]
• Multiclass semantic segmentation using DeepLabV3
• Monocular depth estimation [Hyeongwon Kang]
• Image classification with EANet (External Attention Transformer)
• FixRes: Fixing train-test resolution discrepancy
• Grad-CAM class activation visualization [Jaehyuk Heo]
• [Gradient Centralization for Better Training Performance] (https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Gradient_Centralization_for_Better_Training_Performance) [Jaehyuk Heo]
• Handwriting recognition
• Image Captioning [Yonggi Jeong]
• Image classification via fine-tuning with EfficientNet
• Image classification with Vision Transformer [Jaehyuk Heo]
• Model interpretability with Integrated Gradients [Jaehyuk Heo]
• Involutional neural networks [Subin Kim]
• Keypoint Detection with Transfer Learning
• Knowledge Distillation [Jaehyuk Heo]
• Learning to Resize in Computer Vision
• Masked image modeling with Autoencoders
• Metric learning for image similarity search [Jaehyuk Heo]
• Low-light image enhancement using MIRNet
• MixUp augmentation for image classification
• Image classification with modern MLP models
• MobileViT: A mobile-friendly Transformer-based model for image classification
• Near-duplicate image search
• 3D volumetric rendering with NeRF
• Self-supervised contrastive learning with NNCLR
• Augmenting convnets with aggregated attention
• Image classification with Perceiver
• Point cloud classification with PointNet [Hyeongwon Kang]
• Point cloud segmentation with PointNet [Hyeongwon Kang]
• RandAugment for Image Classification for Improved Robustness [Yonggi Jeong]
• Few-Shot learning with Reptile
• Object Detection with RetinaNet [Jaehyuk Heo]
• Semantic Image Clustering [Yonggi Jeong]
• Semi-supervised image classification using contrastive pretraining with SimCLR [Subin Kim]
• Image similarity estimation using a Siamese Network with a contrastive loss
• Image similarity estimation using a Siamese Network with a triplet loss [Yonggi Jeong]
• Self-supervised contrastive learning with SimSiam [Jaehyuk Heo]
• Image Super-Resolution using an Efficient Sub-Pixel CNN
• Supervised Contrastive Learning [Subin Kim]
• Image classification with Swin Transformers
• Learning to tokenize in Vision Transformers
• Video Classification with Transformers Video Vision Transformer [Hyeongwon Kang]
• Visualizing what convnets learn [Jaehyuk Heo]
• Train a Vision Transformer on small datasets
• Zero-DCE for low-light image enhancement
• Model Soup [Jaehyuk Heo]
• Finetuning ViT with LoRA [Jaehyuk Heo]

• Review Classification using Active Learning
• Sequence to sequence learning for performing number addition [Yookyung Kho]
• Bidirectional LSTM on IMDB [Jeongseob Kim]
• Character-level recurrent sequence-to-sequence model [Jeongseob Kim]
• End-to-end Masked Language Modeling with BERT [Subin Kim]
• Large-scale multi-label text classification
• Multimodal entailment [Yookyung Kho]
• Named Entity Recognition using Transformers [Subin Kim]
• English-to-Spanish translation with a sequence-to-sequence Transformer [Yookyung Kho]
• Natural language image search with a Dual Encoder [Subin Kim]
• Using pre-trained word embeddings
• Question Answering with Hugging Face Transformers [Yookyung Kho]
• Semantic Similarity with BERT [Jaehyuk Heo]
• Text classification with Switch Transformer [Subin Kim]
• Text classification with Transformer [Yookyung Kho]
• Text Extraction with BERT [Jaehyuk Heo]
• Text Generation using FNet

• TorchText introduction [Jeongseob Kim]
• Table Pre-training with TapasForMaskedLM [Yookyung Kho]

• Classification with Gated Residual and Variable Selection Networks [Hyeongwon Kang]
• Collaborative Filtering for Movie Recommendations [Hyeongwon Kang]
• Classification with Neural Decision Forests
• Imbalanced classification: credit card fraud detection
• A Transformer-based recommendation system [Hyeongwon Kang]
• Structured data learning with TabTransformer [Hyeongwon Kang]
• Structured data learning with Wide, Deep, and Cross networks

• Timeseries anomaly detection using an Autoencoder [Hyeongwon Kang]
• Timeseries classification with a Transformer model [Hyeongwon Kang]
• Traffic forecasting using graph neural networks and LSTM
• Timeseries forecasting for weather prediction [Hyeongwon Kang]

• Automatic Speech Recognition using CTC
• MelGAN-based spectrogram inversion using feature matching
• Speaker Recognition [Subin Kim]
• Automatic Speech Recognition with Transformer

• Variational AutoEncoder [Jaehyuk Heo]
• DCGAN to generate face images [Hyeongwon Kang]
• WGAN-GP overriding Model.train_step
• Neural style transfer [Subin Kim]
• Deep Dream [Jaehyuk Heo]
• Neural Style Transfer with AdaIN
• Conditional GAN [Yonggi Jeong]
• CycleGAN [Yonggi Jeong]
• Data-efficient GANs with Adaptive Discriminator Augmentation
• GauGAN for conditional image generation
• Character-level text generation with LSTM
• PixelCNN [Jeongseob Kim]
• Density estimation using Real NVP [Jeongseob Kim]
• Face image generation with StyleGAN
• Text generation with a miniature GPT [Subin Kim]
• Vector-Quantized Variational Autoencoders
• WGAN-GP with R-GCN for the generation of small molecular graphs

• Distributions_TFP_Pyro [Jeongseob Kim]
• Non-linear Independent Component Estimation (NICE) [Jeongseob Kim]
• Diffusion generative model(Tutorials) [Jeongseob Kim]
• Diffusion generative model(Examples - Swiss-roll, MNIST, F-MNIST, CELEBA) [Jeongseob Kim]
• Score based generative model(Tutorials) [Jeongseob Kim]

• Actor Critic Method [Hyeongwon Kang]
• Deep Deterministic Policy Gradient (DDPG) [Hyeongwon Kang]
• Deep Q-Learning for Atari Breakout [Hyeongwon Kang]
• Proximal Policy Optimization [Hyeongwon Kang]

• Graph attention networks for node classification
• Node Classification with Graph Neural Networks
• Message-passing neural network for molecular property prediction
• Graph representation learning with node2vec

• Fast Gradient Sign Method [Jaehyuk Heo]
• Projected Gradient Descent [Jaehyuk Heo]

• PatchCore [Jaehyuk Heo]

• Automatic Mixed Precision [Jaehyuk Heo]
• Gradient Accumulation [Jaehyuk Heo]
• Distributed Data Parallel [Jaehyuk Heo]