Hugging Face's logo

Spaces:
TexasInstruments
/
README
Running

App Files Community
nijil-ti commited on
Commit
f0fa7a0
·
verified ·
1 Parent(s): ef30e76

Update organization card

Browse files
Files changed (1) hide show
  1. README.md +38 -19
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: TexasInstruments
3
  emoji: 🤖
4
  colorFrom: red
5
  colorTo: gray
@@ -7,6 +7,8 @@ sdk: static
7
  pinned: false
8
  ---
9
 
 
 
10
  <div align="center">
11
 
12
  <img src="https://huggingface.co/spaces/TexasInstruments/README/resolve/main/docs/assets/TXN-Logo.png" alt="Texas Instruments" width="72" height="72" />
@@ -36,6 +38,8 @@ compilation options, runtimes, and supported operators, see the
36
  - ✅ Benchmarked on a variety of TI MPU devices with C7 NPU
37
  - ✅ Automated scripts for model compilation, benchmark & deployment
38
 
 
 
39
  ## Use Cases
40
 
41
  | | | |
@@ -43,6 +47,8 @@ compilation options, runtimes, and supported operators, see the
43
  | **Automotive** | **Aerospace & Defense** | **Industrial** |
44
  | **Surveillance** | **Robotics** | **Edge IoT** |
45
 
 
 
46
  ## License Summary
47
 
48
  Models in this hub are distributed under various open-source licenses — each model's license is indicated in its own documentation page.
@@ -54,6 +60,8 @@ Models in this hub are distributed under various open-source licenses — each m
54
  > regarding the suitability of these licenses for any particular purpose and accepts no legal
55
  > responsibility for the user's compliance obligations.
56
 
 
 
57
  ## Supported Hardware
58
 
59
  Compatible TI MPU device families compiled and validated via TIDL. See the supported devices, SDKs and version compatibility at the
@@ -68,6 +76,8 @@ Compatible TI MPU device families compiled and validated via TIDL. See the suppo
68
  | **J721S2** | [TDA4VE](https://www.ti.com/product/TDA4VE-Q1) · [TDA4VL](https://www.ti.com/product/TDA4VL-Q1) · [TDA4AL](https://www.ti.com/product/TDA4AL-Q1) · [AM68A](https://www.ti.com/product/AM68A) |
69
  | **J784S4** | [TDA4VH](https://www.ti.com/product/TDA4VH-Q1) · [TDA4AH](https://www.ti.com/product/TDA4AH-Q1) · [AM69A](https://www.ti.com/product/AM69A) |
70
 
 
 
71
  ## Compilation & Deployment
72
 
73
  | Tool | Description |
@@ -75,6 +85,8 @@ Compatible TI MPU device families compiled and validated via TIDL. See the suppo
75
  | **[edgeai-tidlrunner](https://github.com/TexasInstruments/edgeai-tidlrunner)** | High-level compilation and benchmark interface. (Recommended for compilation and benchmark) |
76
  | **[edgeai-tidl-tools](https://github.com/TexasInstruments/edgeai-tidl-tools)** | Deployment tools (and also low-level compilation tools for advanced users). |
77
 
 
 
