ztshuaiUCLA commited on
Commit
d58cebb
·
verified ·
1 Parent(s): b378636

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -15
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  license: apache-2.0
3
  library_name: pytorch
4
- pipeline_tag: time-series-forecasting
5
  tags:
6
  - sensor-time-series
7
  - physiological-signal
@@ -13,19 +13,16 @@ datasets:
13
  - physionet/mimic-iv-ecg
14
  ---
15
 
16
- # SensorGen-SiT
17
 
18
  [![Paper](https://img.shields.io/badge/paper-arXiv-red)](#)
19
  [![Webpage](https://img.shields.io/badge/website-project--page-blue)](#)
20
  [![GitHub](https://img.shields.io/badge/code-GitHub-181717?logo=github)](https://github.com/yang-ai-lab/SensorGen)
21
- [![HuggingFace](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-SensorGen--SiT-FFD21E)](https://huggingface.co/yang-ai-lab/SensorGen-SiT)
22
  [![Python](https://img.shields.io/badge/python-3.10%2B-brightgreen)](https://www.python.org/)
23
  [![PyTorch](https://img.shields.io/badge/PyTorch-2.4%2B-EE4C2C?logo=pytorch)](https://pytorch.org/)
24
 
25
 
26
- > Scalable Interpolant Transformer (SiT-B/1d) reference models for the
27
- > SensorGen benchmark on real-world sensor time series.
28
-
29
  This repository hosts the pre-trained checkpoints used in the SensorGen study
30
  ("*Signal or Noise? Understanding Generative Models for Real-World Sensor
31
  Time Series*").
@@ -36,12 +33,6 @@ Time Series*").
36
  | `bp_translation.pt` | PPG and NIBP to invasive BP | VitalDB |
37
 
38
 
39
- For VitalDB forecasting we observed a U-shape in validation loss past ~20K
40
- steps; the **18K best-validation checkpoint** is what we use to report paper
41
- numbers. The 200K extended checkpoint is provided as a reference for
42
- practitioners who prefer the longer-trained generator at the cost of mild
43
- overfit on the validation set.
44
-
45
 
46
  ## Usage
47
 
@@ -54,15 +45,15 @@ Pair this checkpoint repository with the GitHub code release at
54
  from huggingface_hub import hf_hub_download
55
 
56
  ckpt_path = hf_hub_download(
57
- repo_id="yang-ai-lab/SensorGen-SiT",
58
  filename="text2ecg.pt",
59
  )
60
  ```
61
 
62
- ### Download all checkpoints (≈26 GB)
63
 
64
  ```bash
65
- hf download yang-ai-lab/SensorGen-SiT --local-dir ./ckpts
66
  ```
67
 
68
 
 
1
  ---
2
  license: apache-2.0
3
  library_name: pytorch
4
+ pipeline_tag: time-series-generation
5
  tags:
6
  - sensor-time-series
7
  - physiological-signal
 
13
  - physionet/mimic-iv-ecg
14
  ---
15
 
16
+ # SensorGen
17
 
18
  [![Paper](https://img.shields.io/badge/paper-arXiv-red)](#)
19
  [![Webpage](https://img.shields.io/badge/website-project--page-blue)](#)
20
  [![GitHub](https://img.shields.io/badge/code-GitHub-181717?logo=github)](https://github.com/yang-ai-lab/SensorGen)
21
+ [![HuggingFace](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-SensorGen-FFD21E)](https://huggingface.co/yang-ai-lab/SensorGen-SiT)
22
  [![Python](https://img.shields.io/badge/python-3.10%2B-brightgreen)](https://www.python.org/)
23
  [![PyTorch](https://img.shields.io/badge/PyTorch-2.4%2B-EE4C2C?logo=pytorch)](https://pytorch.org/)
24
 
25
 
 
 
 
26
  This repository hosts the pre-trained checkpoints used in the SensorGen study
27
  ("*Signal or Noise? Understanding Generative Models for Real-World Sensor
28
  Time Series*").
 
33
  | `bp_translation.pt` | PPG and NIBP to invasive BP | VitalDB |
34
 
35
 
 
 
 
 
 
 
36
 
37
  ## Usage
38
 
 
45
  from huggingface_hub import hf_hub_download
46
 
47
  ckpt_path = hf_hub_download(
48
+ repo_id="yang-ai-lab/SensorGen",
49
  filename="text2ecg.pt",
50
  )
51
  ```
52
 
53
+ ### Download all checkpoints
54
 
55
  ```bash
56
+ hf download yang-ai-lab/SensorGen --local-dir ./ckpts
57
  ```
58
 
59