| 1 |
Vision_Transformer.ipynb |
Build Vision Transformer from scratch (pytorch)
+use pretrained model (via huggingface) |
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale |
Denoising Images |
CIFAR10 : Trainset Accuracy - 67% / Testset Accuracy - 50% |
| 2 |
Swin_Transformer.ipynb |
Build Swin Transformer from scratch (pytorch) |
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows |
AI-based X-ray security screening system |
| |
| 3 |
PEGASUS_to_KoBART.ipynb |
Apply pretraining methodology to KoBART |
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization |
Get Wings! |
| BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension |
| 4 |
[-.ipynb](-) |
YOLOv3: An Incremental Improvement |
Face Mask Detection |
| 5 |
[-.ipynb](-) |
Image-to-Image Translation with Conditional Adversarial Networks
|
Han2Han |
| 6 |
[-.ipynb](-) |
Conditional Generative Adversarial Nets |
| 7 |
[-.ipynb](-) |
Attention is all you need |
Chatbot |
| 8 |
[-.ipynb](-) |
GPT2 |
| 9 |
[-.ipynb](-) |
Colorization Transformer |
Colorization Transformer |
| 10 |
[-.ipynb](-) |
ELECTRA: PRE-TRAINING TEXT ENCODERS AS DISCRIMINATORS RATHER THAN GENERATORS |
Hate Speech Detection |
| 11 |
[-.ipynb](-) |
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers |
Empirical analysis of traffic accidents based on deep learning. |
