Hugging Face's logo

qualcomm
/
Depth-Anything

Depth Estimation
PyTorch
LiteRT
android
Model card Files
xet
Community

Depth-Anything: Optimized for Mobile Deployment

Deep Convolutional Neural Network model for depth estimation

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

This model is an implementation of Depth-Anything found here.

This repository provides scripts to run Depth-Anything 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: DepthAnything_Small
    • Input resolution: 518x518
    • Number of parameters: 24.7M
    • Model size (float): 94.3 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Depth-Anything float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 197.822 ms 1 - 171 MB NPU Depth-Anything.tflite
Depth-Anything float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 179.234 ms 0 - 184 MB NPU Depth-Anything.dlc
Depth-Anything float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 118.308 ms 1 - 169 MB NPU Depth-Anything.tflite
Depth-Anything float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 123.689 ms 3 - 187 MB NPU Depth-Anything.dlc
Depth-Anything float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 85.673 ms 0 - 46 MB NPU Depth-Anything.tflite
Depth-Anything float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 76.435 ms 0 - 43 MB NPU Depth-Anything.dlc
Depth-Anything float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 76.398 ms 0 - 33 MB NPU Depth-Anything.onnx.zip
Depth-Anything float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 429.985 ms 1 - 171 MB NPU Depth-Anything.tflite
Depth-Anything float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 81.995 ms 3 - 187 MB NPU Depth-Anything.dlc
Depth-Anything float SA7255P ADP Qualcomm® SA7255P TFLITE 197.822 ms 1 - 171 MB NPU Depth-Anything.tflite
Depth-Anything float SA7255P ADP Qualcomm® SA7255P QNN_DLC 179.234 ms 0 - 184 MB NPU Depth-Anything.dlc
Depth-Anything float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 85.295 ms 1 - 38 MB NPU Depth-Anything.tflite
Depth-Anything float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 76.271 ms 3 - 46 MB NPU Depth-Anything.dlc
Depth-Anything float SA8295P ADP Qualcomm® SA8295P TFLITE 131.855 ms 0 - 165 MB NPU Depth-Anything.tflite
Depth-Anything float SA8295P ADP Qualcomm® SA8295P QNN_DLC 107.365 ms 2 - 192 MB NPU Depth-Anything.dlc
Depth-Anything float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 85.336 ms 1 - 38 MB NPU Depth-Anything.tflite
Depth-Anything float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 76.207 ms 3 - 51 MB NPU Depth-Anything.dlc
Depth-Anything float SA8775P ADP Qualcomm® SA8775P TFLITE 429.985 ms 1 - 171 MB NPU Depth-Anything.tflite
Depth-Anything float SA8775P ADP Qualcomm® SA8775P QNN_DLC 81.995 ms 3 - 187 MB NPU Depth-Anything.dlc
Depth-Anything float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 59.943 ms 1 - 173 MB NPU Depth-Anything.tflite
Depth-Anything float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 57.188 ms 3 - 191 MB NPU Depth-Anything.dlc
Depth-Anything float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 58.8 ms 0 - 387 MB NPU Depth-Anything.onnx.zip
Depth-Anything float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 46.868 ms 0 - 207 MB NPU Depth-Anything.tflite
Depth-Anything float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 40.006 ms 0 - 195 MB NPU Depth-Anything.dlc
Depth-Anything float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 43.694 ms 4 - 390 MB NPU Depth-Anything.onnx.zip
Depth-Anything float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 40.588 ms 0 - 180 MB NPU Depth-Anything.tflite
Depth-Anything float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 34.395 ms 3 - 241 MB NPU Depth-Anything.dlc
Depth-Anything float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 38.553 ms 4 - 376 MB NPU Depth-Anything.onnx.zip
Depth-Anything float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 76.914 ms 79 - 79 MB NPU Depth-Anything.dlc
Depth-Anything float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 75.139 ms 61 - 61 MB NPU Depth-Anything.onnx.zip

Installation

Install the package via pip:

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

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.depth_anything.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.depth_anything.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.depth_anything.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.depth_anything 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.depth_anything.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.depth_anything.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 Depth-Anything's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month
168
Inference Providers NEW
Depth Estimation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support