Pytorch Tutorial
Intro
[D] What deep learning papers should I implement to learn?에서 가져온 논문 리스트를 PyTorch 구현하는 연습 repo입니다.
현재 각 모델은 Google Colab 또는 Kaggle 커널을 사용하여 진행할 예정이며, 모델의 구현 과정은 강의로 후에 찍을 예정입니다.
Architectures
| Title | paper | code | reference |
|---|---|---|---|
| AlexNet | paper | ||
| ZFNet | paper | ||
| VGG16 | paper | ||
| ResNet | paper | ||
| GoogLeNet | paper | ||
| Inception | paper | ||
| Xception | paper | ||
| MobileNet | paper |
Semantic Segmentation
| Title | paper | code | reference |
|---|---|---|---|
| FCN | paper | ||
| SegNet | paper | ||
| UNet | paper | ||
| PSPNet | paper | ||
| DeepLab | paper | ||
| ICNet | paper | ||
| ENet | paper |
Generative adversarial networks
| Title | paper | code | reference |
|---|---|---|---|
| GAN | paper | ||
| DCGAN | paper | ||
| WGAN | paper | ||
| Pix2Pix | paper | ||
| CycleGAN | paper |
Object detection
| Title | paper | code | reference |
|---|---|---|---|
| RCNN | paper | ||
| Fast-RCNN | paper | ||
| Faster-RCNN | paper | ||
| SSD | paper | ||
| YOLO | paper | ||
| YOLO9000 | paper |