Hugging Face's logo

qualcomm
/
Midas-V2

Depth Estimation
PyTorch
LiteRT
ONNX
android
Model card Files Community

Midas-V2: Optimized for Mobile Deployment

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 found here.

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

Model Details

  • Model Type: Model_use_case.depth_estimation
  • Model Stats:
    • Model checkpoint: MiDaS_small
    • Input resolution: 256x256
    • Number of parameters: 16.6M
    • Model size (float): 63.2 MB
    • Model size (w8a8): 16.6 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Midas-V2 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 12.862 ms 0 - 39 MB NPU Midas-V2.tflite
Midas-V2 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 12.36 ms 1 - 11 MB NPU Use Export Script
Midas-V2 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 4.982 ms 0 - 50 MB NPU Midas-V2.tflite
Midas-V2 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 7.353 ms 0 - 35 MB NPU Use Export Script
Midas-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 3.239 ms 0 - 255 MB NPU Midas-V2.tflite
Midas-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 3.009 ms 1 - 3 MB NPU Use Export Script
Midas-V2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 4.546 ms 0 - 41 MB NPU Midas-V2.tflite
Midas-V2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 4.235 ms 0 - 14 MB NPU Use Export Script
Midas-V2 float SA7255P ADP Qualcomm® SA7255P TFLITE 12.862 ms 0 - 39 MB NPU Midas-V2.tflite
Midas-V2 float SA7255P ADP Qualcomm® SA7255P QNN 12.36 ms 1 - 11 MB NPU Use Export Script
Midas-V2 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 3.23 ms 0 - 253 MB NPU Midas-V2.tflite
Midas-V2 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 3.014 ms 0 - 2 MB NPU Use Export Script
Midas-V2 float SA8295P ADP Qualcomm® SA8295P TFLITE 5.754 ms 0 - 25 MB NPU Midas-V2.tflite
Midas-V2 float SA8295P ADP Qualcomm® SA8295P QNN 5.421 ms 1 - 18 MB NPU Use Export Script
Midas-V2 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 3.233 ms 0 - 274 MB NPU Midas-V2.tflite
Midas-V2 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 3.011 ms 1 - 3 MB NPU Use Export Script
Midas-V2 float SA8775P ADP Qualcomm® SA8775P TFLITE 4.546 ms 0 - 41 MB NPU Midas-V2.tflite
Midas-V2 float SA8775P ADP Qualcomm® SA8775P QNN 4.235 ms 0 - 14 MB NPU Use Export Script
Midas-V2 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 3.243 ms 0 - 261 MB NPU Midas-V2.tflite
Midas-V2 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 3.034 ms 0 - 14 MB NPU Use Export Script
Midas-V2 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 2.98 ms 0 - 73 MB NPU Midas-V2.onnx
Midas-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 2.293 ms 0 - 65 MB NPU Midas-V2.tflite
Midas-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 2.188 ms 1 - 37 MB NPU Use Export Script
Midas-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 2.059 ms 0 - 47 MB NPU Midas-V2.onnx
Midas-V2 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 1.792 ms 0 - 43 MB NPU Midas-V2.tflite
Midas-V2 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 1.91 ms 1 - 29 MB NPU Use Export Script
Midas-V2 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 1.948 ms 1 - 32 MB NPU Midas-V2.onnx
Midas-V2 float Snapdragon X Elite CRD Snapdragon® X Elite QNN 3.213 ms 1 - 1 MB NPU Use Export Script
Midas-V2 float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 3.065 ms 35 - 35 MB NPU Midas-V2.onnx
Midas-V2 w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 2.464 ms 0 - 27 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 2.831 ms 0 - 10 MB NPU Use Export Script
Midas-V2 w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.574 ms 0 - 47 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 1.986 ms 0 - 45 MB NPU Use Export Script
Midas-V2 w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.064 ms 0 - 134 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 1.293 ms 0 - 4 MB NPU Use Export Script
Midas-V2 w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.353 ms 0 - 30 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 1.574 ms 0 - 15 MB NPU Use Export Script
Midas-V2 w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 3.612 ms 0 - 45 MB NPU Midas-V2.tflite
Midas-V2 w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 5.705 ms 0 - 14 MB NPU Use Export Script
Midas-V2 w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 16.032 ms 0 - 3 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 2.464 ms 0 - 27 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA7255P ADP Qualcomm® SA7255P QNN 2.831 ms 0 - 10 MB NPU Use Export Script
Midas-V2 w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.062 ms 0 - 132 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 1.289 ms 0 - 2 MB NPU Use Export Script
Midas-V2 w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 1.891 ms 0 - 31 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8295P ADP Qualcomm® SA8295P QNN 2.156 ms 0 - 16 MB NPU Use Export Script
Midas-V2 w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.057 ms 0 - 133 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 1.289 ms 0 - 2 MB NPU Use Export Script
Midas-V2 w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 1.353 ms 0 - 30 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8775P ADP Qualcomm® SA8775P QNN 1.574 ms 0 - 15 MB NPU Use Export Script
Midas-V2 w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 1.072 ms 0 - 132 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 1.292 ms 0 - 122 MB NPU Use Export Script
Midas-V2 w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 115.256 ms 12 - 119 MB NPU Midas-V2.onnx
Midas-V2 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.762 ms 0 - 57 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.903 ms 0 - 54 MB NPU Use Export Script
Midas-V2 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 93.772 ms 24 - 356 MB NPU Midas-V2.onnx
Midas-V2 w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.675 ms 0 - 30 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.682 ms 0 - 32 MB NPU Use Export Script
Midas-V2 w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 98.215 ms 28 - 355 MB NPU Midas-V2.onnx
Midas-V2 w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 1.419 ms 0 - 0 MB NPU Use Export Script
Midas-V2 w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 123.184 ms 65 - 65 MB NPU Midas-V2.onnx

Installation

Install the package via pip:

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

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.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.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.export

Profiling Results
------------------------------------------------------------
Midas-V2
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 12.9                                 
Estimated peak memory usage (MB): [0, 39]                              
Total # Ops                     : 138                                  
Compute Unit(s)                 : npu (138 ops) gpu (0 ops) cpu (0 ops)

How does this work?

This export script leverages Qualcomm® AI Hub 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.

import torch

import qai_hub as hub
from qai_hub_models.models.midas 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.

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.

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.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.midas.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.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's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Depth Estimation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support