v0.48.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: object-detection
|
|
| 15 |
Deformable DETR is a machine learning model that can detect objects (trained on COCO dataset).
|
| 16 |
|
| 17 |
This is based on the implementation of DeformableDETR found [here](https://github.com/fundamentalvision/Deformable-DETR).
|
| 18 |
-
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/
|
| 19 |
|
| 20 |
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.
|
| 21 |
|
|
@@ -28,22 +28,22 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deformable_detr/releases/v0.
|
| 32 |
-
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deformable_detr/releases/v0.
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[DeformableDETR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/deformable_detr)**.
|
| 35 |
|
| 36 |
|
| 37 |
### Option 2: Export with Custom Configurations
|
| 38 |
|
| 39 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/
|
| 40 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 41 |
- Custom input shapes
|
| 42 |
- Target device and runtime configurations
|
| 43 |
|
| 44 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 45 |
|
| 46 |
-
See our repository for [DeformableDETR on GitHub](https://github.com/
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
@@ -58,6 +58,7 @@ See our repository for [DeformableDETR on GitHub](https://github.com/quic/ai-hub
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
|
|
|
| 61 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® X Elite | 2795.423 ms | 90 - 90 MB | NPU
|
| 62 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2355.274 ms | 67 - 2032 MB | NPU
|
| 63 |
| DeformableDETR | ONNX | w8a16 | Qualcomm® QCS6490 | 7549.381 ms | 1052 - 1059 MB | CPU
|
|
@@ -66,7 +67,6 @@ See our repository for [DeformableDETR on GitHub](https://github.com/quic/ai-hub
|
|
| 66 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1684.91 ms | 63 - 1330 MB | NPU
|
| 67 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3776.96 ms | 1044 - 1067 MB | CPU
|
| 68 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1412.598 ms | 65 - 1358 MB | NPU
|
| 69 |
-
| DeformableDETR | ONNX | w8a16 | Snapdragon® X2 Elite | 1632.94 ms | 93 - 93 MB | NPU
|
| 70 |
|
| 71 |
## License
|
| 72 |
* The license for the original implementation of DeformableDETR can be found
|
|
|
|
| 15 |
Deformable DETR is a machine learning model that can detect objects (trained on COCO dataset).
|
| 16 |
|
| 17 |
This is based on the implementation of DeformableDETR found [here](https://github.com/fundamentalvision/Deformable-DETR).
|
| 18 |
+
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/main/qai_hub_models/models/deformable_detr) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 19 |
|
| 20 |
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.
|
| 21 |
|
|
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
+
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deformable_detr/releases/v0.48.0/deformable_detr-onnx-float.zip)
|
| 32 |
+
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/deformable_detr/releases/v0.48.0/deformable_detr-onnx-w8a16.zip)
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[DeformableDETR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/deformable_detr)**.
|
| 35 |
|
| 36 |
|
| 37 |
### Option 2: Export with Custom Configurations
|
| 38 |
|
| 39 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/deformable_detr) Python library to compile and export the model with your own:
|
| 40 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 41 |
- Custom input shapes
|
| 42 |
- Target device and runtime configurations
|
| 43 |
|
| 44 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 45 |
|
| 46 |
+
See our repository for [DeformableDETR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/deformable_detr) for usage instructions.
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
| 61 |
+
| DeformableDETR | ONNX | w8a16 | Snapdragon® X2 Elite | 1632.94 ms | 93 - 93 MB | NPU
|
| 62 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® X Elite | 2795.423 ms | 90 - 90 MB | NPU
|
| 63 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2355.274 ms | 67 - 2032 MB | NPU
|
| 64 |
| DeformableDETR | ONNX | w8a16 | Qualcomm® QCS6490 | 7549.381 ms | 1052 - 1059 MB | CPU
|
|
|
|
| 67 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1684.91 ms | 63 - 1330 MB | NPU
|
| 68 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3776.96 ms | 1044 - 1067 MB | CPU
|
| 69 |
| DeformableDETR | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1412.598 ms | 65 - 1358 MB | NPU
|
|
|
|
| 70 |
|
| 71 |
## License
|
| 72 |
* The license for the original implementation of DeformableDETR can be found
|