v0.46.1

See https://github.com/quic/ai-hub-models/releases/v0.46.1 for changelog.

CVT_float.dlc

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:317f70afee9be85c3ebf66f3aced8da0d1587b661db71f8212a9ad668424e27d
-size 5724988

CVT_float.tflite

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8371b3b3b7e8edf24785d8ec8dddd1dc94672ecb9854ca8668296f157118dea3
-size 5431872

README.md

@@ -9,241 +9,91 @@ pipeline_tag: other
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/web-assets/model_demo.png)
 
-# CVT: Optimized for Mobile Deployment
-## Construct a map view from sensors mounted on a vehicle
-
+# CVT: Optimized for Qualcomm Devices
 
 Cross-View Transformer generates real-time bird's-eye view maps from multiple vehicle cameras for autonomous driving.
 
-This model is an implementation of CVT found [here](https://github.com/bradyz/cross_view_transformers).
-
-
-This repository provides scripts to run CVT on Qualcomm® devices.
-More details on model performance across various devices, can be found
-[here](https://aihub.qualcomm.com/models/cvt).
-
-
-
-### Model Details
-
-- **Model Type:** Model_use_case.driver_assistance
-- **Model Stats:**
-  - Model checkpoint: vehicles_50k.pt
-  - Inference latency: RealTime
-  - Input resolution: 1x6x3x224x480
-  - Number of parameters: 1.33M
-  - Model size (float): 5.18 MB
-
-| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
-|---|---|---|---|---|---|---|---|---|
-| CVT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 438.532 ms | 0 - 2052 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 428.856 ms | 0 - 2047 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 492.978 ms | 0 - 2582 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 483.659 ms | 7 - 2510 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 343.008 ms | 0 - 4 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 337.257 ms | 8 - 11 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 319.202 ms | 0 - 2051 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 311.571 ms | 2 - 2048 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 438.532 ms | 0 - 2052 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 428.856 ms | 0 - 2047 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 364.408 ms | 1 - 2156 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 362.017 ms | 0 - 2108 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 319.202 ms | 0 - 2051 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 311.571 ms | 2 - 2048 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 251.664 ms | 2 - 2426 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 197.937 ms | 0 - 2068 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 201.332 ms | 7 - 2001 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 182.132 ms | 0 - 2057 MB | NPU | [CVT.tflite](https://huggingface.co/qualcomm/CVT/blob/main/CVT.tflite) |
-| CVT | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 178.735 ms | 7 - 2095 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-| CVT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 290.792 ms | 7 - 7 MB | NPU | [CVT.dlc](https://huggingface.co/qualcomm/CVT/blob/main/CVT.dlc) |
-
-
-
-
-## 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[cvt]"
-```
-
-
-## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
-
-Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.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://workbench.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.cvt.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.cvt.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.cvt.export
-```
-
-
-
-## How does this work?
-
-This [export script](https://aihub.qualcomm.com/models/cvt/qai_hub_models/models/CVT/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.cvt 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 Workbench. [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.cvt.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.cvt.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 CVT's performance across various devices [here](https://aihub.qualcomm.com/models/cvt).
-Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
-
+This is based on the implementation of CVT found [here](https://github.com/bradyz/cross_view_transformers).
+This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/cvt) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
+
+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.
+
+## Getting Started
+There are two ways to deploy this model on your device:
+
+### Option 1: Download Pre-Exported Models
+
+Below are pre-exported model assets ready for deployment.
+
+| Runtime | Precision | Chipset | SDK Versions | Download |
+|---|---|---|---|---|
+| ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.46.1/cvt-onnx-float.zip)
+| QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.46.1/cvt-qnn_dlc-float.zip)
+| TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.46.1/cvt-tflite-float.zip)
+
+For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
+
+
+### Option 2: Export with Custom Configurations
+
+Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/cvt) Python library to compile and export the model with your own:
+- Custom weights (e.g., fine-tuned checkpoints)
+- Custom input shapes
+- Target device and runtime configurations
+
+This option is ideal if you need to customize the model beyond the default configuration provided here.
+
+See our repository for [CVT on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/cvt) for usage instructions.
+
+## Model Details
+
+**Model Type:** Model_use_case.driver_assistance
+
+**Model Stats:**
+- Model checkpoint: vehicles_50k.pt
+- Inference latency: RealTime
+- Input resolution: 1x6x3x224x480
+- Number of parameters: 1.33M
+- Model size (float): 5.18 MB
+
+## Performance Summary
+| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
+|---|---|---|---|---|---|---
+| CVT | ONNX | float | Snapdragon® X Elite | 337.851 ms | 20 - 20 MB | NPU
+| CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 307.125 ms | 8 - 2453 MB | NPU
+| CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 407.302 ms | 0 - 24 MB | NPU
+| CVT | ONNX | float | Qualcomm® QCS9075 | 331.746 ms | 7 - 10 MB | NPU
+| CVT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 259.644 ms | 4 - 2088 MB | NPU
+| CVT | QNN_DLC | float | Snapdragon® X Elite | 281.503 ms | 7 - 7 MB | NPU
+| CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 221.782 ms | 8 - 2556 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 423.067 ms | 0 - 2186 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 329.044 ms | 8 - 578 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® SA8775P | 292.094 ms | 0 - 2186 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® QCS9075 | 323.368 ms | 7 - 17 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 439.183 ms | 7 - 2650 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® SA7255P | 423.067 ms | 0 - 2186 MB | NPU
+| CVT | QNN_DLC | float | Qualcomm® SA8295P | 332.938 ms | 0 - 2240 MB | NPU
+| CVT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 184.599 ms | 7 - 2173 MB | NPU
+| CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 169.256 ms | 7 - 2259 MB | NPU
+| CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 224.811 ms | 0 - 2562 MB | NPU
+| CVT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 426.207 ms | 0 - 2193 MB | NPU
+| CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 339.717 ms | 0 - 4 MB | NPU
+| CVT | TFLITE | float | Qualcomm® SA8775P | 297.388 ms | 0 - 2193 MB | NPU
+| CVT | TFLITE | float | Qualcomm® QCS9075 | 325.057 ms | 0 - 35 MB | NPU
+| CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 451.485 ms | 0 - 2731 MB | NPU
+| CVT | TFLITE | float | Qualcomm® SA7255P | 426.207 ms | 0 - 2193 MB | NPU
+| CVT | TFLITE | float | Qualcomm® SA8295P | 342.185 ms | 0 - 2289 MB | NPU
+| CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 188.96 ms | 0 - 2243 MB | NPU
+| CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 172.317 ms | 0 - 2287 MB | NPU
 
 ## License
 * The license for the original implementation of CVT can be found
   [here](https://github.com/bradyz/cross_view_transformers/blob/master/LICENSE).
 
-
-
 ## References
 * [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://arxiv.org/abs/2205.02833)
 * [Source Model Implementation](https://github.com/bradyz/cross_view_transformers)
 
-
-
 ## 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

@@ -1,3 +0,0 @@
-tool_versions:
-  qnn_dlc:
-    qairt: 2.41.0.251128145156_191518