v0.41.2

See https://github.com/quic/ai-hub-models/releases/v0.41.2 for changelog.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text

BEVDet_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7063ce1194183e1ed5bf3b710ad9e09d7e34964a7bdd9055f5013e31b39845a2
+size 165995340

BEVDet_float.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28443665e46f84910baccdba85cbd880f163c3bae5ca9373187833434b8048c
+size 196507216

BEVDet_w8a16_mixed_fp16.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1488915bbbf38987bfc3249f02c6bdcae8a73bf8e639a8b187583b16ce69caa5
+size 80571058

DEPLOYMENT_MODEL_LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
+size 109629

LICENSE

@@ -0,0 +1,2 @@
+The license of the original trained model can be found at https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE.
+The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.

README.md

@@ -0,0 +1,251 @@
+---
+library_name: pytorch
+license: other
+tags:
+- android
+pipeline_tag: other
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevdet/web-assets/model_demo.png)
+
+# BEVDet: Optimized for Mobile Deployment
+## Construct a bird’s eye view from sensors mounted on a vehicle
+
+
+BEVDet is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.
+
+This model is an implementation of BEVDet found [here](https://github.com/HuangJunJie2017/BEVDet/).
+
+
+This repository provides scripts to run BEVDet on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/bevdet).
+
+
+
+### Model Details
+
+- **Model Type:** Model_use_case.driver_assistance
+- **Model Stats:**
+  - Model checkpoint: bevdet-r50.pth
+  - Input resolution: 1 x 6 x 3 x 256 x 704
+  - Number of parameters: 44M
+  - Model size: 171 MB
+
+| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| BEVDet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3066.089 ms | 129 - 141 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2366.717 ms | 129 - 150 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2046.52 ms | 128 - 132 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2513.257 ms | 298 - 301 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
+| BEVDet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2513.882 ms | 128 - 140 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3066.089 ms | 129 - 141 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 2016.379 ms | 127 - 130 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2018.721 ms | 129 - 144 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1889.096 ms | 126 - 129 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2513.882 ms | 128 - 140 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1757.655 ms | 123 - 147 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2041.163 ms | 296 - 316 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
+| BEVDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1297.116 ms | 93 - 107 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1541.601 ms | 266 - 281 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
+| BEVDet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1095.612 ms | 111 - 124 MB | CPU | [BEVDet.tflite](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.tflite) |
+| BEVDet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1532.157 ms | 284 - 295 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
+| BEVDet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 635.531 ms | 333 - 333 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet.onnx.zip) |
+| BEVDet | w8a16_mixed_fp16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2681.45 ms | 354 - 375 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
+| BEVDet | w8a16_mixed_fp16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2142.514 ms | 313 - 338 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
+| BEVDet | w8a16_mixed_fp16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1705.028 ms | 328 - 342 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
+| BEVDet | w8a16_mixed_fp16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1635.254 ms | 307 - 321 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
+| BEVDet | w8a16_mixed_fp16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 967.514 ms | 1122 - 1122 MB | CPU | [BEVDet.onnx.zip](https://huggingface.co/qualcomm/BEVDet/blob/main/BEVDet_w8a16_mixed_fp16.onnx.zip) |
+
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
+pip install nuscenes-devkit==1.2.0 --no-deps
+pip install "qai-hub-models[bevdet]"
+```
+
+
+## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
+
+Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
+Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
+
+With this API token, you can configure your client to run models on the cloud
+hosted devices.
+```bash
+qai-hub configure --api_token API_TOKEN
+```
+Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
+
+
+
+## Demo off target
+
+The package contains a simple end-to-end demo that downloads pre-trained
+weights and runs this model on a sample input.
+
+```bash
+python -m qai_hub_models.models.bevdet.demo
+```
+
+The above demo runs a reference implementation of pre-processing, model
+inference, and post processing.
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.bevdet.demo
+```
+
+
+### Run model on a cloud-hosted device
+
+In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
+device. This script does the following:
+* Performance check on-device on a cloud-hosted device
+* Downloads compiled assets that can be deployed on-device for Android.
+* Accuracy check between PyTorch and on-device outputs.
+
+```bash
+python -m qai_hub_models.models.bevdet.export
+```
+
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/bevdet/qai_hub_models/models/BEVDet/export.py)
+leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
+on-device. Lets go through each step below in detail:
+
+Step 1: **Compile model for on-device deployment**
+
+To compile a PyTorch model for on-device deployment, we first trace the model
+in memory using the `jit.trace` and then call the `submit_compile_job` API.
+
+```python
+import torch
+
+import qai_hub as hub
+from qai_hub_models.models.bevdet import Model
+
+# Load the model
+torch_model = Model.from_pretrained()
+
+# Device
+device = hub.Device("Samsung Galaxy S25")
+
+# Trace model
+input_shape = torch_model.get_input_spec()
+sample_inputs = torch_model.sample_inputs()
+
+pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+
+# Compile model on a specific device
+compile_job = hub.submit_compile_job(
+    model=pt_model,
+    device=device,
+    input_specs=torch_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+target_model = compile_job.get_target_model()
+
+```
+
+
+Step 2: **Performance profiling on cloud-hosted device**
+
+After compiling models from step 1. Models can be profiled model on-device using the
+`target_model`. Note that this scripts runs the model on a device automatically
+provisioned in the cloud.  Once the job is submitted, you can navigate to a
+provided job URL to view a variety of on-device performance metrics.
+```python
+profile_job = hub.submit_profile_job(
+    model=target_model,
+    device=device,
+)
+        
+```
+
+Step 3: **Verify on-device accuracy**
+
+To verify the accuracy of the model on-device, you can run on-device inference
+on sample input data on the same cloud hosted device.
+```python
+input_data = torch_model.sample_inputs()
+inference_job = hub.submit_inference_job(
+    model=target_model,
+    device=device,
+    inputs=input_data,
+)
+    on_device_output = inference_job.download_output_data()
+
+```
+With the output of the model, you can compute like PSNR, relative errors or
+spot check the output with expected output.
+
+**Note**: This on-device profiling and inference requires access to Qualcomm®
+AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
+
+
+
+## Run demo on a cloud-hosted device
+
+You can also run the demo on-device.
+
+```bash
+python -m qai_hub_models.models.bevdet.demo --eval-mode on-device
+```
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.bevdet.demo -- --eval-mode on-device
+```
+
+
+## Deploying compiled model to Android
+
+
+The models can be deployed using multiple runtimes:
+- TensorFlow Lite (`.tflite` export): [This
+  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
+  guide to deploy the .tflite model in an Android application.
+
+
+- QNN (`.so` export ): This [sample
+  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
+provides instructions on how to use the `.so` shared library  in an Android application.
+
+
+## View on Qualcomm® AI Hub
+Get more details on BEVDet's performance across various devices [here](https://aihub.qualcomm.com/models/bevdet).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of BEVDet can be found
+  [here](https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+
+
+
+## References
+* [BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View](https://arxiv.org/abs/2112.11790)
+* [Source Model Implementation](https://github.com/HuangJunJie2017/BEVDet/)
+
+
+
+## Community
+* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
+* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
+
+

tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  onnx:
+    onnx_runtime: 1.23.0