Hugging Face's logo

qualcomm
/
Depth-Anything

Depth Estimation
PyTorch
LiteRT
ONNX
android
Model card Files 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: 24.8M
    • Model size: 94 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 274.389 ms 1 - 595 MB NPU Depth-Anything.tflite
Depth-Anything float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 244.903 ms 0 - 692 MB NPU Depth-Anything.dlc
Depth-Anything float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 182.266 ms 1 - 631 MB NPU Depth-Anything.tflite
Depth-Anything float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 256.92 ms 0 - 640 MB NPU Depth-Anything.dlc
Depth-Anything float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 148.282 ms 1 - 100 MB NPU Depth-Anything.tflite
Depth-Anything float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 130.472 ms 3 - 94 MB NPU Depth-Anything.dlc
Depth-Anything float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 143.621 ms 1 - 596 MB NPU Depth-Anything.tflite
Depth-Anything float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 129.008 ms 112 - 803 MB NPU Depth-Anything.dlc
Depth-Anything float SA7255P ADP Qualcomm® SA7255P TFLITE 274.389 ms 1 - 595 MB NPU Depth-Anything.tflite
Depth-Anything float SA7255P ADP Qualcomm® SA7255P QNN_DLC 244.903 ms 0 - 692 MB NPU Depth-Anything.dlc
Depth-Anything float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 148.353 ms 1 - 101 MB NPU Depth-Anything.tflite
Depth-Anything float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 124.745 ms 0 - 110 MB NPU Depth-Anything.dlc
Depth-Anything float SA8295P ADP Qualcomm® SA8295P TFLITE 182.609 ms 1 - 598 MB NPU Depth-Anything.tflite
Depth-Anything float SA8295P ADP Qualcomm® SA8295P QNN_DLC 161.2 ms 0 - 671 MB NPU Depth-Anything.dlc
Depth-Anything float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 149.658 ms 1 - 91 MB NPU Depth-Anything.tflite
Depth-Anything float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 124.827 ms 3 - 110 MB NPU Depth-Anything.dlc
Depth-Anything float SA8775P ADP Qualcomm® SA8775P TFLITE 143.621 ms 1 - 596 MB NPU Depth-Anything.tflite
Depth-Anything float SA8775P ADP Qualcomm® SA8775P QNN_DLC 129.008 ms 112 - 803 MB NPU Depth-Anything.dlc
Depth-Anything float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 150.557 ms 1 - 96 MB NPU Depth-Anything.tflite
Depth-Anything float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 131.476 ms 3 - 96 MB NPU Depth-Anything.dlc
Depth-Anything float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 146.633 ms 0 - 201 MB NPU Depth-Anything.onnx
Depth-Anything float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 110.455 ms 1 - 590 MB NPU Depth-Anything.tflite
Depth-Anything float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 97.854 ms 3 - 689 MB NPU Depth-Anything.dlc
Depth-Anything float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 107.682 ms 5 - 782 MB NPU Depth-Anything.onnx
Depth-Anything float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 86.949 ms 1 - 561 MB NPU Depth-Anything.tflite
Depth-Anything float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 86.776 ms 0 - 696 MB NPU Depth-Anything.dlc
Depth-Anything float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 89.475 ms 5 - 770 MB NPU Depth-Anything.onnx
Depth-Anything float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 138.955 ms 115 - 115 MB NPU Depth-Anything.dlc
Depth-Anything float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 140.742 ms 67 - 67 MB NPU Depth-Anything.onnx

Installation

Install the package via pip:

pip install "qai-hub-models[depth-anything]"

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.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

Profiling Results
------------------------------------------------------------
Depth-Anything
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 274.4                                
Estimated peak memory usage (MB): [1, 595]                             
Total # Ops                     : 646                                  
Compute Unit(s)                 : npu (646 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.depth_anything 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.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
71
Inference Providers NEW
Depth Estimation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support