78
  ## Quick Start
79
 
80
  **1. Clone the repository**
@@ -103,29 +115,36 @@ tidlrunner-cli infer --target_device <device> \
103
  --config_path /path/to/edgeai-modelhub/<model>_config.yaml
104
  ```
105
 
 
 
106
  ## Deployment
 
107
  Deplyment can be done using **[edgeai-tidl-tools](https://github.com/TexasInstruments/edgeai-tidl-tools)**. For ONNX models, onnxruntime-tidl with TIDL acceleration can be used. Consult the documentation of edgeai-tidl-tools for more details.
108
 
 
 
109
  ## Model Catalog
110
 
111
- | Model | Capability | Variants | Input | Reference Performance | License | Docs |
112
  |---|---|---|---|---|---|---|
113
- | **MobileNetV3** | Image Classification | large | 224×224 | 75.3% Top-1 | [![BSD-3-Clause](https://img.shields.io/badge/BSD--3--Clause-065f46?style=flat-square)](https://opensource.org/licenses/BSD-3-Clause) | [View](models/vision/classification/MobileNetV3/) |
114
- | **ResNet-50** | Image Classification | v1.5, v1 | 224×224 | 74.93–76.15% Top-1 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/classification/ResNet/) |
115
- | **DINO** | Image Classification | ViT-S/16, ViT-S/8, ViT-B/16, ViT-B/8, ResNet-50 | 224×224 | 75.3–80.1% Top-1 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/classification/DINO/) |
116
- | **DINOv2** | Image Classification | ViT-S/14, ViT-B/14 (w/ & w/o registers) | 224×224 | 80.9–84.6% Top-1 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/classification/DINOv2/) |
117
- | **ViT** | Image Classification | vit_b_16, vit_b_32, vit_l_16, vit_l_32 | 224×224 | 75.9–81.1% Top-1 | [![BSD-3-Clause](https://img.shields.io/badge/BSD--3--Clause-065f46?style=flat-square)](https://opensource.org/licenses/BSD-3-Clause) | [View](models/vision/classification/ViT/) |
118
- | **ConvNeXt** | Image Classification | convnext_tiny, convnext_small, convnext_base, convnext_large | 224×224 | 82.5–84.4% Top-1 | [![BSD-3-Clause](https://img.shields.io/badge/BSD--3--Clause-065f46?style=flat-square)](https://opensource.org/licenses/BSD-3-Clause) | [View](models/vision/classification/ConvNeXt/) |
119
- | **DEIMv2** | Object Detection | s, m | 640×640 | 50.9–53.0% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/DEIMv2/) |
120
- | **DETR** | Object Detection | detr_resnet50, detr_resnet50_dc5, detr_resnet101, detr_resnet101_dc5 | 800×800 (flexible) | AP50:95 42.0–44.9, AP50 62.4–64.7 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/DETR/) |
121
- | **Deformable-DETR** | Object Detection | single-scale | 800×800 | AP50:95 39.4% | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/Deformable-DETR/) |
122
- | **RF-DETR** | Object Detection | nano, s, m, l | 384–704px | 48.4–56.5% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/RF-DETR/) |
123
- | **RT-DETRv2** | Object Detection | s, ms, m, l, x | 640×640 | 48.1–54.3% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/RT-DETRv2/) |
124
- | **RTMDet** | Object Detection | tiny, s, m, l, x | 640×640 | 40.9–52.8% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/RTMDet/) |
125
- | **YOLO11** | Object Detection | n, s, m, l, x | 640×640 | 39.5–54.7% mAP | [![AGPL 3.0](https://img.shields.io/badge/AGPL%203.0-9d174d?style=flat-square)](https://www.gnu.org/licenses/agpl-3.0.html) | [View](models/vision/detection/YOLO11/) |
