View Code? Open in Web Editor
NEW
This project forked from davide-coccomini/timesformer-video-classification
The notebook explains the various steps to obtain the results of publication: "Is Space-Time Attention All You Need for Video Understanding?"
timesformer-video-classification's Introduction
- Experienced data scientist with masters in Data Science from London School of Economics.
- Currently data science trainer at LSE Digital Skills Lab for Python, R, SQL.
- 🔭 Focusing on Advanced Deep Learning algorithms.
| Project Area |
Name of the Project |
| Computer Vision |
ColorVision Assist using cv2 |
| Deep Learning |
CIFAR-10 Image Classification with PyTorch |
| Natural Language Proecessing |
Sentiment Analysis on webscraped reviews |
| Speech Processing |
Voice Commands Decoded: Tensorflow Speech-to-Text Model |
| Artificial Intelligence |
Image classification through VGG16 |
| Code |
Name |
| ST449 |
Artificial Intelligence |
| MY474 |
Machine Learning |
| ST446 |
Distributed Computing for Big Data |
| ST456 |
Deep Learning |
| MY472 |
Data for Data Scientists with Cloud Computing |
| MY470 |
Computer Programming |
timesformer-video-classification's People
Contributors
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent