Hugging Face's logo

qualcomm
/
Midas-V2

Depth Estimation
PyTorch
LiteRT
android
Model card Files
xet
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): 16.9 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 13.172 ms 0 - 43 MB NPU Midas-V2.tflite
Midas-V2 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 11.934 ms 1 - 30 MB NPU Midas-V2.dlc
Midas-V2 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 4.924 ms 0 - 62 MB NPU Midas-V2.tflite
Midas-V2 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 7.417 ms 0 - 38 MB NPU Midas-V2.dlc
Midas-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 3.301 ms 0 - 293 MB NPU Midas-V2.tflite
Midas-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.009 ms 1 - 19 MB NPU Midas-V2.dlc
Midas-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 3.08 ms 0 - 123 MB NPU Midas-V2.onnx.zip
Midas-V2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 4.645 ms 0 - 45 MB NPU Midas-V2.tflite
Midas-V2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 17.814 ms 1 - 30 MB NPU Midas-V2.dlc
Midas-V2 float SA7255P ADP Qualcomm® SA7255P TFLITE 13.172 ms 0 - 43 MB NPU Midas-V2.tflite
Midas-V2 float SA7255P ADP Qualcomm® SA7255P QNN_DLC 11.934 ms 1 - 30 MB NPU Midas-V2.dlc
Midas-V2 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 3.302 ms 0 - 301 MB NPU Midas-V2.tflite
Midas-V2 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.001 ms 0 - 11 MB NPU Midas-V2.dlc
Midas-V2 float SA8295P ADP Qualcomm® SA8295P TFLITE 5.817 ms 0 - 33 MB NPU Midas-V2.tflite
Midas-V2 float SA8295P ADP Qualcomm® SA8295P QNN_DLC 5.336 ms 1 - 32 MB NPU Midas-V2.dlc
Midas-V2 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 3.287 ms 0 - 321 MB NPU Midas-V2.tflite
Midas-V2 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.007 ms 1 - 14 MB NPU Midas-V2.dlc
Midas-V2 float SA8775P ADP Qualcomm® SA8775P TFLITE 4.645 ms 0 - 45 MB NPU Midas-V2.tflite
Midas-V2 float SA8775P ADP Qualcomm® SA8775P QNN_DLC 17.814 ms 1 - 30 MB NPU Midas-V2.dlc
Midas-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 2.327 ms 0 - 71 MB NPU Midas-V2.tflite
Midas-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.081 ms 1 - 38 MB NPU Midas-V2.dlc
Midas-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 2.107 ms 0 - 46 MB NPU Midas-V2.onnx.zip
Midas-V2 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 1.827 ms 0 - 51 MB NPU Midas-V2.tflite
Midas-V2 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.539 ms 1 - 37 MB NPU Midas-V2.dlc
Midas-V2 float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 1.684 ms 0 - 33 MB NPU Midas-V2.onnx.zip
Midas-V2 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1.442 ms 0 - 50 MB NPU Midas-V2.tflite
Midas-V2 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.319 ms 1 - 37 MB NPU Midas-V2.dlc
Midas-V2 float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 1.415 ms 0 - 31 MB NPU Midas-V2.onnx.zip
Midas-V2 float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 3.211 ms 194 - 194 MB NPU Midas-V2.dlc
Midas-V2 float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 2.907 ms 36 - 36 MB NPU Midas-V2.onnx.zip
Midas-V2 w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 2.583 ms 0 - 33 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 2.9 ms 0 - 34 MB NPU Midas-V2.dlc
Midas-V2 w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.413 ms 0 - 54 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 1.847 ms 0 - 50 MB NPU Midas-V2.dlc
Midas-V2 w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.07 ms 0 - 149 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 1.275 ms 0 - 134 MB NPU Midas-V2.dlc
Midas-V2 w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 5.209 ms 0 - 34 MB NPU Midas-V2.tflite
Midas-V2 w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 1.588 ms 0 - 34 MB NPU Midas-V2.dlc
Midas-V2 w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 3.817 ms 0 - 49 MB NPU Midas-V2.tflite
Midas-V2 w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 5.605 ms 0 - 50 MB NPU Midas-V2.dlc
Midas-V2 w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 16.156 ms 0 - 7 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 2.583 ms 0 - 33 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 2.9 ms 0 - 34 MB NPU Midas-V2.dlc
Midas-V2 w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.073 ms 0 - 146 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 1.283 ms 0 - 140 MB NPU Midas-V2.dlc
Midas-V2 w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 2.018 ms 0 - 38 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 2.19 ms 0 - 40 MB NPU Midas-V2.dlc
Midas-V2 w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.081 ms 0 - 147 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 1.28 ms 0 - 135 MB NPU Midas-V2.dlc
Midas-V2 w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 5.209 ms 0 - 34 MB NPU Midas-V2.tflite
Midas-V2 w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 1.588 ms 0 - 34 MB NPU Midas-V2.dlc
Midas-V2 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.772 ms 0 - 58 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.9 ms 0 - 61 MB NPU Midas-V2.dlc
Midas-V2 w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 0.597 ms 0 - 37 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 0.676 ms 0 - 40 MB NPU Midas-V2.dlc
Midas-V2 w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile TFLITE 1.464 ms 0 - 48 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 1.577 ms 0 - 52 MB NPU Midas-V2.dlc
Midas-V2 w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 0.524 ms 0 - 35 MB NPU Midas-V2.tflite
Midas-V2 w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 0.555 ms 0 - 42 MB NPU Midas-V2.dlc
Midas-V2 w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 1.446 ms 143 - 143 MB NPU Midas-V2.dlc

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[midas]"

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

Sign-in to Qualcomm® AI Hub Workbench 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

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 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.

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 Workbench. 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 --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.midas.demo -- --eval-mode 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
915
Inference Providers NEW
Depth Estimation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support