126
- | **YOLO26** | Object Detection | n, s, m, l, x | 640×640 | 40.9–57.5% mAP | [![AGPL 3.0](https://img.shields.io/badge/AGPL%203.0-9d174d?style=flat-square)](https://www.gnu.org/licenses/agpl-3.0.html) | [View](models/vision/detection/YOLO26/) |
127
- | **YOLOv8** | Object Detection | n, m | 640×640 | 37.3–50.2% mAP | [![AGPL 3.0](https://img.shields.io/badge/AGPL%203.0-9d174d?style=flat-square)](https://www.gnu.org/licenses/agpl-3.0.html) | [View](models/vision/detection/YOLOv8/) |
128
- | **YOLOX** | Object Detection | nano, tiny, m, l, x, darknet53 | 416×416 / 640×640 | 24.8–51.2% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](models/vision/detection/YOLOX/) |
 
 
129
 
130
  ## Resources & Links
131
 
@@ -137,7 +156,7 @@ Deplyment can be done using **[edgeai-tidl-tools](https://github.com/TexasInstru
137
 
138
  <div align="center">
139
 
140
- Maintained by Texas Instruments EdgeAI Team &nbsp;|&nbsp; Last Updated August 2026
141
 
142
  [Contact](mailto:edgeai-dev@list.ti.com)
143
 
 
1
  ---
2
+ title: TIEdgeAI
3
  emoji: 🤖
4
  colorFrom: red
5
  colorTo: gray
 
7
  pinned: false
8
  ---
9
 
10
+ <!-- AUTO-GENERATED by packaging/generate_org_card.py from README.md — do not edit by hand. Edit README.md and re-run the generator instead. -->
11
+
12
  <div align="center">
13
 
14
  <img src="https://huggingface.co/spaces/TexasInstruments/README/resolve/main/docs/assets/TXN-Logo.png" alt="Texas Instruments" width="72" height="72" />
 
38
  - ✅ Benchmarked on a variety of TI MPU devices with C7 NPU
39
  - ✅ Automated scripts for model compilation, benchmark & deployment
40
 
41
+ ---
42
+
43
  ## Use Cases
44
 
45
  | | | |
 
47
  | **Automotive** | **Aerospace & Defense** | **Industrial** |
48
  | **Surveillance** | **Robotics** | **Edge IoT** |
49
 
50
+ ---
51
+
52
  ## License Summary
53
 
54
  Models in this hub are distributed under various open-source licenses — each model's license is indicated in its own documentation page.
 
60
  > regarding the suitability of these licenses for any particular purpose and accepts no legal
61
  > responsibility for the user's compliance obligations.
62
 
63
+ ---
64
+
65
  ## Supported Hardware
66
 
67
  Compatible TI MPU device families compiled and validated via TIDL. See the supported devices, SDKs and version compatibility at the
 
76
  | **J721S2** | [TDA4VE](https://www.ti.com/product/TDA4VE-Q1) · [TDA4VL](https://www.ti.com/product/TDA4VL-Q1) · [TDA4AL](https://www.ti.com/product/TDA4AL-Q1) · [AM68A](https://www.ti.com/product/AM68A) |
77
  | **J784S4** | [TDA4VH](https://www.ti.com/product/TDA4VH-Q1) · [TDA4AH](https://www.ti.com/product/TDA4AH-Q1) · [AM69A](https://www.ti.com/product/AM69A) |
78
 
79
+ ---
80
+
81
  ## Compilation & Deployment
82
 
83
  | Tool | Description |
 
85
  | **[edgeai-tidlrunner](https://github.com/TexasInstruments/edgeai-tidlrunner)** | High-level compilation and benchmark interface. (Recommended for compilation and benchmark) |
86
  | **[edgeai-tidl-tools](https://github.com/TexasInstruments/edgeai-tidl-tools)** | Deployment tools (and also low-level compilation tools for advanced users). |
87
 
88
+ ---
89
+
90
  ## Quick Start
91
 
92
  **1. Clone the repository**
 
115
  --config_path /path/to/edgeai-modelhub/<model>_config.yaml
116
  ```
117
 
