mathmanu commited on
Commit
9874c54
·
verified ·
1 Parent(s): b87c0aa

Update intro card

Browse files
Files changed (1) hide show
  1. README.md +5 -17
README.md CHANGED
@@ -11,10 +11,8 @@ pinned: false
11
 
12
  <img src="https://huggingface.co/spaces/TIEdgeAI/README/resolve/main/docs/assets/TXN-Logo.png" alt="Texas Instruments" width="80" height="80" />
13
 
14
-
15
  # Texas Instruments
16
 
17
-
18
  ### Semiconductor solutions for embedded and edge applications
19
 
20
  </div>
@@ -24,17 +22,12 @@ pinned: false
24
  [![Models](https://img.shields.io/badge/Models-50%2B-brightgreen)](https://huggingface.co/TexasInstruments-EdgeAI) [![Hardware](https://img.shields.io/badge/Hardware-TI%20MPUs%20With%20C7%20NPU-brightgreen)](https://huggingface.co/TexasInstruments-EdgeAI) [![License](https://img.shields.io/badge/License-Open%20Source-brightgreen)](https://huggingface.co/TexasInstruments-EdgeAI)
25
 
26
  Bring Your Own Models and deploy on Texas Instruments Micro Processors with C7 NPU acceleration
27
- <details open>
28
-
29
- #### [TI Edge-AI Model Hub](https://huggingface.co/TexasInstruments-EdgeAI)
30
-
31
- Pre-trained AI models for TI edge devices, with scripts & configs for compilation, benchmark and deployment. Browse the full model catalog, docs & deployment guides.
32
 
 
33
  - Optimized, benchmarked on real hardware & portable across TI MPU devices; automated compile/benchmark/deploy scripts
34
  - Image classification (ResNet, ViT, ConvNeXt, DINO/DINOv2, MobileNetV3) & object detection (YOLO11/26/v8/X, RT-DETRv2, RTMDet, RF-DETR, DETR & more)
35
  - Validated on C7 NPU SOCs: AM62A, TDA4AEN/AM67A, TDA4VM, TDA4VE/TDA4VL/AM68A, TDA4VH/AM69A
36
- - **Use cases:** Automotive · Aerospace & Defense · Industrial · Surveillance · Robotics · Edge IoT
37
- </details>
38
 
39
  ---
40
 
@@ -42,22 +35,17 @@ Pre-trained AI models for TI edge devices, with scripts & configs for compilatio
42
  [![Devices](https://img.shields.io/badge/MCU%20Devices-MSP%20%7C%20AM13%20%7C%20C2000%20%7C%20Radar-brightgreen)](https://github.com/TexasInstruments/tinyml-modelzoo) [![GUI Tooling](https://img.shields.io/badge/GUI%20Tooling-Edge%20AI%20Studio-brightgreen)](https://www.ti.com/tool/EDGE-AI-STUDIO)
43
 
44
  Bring Your Own Data or Bring Your Own Models and deploy on TI microcontrollers, connectivity devices & radar sensors
45
- <details open>
46
 
47
- #### [Tiny ML ModelZoo](https://github.com/TexasInstruments/tinyml-modelzoo)
48
- TI's central repo of AI models, examples & configs for MCU applications. Clone, install, and run an example config against your target device — training, quantization & compilation happen automatically. Browse example configs, supported devices & the training/compilation toolchain.
49
  - Ready-to-run examples, each with a dataset, tuned model & device-specific config; no separate toolchain clone needed
50
  - Time-series classification/regression/forecasting/anomaly detection, plus audio, image & radar point-cloud classification
51
  - Devices: AM13, MSPM0, C2000 (C28/C29 DSP), MSPM33C, AM26x, CC13xx/CC27xx/CC35xx connectivity, IWRL6432 radar — several with a TinyEngine NPU accelerator
52
- - Use cases: Motor & fault diagnostics · Predictive maintenance · Keyword spotting · Presence & fall detection · Grid & power monitoring · Gesture recognition and more.
53
- - In addition, [tinyml-tensorlab](https://github.com/TexasInstruments/tinyml-tensorlab) has Python packages, agent skills and tools for BYOD/BYOM workflows.
54
 
55
- #### [Edge AI Studio GUI](https://www.ti.com/tool/EDGE-AI-STUDIO)
56
- TI's graphical & command-line tools for MCU AI development, part of the CCStudio™ ecosystem — for AI-accelerated MCU devices (TinyEngine™ MCUs) and non-accelerated devices alike. Use or Download the IDE for MCU AI development.
57
  - Model Composer: no-code GUI for data collection, annotation, training & deployment
58
  - BYOD to retrain TI Model Zoo models, or BYOM via command-line tools built on the TVM compiler framework (TIDL for C7 NPU devices)
59
  - Cloud app for processors; cloud or desktop app for MCUs, connectivity devices & radar sensors; integrates with the CCStudio™ IDE
60
- </details>
61
 
