v0.31.0

See https://github.com/quic/ai-hub-models/releases/v0.31.0 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
+SalsaNext.dlc filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,231 @@
+---
+library_name: pytorch
+license: other
+tags:
+- android
+pipeline_tag: image-segmentation
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/salsanext/web-assets/model_demo.png)
+
+# SalsaNext: Optimized for Mobile Deployment
+## Semantic segmentation model optimized for LiDAR point cloud data
+
+SalsaNext is a LiDAR-based semantic segmentation model designed for efficient and accurate
+
+This repository provides scripts to run SalsaNext on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/salsanext).
+
+
+### Model Details
+
+- **Model Type:** Model_use_case.semantic_segmentation
+- **Model Stats:**
+  - Model checkpoint: SalsaNext
+  - Input resolution: 1x5x64x2048
+  - Model size: 108 MB
+
+| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| SalsaNext | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 148.718 ms | 64 - 93 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 115.246 ms | 0 - 40 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 65.38 ms | 64 - 106 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 56.086 ms | 3 - 61 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 47.762 ms | 64 - 89 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 31.235 ms | 3 - 16 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 58.582 ms | 64 - 93 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 36.864 ms | 0 - 41 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 48.477 ms | 64 - 89 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 31.188 ms | 3 - 19 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 32.053 ms | 20 - 65 MB | NPU | [SalsaNext.onnx](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.onnx) |
+| SalsaNext | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 36.615 ms | 63 - 104 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 23.162 ms | 3 - 46 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 23.744 ms | 24 - 77 MB | NPU | [SalsaNext.onnx](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.onnx) |
+| SalsaNext | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 33.594 ms | 64 - 98 MB | NPU | [SalsaNext.tflite](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.tflite) |
+| SalsaNext | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 17.52 ms | 3 - 47 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 18.546 ms | 25 - 71 MB | NPU | [SalsaNext.onnx](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.onnx) |
+| SalsaNext | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 31.316 ms | 40 - 40 MB | NPU | [SalsaNext.dlc](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.dlc) |
+| SalsaNext | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 32.14 ms | 35 - 35 MB | NPU | [SalsaNext.onnx](https://huggingface.co/qualcomm/SalsaNext/blob/main/SalsaNext.onnx) |
+
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+pip install qai-hub-models
+```
+
+
+## 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.salsanext.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.salsanext.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.salsanext.export
+```
+```
+Profiling Results
+------------------------------------------------------------
+SalsaNext
+Device                          : cs_8275 (ANDROID 14)                  
+Runtime                         : TFLITE                                
+Estimated inference time (ms)   : 148.7                                 
+Estimated peak memory usage (MB): [64, 93]                              
+Total # Ops                     : 249                                   
+Compute Unit(s)                 : npu (237 ops) gpu (0 ops) cpu (12 ops)
+```
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/salsanext/qai_hub_models/models/SalsaNext/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.salsanext import Model
+
+# Load the model
+torch_model = Model.from_pretrained()
+
+# Device
+device = hub.Device("Samsung Galaxy S24")
+
+# 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).
+
+
+
+
+## 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 SalsaNext's performance across various devices [here](https://aihub.qualcomm.com/models/salsanext).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of SalsaNext can be found
+  [here](https://github.com/TiagoCortinhal/SalsaNext/blob/master/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)
+
+
+
+
+## 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).
+
+

SalsaNext.dlc

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4955ad9883f6d8a11e9f29dd0b50089b431c597f5a0285fe75980bd71d45fd
+size 27054185

SalsaNext.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47342cc847c2d0a038975071ea9d484f46e1830aa6c2cadafdc0e2864ff86b5e
+size 26962206

SalsaNext.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22ef412c86ecab0b7cb1178aae5d814669d686e2b074ed64c346657ca4768a0
+size 26903628