v0.63.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.
- README.md +24 -19
- release_assets.json +4 -4
README.md
CHANGED
|
@@ -14,7 +14,7 @@ pipeline_tag: other
|
|
| 14 |
|
| 15 |
StateTransformer is a transformer-based model designed for trajectory prediction in self-driving scenarios. It integrates rasterized map data, agent context, and temporal dynamics to generate accurate future trajectories.
|
| 16 |
|
| 17 |
-
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 18 |
|
| 19 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 20 |
|
|
@@ -27,22 +27,22 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| ONNX | float | Universal | QAIRT 2.
|
| 31 |
-
| TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.
|
| 32 |
|
| 33 |
For more device-specific assets and performance metrics, visit **[StateTransformer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/statetransformer)**.
|
| 34 |
|
| 35 |
|
| 36 |
### Option 2: Export with Custom Configurations
|
| 37 |
|
| 38 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 39 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 40 |
- Custom input shapes
|
| 41 |
- Target device and runtime configurations
|
| 42 |
|
| 43 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 44 |
|
| 45 |
-
See our repository for [StateTransformer on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 46 |
|
| 47 |
## Model Details
|
| 48 |
|
|
@@ -57,21 +57,26 @@ See our repository for [StateTransformer on GitHub](https://github.com/qualcomm/
|
|
| 57 |
## Performance Summary
|
| 58 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 59 |
|---|---|---|---|---|---|---
|
| 60 |
-
| StateTransformer | ONNX | float | Snapdragon® 8 Gen
|
| 61 |
-
| StateTransformer | ONNX | float |
|
| 62 |
-
| StateTransformer | ONNX | float |
|
| 63 |
-
| StateTransformer | ONNX | float |
|
| 64 |
-
| StateTransformer | ONNX | float |
|
| 65 |
-
| StateTransformer | ONNX | float |
|
| 66 |
-
| StateTransformer | ONNX | float |
|
| 67 |
-
| StateTransformer |
|
| 68 |
-
| StateTransformer |
|
| 69 |
-
| StateTransformer | TFLITE | float |
|
| 70 |
-
| StateTransformer | TFLITE | float |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
| StateTransformer | TFLITE | float | Qualcomm® QCS8450 | 808.833 ms | 450 - 470 MB | CPU
|
| 72 |
-
| StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 73 |
-
| StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 |
|
| 74 |
-
| StateTransformer | TFLITE | float |
|
| 75 |
|
| 76 |
## License
|
| 77 |
* The license for the original implementation of StateTransformer can be found
|
|
|
|
| 14 |
|
| 15 |
StateTransformer is a transformer-based model designed for trajectory prediction in self-driving scenarios. It integrates rasterized map data, agent context, and temporal dynamics to generate accurate future trajectories.
|
| 16 |
|
| 17 |
+
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/statetransformer) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 18 |
|
| 19 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 20 |
|
|
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
+
| ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.63.0/statetransformer-onnx-float.zip)
|
| 31 |
+
| TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.63.0/statetransformer-tflite-float.zip)
|
| 32 |
|
| 33 |
For more device-specific assets and performance metrics, visit **[StateTransformer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/statetransformer)**.
|
| 34 |
|
| 35 |
|
| 36 |
### Option 2: Export with Custom Configurations
|
| 37 |
|
| 38 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/statetransformer) Python library to compile and export the model with your own:
|
| 39 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 40 |
- Custom input shapes
|
| 41 |
- Target device and runtime configurations
|
| 42 |
|
| 43 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 44 |
|
| 45 |
+
See our repository for [StateTransformer on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/statetransformer) for usage instructions.
|
| 46 |
|
| 47 |
## Model Details
|
| 48 |
|
|
|
|
| 57 |
## Performance Summary
|
| 58 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 59 |
|---|---|---|---|---|---|---
|
| 60 |
+
| StateTransformer | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 192.571 ms | 173 - 4349 MB | NPU
|
| 61 |
+
| StateTransformer | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 210.813 ms | 177 - 4275 MB | NPU
|
| 62 |
+
| StateTransformer | ONNX | float | Snapdragon® X2 Elite | 177.638 ms | 279 - 279 MB | NPU
|
| 63 |
+
| StateTransformer | ONNX | float | Snapdragon® X Elite | 434.924 ms | 279 - 279 MB | NPU
|
| 64 |
+
| StateTransformer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 253.642 ms | 188 - 4421 MB | NPU
|
| 65 |
+
| StateTransformer | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 323.989 ms | 100 - 142 MB | NPU
|
| 66 |
+
| StateTransformer | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 279.812 ms | 105 - 146 MB | NPU
|
| 67 |
+
| StateTransformer | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 434.924 ms | 279 - 279 MB | NPU
|
| 68 |
+
| StateTransformer | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 210.813 ms | 177 - 4275 MB | NPU
|
| 69 |
+
| StateTransformer | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 661.397 ms | 292 - 3228 MB | CPU
|
| 70 |
+
| StateTransformer | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 898.831 ms | 292 - 4365 MB | CPU
|
| 71 |
+
| StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1520.712 ms | 294 - 813 MB | CPU
|
| 72 |
+
| StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1114.129 ms | 138 - 401 MB | CPU
|
| 73 |
+
| StateTransformer | TFLITE | float | Qualcomm® SA8775P | 1270.002 ms | 294 - 4058 MB | CPU
|
| 74 |
+
| StateTransformer | TFLITE | float | Qualcomm® SA8650P | 1270.002 ms | 294 - 4058 MB | CPU
|
| 75 |
+
| StateTransformer | TFLITE | float | Qualcomm® SA8255P | 1270.002 ms | 294 - 4058 MB | CPU
|
| 76 |
| StateTransformer | TFLITE | float | Qualcomm® QCS8450 | 808.833 ms | 450 - 470 MB | CPU
|
| 77 |
+
| StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1311.722 ms | 294 - 813 MB | CPU
|
| 78 |
+
| StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 661.397 ms | 292 - 3228 MB | CPU
|
| 79 |
+
| StateTransformer | TFLITE | float | Qualcomm® SA8295P | 954.001 ms | 290 - 3938 MB | CPU
|
| 80 |
|
| 81 |
## License
|
| 82 |
* The license for the original implementation of StateTransformer can be found
|
release_assets.json
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
-
"qairt": "2.
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.
|
| 12 |
},
|
| 13 |
"tflite": {
|
| 14 |
"tool_versions": {},
|
| 15 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.
|
| 16 |
}
|
| 17 |
}
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.63.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
+
"qairt": "2.50.0.260828221209",
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.63.0/statetransformer-onnx-float.zip"
|
| 12 |
},
|
| 13 |
"tflite": {
|
| 14 |
"tool_versions": {},
|
| 15 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.63.0/statetransformer-tflite-float.zip"
|
| 16 |
}
|
| 17 |
}
|
| 18 |
}
|