Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,51 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: static
|
| 7 |
-
pinned:
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Maya4
|
| 3 |
+
emoji: π
|
| 4 |
+
colorFrom: indigo
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: static
|
| 7 |
+
pinned: true
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
thumbnail: >-
|
| 10 |
+
https://cdn-uploads.huggingface.co/production/uploads/68a43a86eea45496edb28ba6/hJyITwdmrofMtEtX8qFmW.png
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# π’ Maya4
|
| 14 |
+
|
| 15 |
+
π **Maya4** is an organization dedicated to curating and providing **multi-level SAR signal representations** from **Sentinel-1 Stripmap** acquisitions.
|
| 16 |
+
|
| 17 |
+
The name *Maya4* is inspired by the **MΔyΔ veil** concept in philosophy, where reality is hidden behind layersβjust as radar signals pass through successive transformations before forming an image.
|
| 18 |
+
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
## π Mission
|
| 22 |
+
|
| 23 |
+
- π‘ Collect and structure **Sentinel-1 Stripmap SAR data**
|
| 24 |
+
- π§© Provide **intermediate signal representations** for research & ML pre-training
|
| 25 |
+
- βοΈ Enable scalable, cloud-native access with **Zarr format**
|
| 26 |
+
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
## π¦ Pre-Training Dataset Spaces
|
| 30 |
+
|
| 31 |
+
Maya4 hosts **Pre-Train (PT) datasets** structured into multiple levels of SAR processing:
|
| 32 |
+
|
| 33 |
+
- π‘ **Raw** β Original SAR echoes
|
| 34 |
+
- ποΈ **RC** β Range Compressed
|
| 35 |
+
- π― **RCMC** β Range Cell Migration Corrected
|
| 36 |
+
- πΌοΈ **Azimuth Compressed**
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
## π Use Cases
|
| 41 |
+
|
| 42 |
+
- π€ **Self-supervised pre-training** of SAR models
|
| 43 |
+
- π°οΈ **Representation learning** for radar signals
|
| 44 |
+
- π¬ **Downstream applications**: classification, detection, reconstruction
|
| 45 |
+
|
| 46 |
+
---
|
| 47 |
+
|
| 48 |
+
## π Acknowledgements
|
| 49 |
+
|
| 50 |
+
- π°οΈ Data provided under the **Copernicus Sentinel-1 mission (ESA)**
|
| 51 |
+
- π’ Curated and maintained by the **Maya4 organization**
|