62
  ---
63
 
 
11
 
12
  <img src="https://huggingface.co/spaces/TIEdgeAI/README/resolve/main/docs/assets/TXN-Logo.png" alt="Texas Instruments" width="80" height="80" />
13
 
 
14
  # Texas Instruments
15
 
 
16
  ### Semiconductor solutions for embedded and edge applications
17
 
18
  </div>
 
22
  [![Models](https://img.shields.io/badge/Models-50%2B-brightgreen)](https://huggingface.co/TexasInstruments-EdgeAI) [![Hardware](https://img.shields.io/badge/Hardware-TI%20MPUs%20With%20C7%20NPU-brightgreen)](https://huggingface.co/TexasInstruments-EdgeAI) [![License](https://img.shields.io/badge/License-Open%20Source-brightgreen)](https://huggingface.co/TexasInstruments-EdgeAI)
23
 
24
  Bring Your Own Models and deploy on Texas Instruments Micro Processors with C7 NPU acceleration
 
 
 
 
 
25
 
26
+ **[TI Edge-AI Model Hub →](https://huggingface.co/TexasInstruments-EdgeAI)** — pre-trained AI models for TI edge devices, with scripts & configs for compilation, benchmark and deployment.
27
  - Optimized, benchmarked on real hardware & portable across TI MPU devices; automated compile/benchmark/deploy scripts
28
  - Image classification (ResNet, ViT, ConvNeXt, DINO/DINOv2, MobileNetV3) & object detection (YOLO11/26/v8/X, RT-DETRv2, RTMDet, RF-DETR, DETR & more)
29
  - Validated on C7 NPU SOCs: AM62A, TDA4AEN/AM67A, TDA4VM, TDA4VE/TDA4VL/AM68A, TDA4VH/AM69A
30
+ - Use cases: Automotive · Aerospace & Defense · Industrial · Surveillance · Robotics · Edge IoT
 
31
 
32
  ---
33
 
 
35
  [![Devices](https://img.shields.io/badge/MCU%20Devices-MSP%20%7C%20AM13%20%7C%20C2000%20%7C%20Radar-brightgreen)](https://github.com/TexasInstruments/tinyml-modelzoo) [![GUI Tooling](https://img.shields.io/badge/GUI%20Tooling-Edge%20AI%20Studio-brightgreen)](https://www.ti.com/tool/EDGE-AI-STUDIO)
36
 
37
  Bring Your Own Data or Bring Your Own Models and deploy on TI microcontrollers, connectivity devices & radar sensors
 
38
 
39
+ **[Tiny ML ModelZoo →](https://github.com/TexasInstruments/tinyml-modelzoo)** — TI's central repo of AI models, examples & configs for MCU applications; training, quantization & compilation happen automatically on any example config. [tinyml-tensorlab](https://github.com/TexasInstruments/tinyml-tensorlab) adds Python packages, agent skills & tools for the same BYOD/BYOM workflows.
 
40
  - Ready-to-run examples, each with a dataset, tuned model & device-specific config; no separate toolchain clone needed
41
  - Time-series classification/regression/forecasting/anomaly detection, plus audio, image & radar point-cloud classification
42
  - Devices: AM13, MSPM0, C2000 (C28/C29 DSP), MSPM33C, AM26x, CC13xx/CC27xx/CC35xx connectivity, IWRL6432 radar — several with a TinyEngine NPU accelerator
43
+ - Use cases: Motor & fault diagnostics · Predictive maintenance · Keyword spotting · Presence & fall detection · Grid & power monitoring · Gesture recognition & more
 
44
 
45
+ **[Edge AI Studio GUI →](https://www.ti.com/tool/EDGE-AI-STUDIO)** — TI's graphical & command-line tools for MCU AI development, part of the CCStudio™ ecosystem, for both AI-accelerated (TinyEngine™) and non-accelerated MCU devices.
 
46
  - Model Composer: no-code GUI for data collection, annotation, training & deployment
47
  - BYOD to retrain TI Model Zoo models, or BYOM via command-line tools built on the TVM compiler framework (TIDL for C7 NPU devices)
48
  - Cloud app for processors; cloud or desktop app for MCUs, connectivity devices & radar sensors; integrates with the CCStudio™ IDE
 
49
 
50
  ---
51