Hugging Face's logo

qualcomm
/
Midas-V2-Quantized

Depth Estimation
PyTorch
LiteRT
ONNX
quantized
android
Model card Files Community
Midas-V2-Quantized / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
8a8a3de verified
preview code
|
raw
history blame
10.2 kB
metadata
library_name: pytorch
license: mit
pipeline_tag: depth-estimation
tags:
  - quantized
  - android

Midas-V2-Quantized: Optimized for Mobile Deployment

Quantized Deep Convolutional Neural Network model for depth estimation

Midas is designed for estimating depth at each point in an image.

This model is an implementation of Midas-V2-Quantized found here.

This repository provides scripts to run Midas-V2-Quantized on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Depth estimation
  • Model Stats:
    • Model checkpoint: MiDaS_small
    • Input resolution: 256x256
    • Number of parameters: 16.6M
    • Model size: 16.6 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
Midas-V2-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 1.1 ms 0 - 59 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 1.439 ms 0 - 64 MB INT8 NPU Midas-V2-Quantized.so
Midas-V2-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 9.224 ms 0 - 82 MB INT8 NPU Midas-V2-Quantized.onnx
Midas-V2-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 0.767 ms 0 - 38 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 1.014 ms 0 - 29 MB INT8 NPU Midas-V2-Quantized.so
Midas-V2-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 7.176 ms 2 - 143 MB INT8 NPU Midas-V2-Quantized.onnx
Midas-V2-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 0.713 ms 0 - 26 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 1.003 ms 0 - 26 MB INT8 NPU Use Export Script
Midas-V2-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 7.906 ms 0 - 127 MB INT8 NPU Midas-V2-Quantized.onnx
Midas-V2-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 3.849 ms 0 - 27 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy QNN 5.812 ms 0 - 11 MB INT8 NPU Use Export Script
Midas-V2-Quantized RB5 (Proxy) QCS8250 Proxy TFLITE 15.87 ms 0 - 2 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized QCS8550 (Proxy) QCS8550 Proxy TFLITE 1.099 ms 0 - 59 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 1.335 ms 0 - 3 MB INT8 NPU Use Export Script
Midas-V2-Quantized SA7255P ADP SA7255P TFLITE 11.071 ms 0 - 22 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized SA7255P ADP SA7255P QNN 12.293 ms 0 - 10 MB INT8 NPU Use Export Script
Midas-V2-Quantized SA8255 (Proxy) SA8255P Proxy TFLITE 1.097 ms 0 - 49 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized SA8255 (Proxy) SA8255P Proxy QNN 1.323 ms 0 - 2 MB INT8 NPU Use Export Script
Midas-V2-Quantized SA8295P ADP SA8295P TFLITE 1.939 ms 0 - 29 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized SA8295P ADP SA8295P QNN 2.489 ms 0 - 14 MB INT8 NPU Use Export Script
Midas-V2-Quantized SA8650 (Proxy) SA8650P Proxy TFLITE 1.098 ms 0 - 59 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized SA8650 (Proxy) SA8650P Proxy QNN 1.326 ms 0 - 2 MB INT8 NPU Use Export Script
Midas-V2-Quantized SA8775P ADP SA8775P TFLITE 1.615 ms 0 - 22 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized SA8775P ADP SA8775P QNN 2.095 ms 0 - 10 MB INT8 NPU Use Export Script
Midas-V2-Quantized QCS8450 (Proxy) QCS8450 Proxy TFLITE 1.429 ms 0 - 26 MB INT8 NPU Midas-V2-Quantized.tflite
Midas-V2-Quantized QCS8450 (Proxy) QCS8450 Proxy QNN 1.801 ms 0 - 28 MB INT8 NPU Use Export Script
Midas-V2-Quantized Snapdragon X Elite CRD Snapdragon® X Elite QNN 1.471 ms 0 - 0 MB INT8 NPU Use Export Script
Midas-V2-Quantized Snapdragon X Elite CRD Snapdragon® X Elite ONNX 8.846 ms 23 - 23 MB INT8 NPU Midas-V2-Quantized.onnx

Installation

This model can be installed as a Python package via pip.

pip install "qai-hub-models[midas_quantized]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub 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.

qai-hub configure --api_token API_TOKEN

Navigate to 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.

python -m qai_hub_models.models.midas_quantized.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.midas_quantized.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.
python -m qai_hub_models.models.midas_quantized.export

Profiling Results
------------------------------------------------------------
Midas-V2-Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 1.1                    
Estimated peak memory usage (MB): [0, 59]                
Total # Ops                     : 145                    
Compute Unit(s)                 : NPU (145 ops)

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.midas_quantized.demo --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.midas_quantized.demo -- --on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on Midas-V2-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of Midas-V2-Quantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community