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 | 13.141 ms | 0 - 43 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.902 ms | 1 - 28 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.926 ms | 0 - 61 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.452 ms | 0 - 38 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.282 ms | 0 - 281 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.996 ms | 1 - 16 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 3.103 ms | 0 - 91 MB | NPU | Midas-V2.onnx.zip |
| Midas-V2 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 19.804 ms | 0 - 44 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.175 ms | 0 - 28 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 13.141 ms | 0 - 43 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 11.902 ms | 1 - 28 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 3.3 ms | 0 - 316 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.013 ms | 0 - 14 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 5.832 ms | 0 - 32 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 5.318 ms | 1 - 35 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 3.28 ms | 0 - 305 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.005 ms | 1 - 12 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 19.804 ms | 0 - 44 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.175 ms | 0 - 28 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.324 ms | 0 - 69 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.085 ms | 1 - 43 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.108 ms | 0 - 47 MB | NPU | Midas-V2.onnx.zip |
| Midas-V2 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.823 ms | 0 - 48 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.539 ms | 1 - 35 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.682 ms | 0 - 33 MB | NPU | Midas-V2.onnx.zip |
| Midas-V2 | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.438 ms | 0 - 48 MB | NPU | Midas-V2.tflite |
| Midas-V2 | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.289 ms | 0 - 34 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.42 ms | 0 - 31 MB | NPU | Midas-V2.onnx.zip |
| Midas-V2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.22 ms | 181 - 181 MB | NPU | Midas-V2.dlc |
| Midas-V2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.924 ms | 36 - 36 MB | NPU | Midas-V2.onnx.zip |
| Midas-V2 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 2.475 ms | 0 - 32 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 2.85 ms | 0 - 32 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.414 ms | 0 - 51 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 1.832 ms | 0 - 49 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.062 ms | 0 - 147 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.252 ms | 0 - 145 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.116 ms | 0 - 32 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.565 ms | 0 - 32 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 3.796 ms | 0 - 48 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 5.743 ms | 0 - 47 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 15.9 ms | 0 - 3 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 2.475 ms | 0 - 32 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 2.85 ms | 0 - 32 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1.065 ms | 0 - 147 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 1.24 ms | 0 - 136 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1.894 ms | 0 - 38 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 2.222 ms | 0 - 38 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1.132 ms | 0 - 148 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 1.249 ms | 0 - 136 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.116 ms | 0 - 32 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.565 ms | 0 - 32 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.755 ms | 0 - 62 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.918 ms | 0 - 61 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.59 ms | 0 - 40 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.671 ms | 0 - 38 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.519 ms | 0 - 34 MB | NPU | Midas-V2.tflite |
| Midas-V2 | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.559 ms | 0 - 36 MB | NPU | Midas-V2.dlc |
| Midas-V2 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.427 ms | 141 - 141 MB | NPU | Midas-V2.dlc |
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
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. 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 (
.tfliteexport): This tutorial provides a guide to deploy the .tflite model in an Android application.QNN (
.soexport ): This sample app provides instructions on how to use the.soshared 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
- Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
- Source Model Implementation
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
- Downloads last month
- 1,089