118
+ ---
119
+
120
  ## Deployment
121
+
122
  Deplyment can be done using **[edgeai-tidl-tools](https://github.com/TexasInstruments/edgeai-tidl-tools)**. For ONNX models, onnxruntime-tidl with TIDL acceleration can be used. Consult the documentation of edgeai-tidl-tools for more details.
123
 
124
+ ---
125
+
126
  ## Model Catalog
127
 
128
+ | Model | Capability | Variants | Input | Reference Performance | License | Repo |
129
  |---|---|---|---|---|---|---|
130
+ | **MobileNetV3** | Image Classification | large | 224×224 | 75.3% Top-1 | [![BSD-3-Clause](https://img.shields.io/badge/BSD--3--Clause-065f46?style=flat-square)](https://opensource.org/licenses/BSD-3-Clause) | [View](https://huggingface.co/TexasInstruments/MobileNetV3-Classification) |
131
+ | **ResNet-50** | Image Classification | v1.5, v1 | 224×224 | 74.93–76.15% Top-1 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/ResNet-Classification) |
132
+ | **DINO** | Image Classification | ViT-S/16, ViT-S/8, ViT-B/16, ViT-B/8, ResNet-50 | 224×224 | 75.3–80.1% Top-1 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/DINO-Classification) |
133
+ | **DINOv2** | Image Classification | ViT-S/14, ViT-B/14 (w/ & w/o registers) | 224×224 | 80.9–84.6% Top-1 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/DINOv2-Classification) |
134
+ | **ViT** | Image Classification | vit_b_16, vit_b_32, vit_l_16, vit_l_32 | 224×224 | 75.9–81.1% Top-1 | [![BSD-3-Clause](https://img.shields.io/badge/BSD--3--Clause-065f46?style=flat-square)](https://opensource.org/licenses/BSD-3-Clause) | [View](https://huggingface.co/TexasInstruments/ViT-Classification) |
135
+ | **ConvNeXt** | Image Classification | convnext_tiny, convnext_small, convnext_base, convnext_large | 224×224 | 82.5–84.4% Top-1 | [![BSD-3-Clause](https://img.shields.io/badge/BSD--3--Clause-065f46?style=flat-square)](https://opensource.org/licenses/BSD-3-Clause) | [View](https://huggingface.co/TexasInstruments/ConvNeXt-Classification) |
136
+ | **DEIMv2** | Object Detection | s, m | 640×640 | 50.9–53.0% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/DEIMv2-Detection) |
137
+ | **DETR** | Object Detection | detr_resnet50, detr_resnet50_dc5, detr_resnet101, detr_resnet101_dc5 | 800×800 (flexible) | AP50:95 42.0–44.9, AP50 62.4–64.7 | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/DETR-Detection) |
138
+ | **Deformable-DETR** | Object Detection | single-scale | 800×800 | AP50:95 39.4% | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/Deformable-DETR-Detection) |
139
+ | **RF-DETR** | Object Detection | nano, s, m, l | 384–704px | 48.4–56.5% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/RF-DETR-Detection) |
140
+ | **RT-DETRv2** | Object Detection | s, ms, m, l, x | 640×640 | 48.1–54.3% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/RT-DETRv2-Detection) |
141
+ | **RTMDet** | Object Detection | tiny, s, m, l, x | 640×640 | 40.9–52.8% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/RTMDet-Detection) |
142
+ | **YOLO11** | Object Detection | n, s, m, l, x | 640×640 | 39.5–54.7% mAP | [![AGPL 3.0](https://img.shields.io/badge/AGPL%203.0-9d174d?style=flat-square)](https://www.gnu.org/licenses/agpl-3.0.html) | [View](https://huggingface.co/TexasInstruments/YOLO11-Detection) |
143
+ | **YOLO26** | Object Detection | n, s, m, l, x | 640×640 | 40.9–57.5% mAP | [![AGPL 3.0](https://img.shields.io/badge/AGPL%203.0-9d174d?style=flat-square)](https://www.gnu.org/licenses/agpl-3.0.html) | [View](https://huggingface.co/TexasInstruments/YOLO26-Detection) |
144
+ | **YOLOv8** | Object Detection | n, m | 640×640 | 37.3–50.2% mAP | [![AGPL 3.0](https://img.shields.io/badge/AGPL%203.0-9d174d?style=flat-square)](https://www.gnu.org/licenses/agpl-3.0.html) | [View](https://huggingface.co/TexasInstruments/YOLOv8-Detection) |
145
+ | **YOLOX** | Object Detection | nano, tiny, m, l, x, darknet53 | 416×416 / 640×640 | 24.8–51.2% mAP | [![Apache 2.0](https://img.shields.io/badge/Apache%202.0-1d4ed8?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0) | [View](https://huggingface.co/TexasInstruments/YOLOX-Detection) |
146
+
147
+ ---
148
 
149
  ## Resources & Links
150
 
 
156
 
157
  <div align="center">
158
 
159
+ **Maintained by Texas Instruments EdgeAI Team &nbsp;|&nbsp; Last Updated August 2026**
160
 
161
  [Contact](mailto:edgeai-dev@list.ti.com)
162