Hugging Face's logo

qualcomm
/
Depth-Anything-V2

Depth Estimation
PyTorch
LiteRT
ONNX
android
Model card Files Community
1

Depth-Anything-V2: 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-V2 found here.

This repository provides scripts to run Depth-Anything-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: DepthAnything_V2_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-V2 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 274.885 ms 1 - 584 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 913.948 ms 3 - 12 MB NPU Use Export Script
Depth-Anything-V2 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 183.217 ms 1 - 620 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 270.676 ms 0 - 663 MB NPU Use Export Script
Depth-Anything-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 145.46 ms 1 - 98 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 145.578 ms 3 - 6 MB NPU Use Export Script
Depth-Anything-V2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 142.11 ms 1 - 584 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 144.205 ms 2 - 14 MB NPU Use Export Script
Depth-Anything-V2 float SA7255P ADP Qualcomm® SA7255P TFLITE 274.885 ms 1 - 584 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float SA7255P ADP Qualcomm® SA7255P QNN 913.948 ms 3 - 12 MB NPU Use Export Script
Depth-Anything-V2 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 138.227 ms 0 - 99 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 146.082 ms 3 - 5 MB NPU Use Export Script
Depth-Anything-V2 float SA8295P ADP Qualcomm® SA8295P TFLITE 192.963 ms 1 - 589 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float SA8295P ADP Qualcomm® SA8295P QNN 180.754 ms 0 - 18 MB NPU Use Export Script
Depth-Anything-V2 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 145.48 ms 0 - 99 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 140.415 ms 3 - 5 MB NPU Use Export Script
Depth-Anything-V2 float SA8775P ADP Qualcomm® SA8775P TFLITE 142.11 ms 1 - 584 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float SA8775P ADP Qualcomm® SA8775P QNN 144.205 ms 2 - 14 MB NPU Use Export Script
Depth-Anything-V2 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 137.952 ms 1 - 99 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 139.271 ms 3 - 95 MB NPU Use Export Script
Depth-Anything-V2 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 149.007 ms 0 - 190 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 109.573 ms 1 - 576 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 110.686 ms 3 - 698 MB NPU Use Export Script
Depth-Anything-V2 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 112.949 ms 5 - 782 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 98.238 ms 1 - 550 MB NPU Depth-Anything-V2.tflite
Depth-Anything-V2 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 93.1 ms 3 - 773 MB NPU Use Export Script
Depth-Anything-V2 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 102.405 ms 2 - 847 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 float Snapdragon X Elite CRD Snapdragon® X Elite QNN 133.617 ms 3 - 3 MB NPU Use Export Script
Depth-Anything-V2 float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 149.271 ms 67 - 67 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 355.782 ms 100 - 317 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 302.989 ms 163 - 1150 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 342.568 ms 175 - 1175 MB NPU Depth-Anything-V2.onnx
Depth-Anything-V2 w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 483.272 ms 231 - 231 MB NPU Depth-Anything-V2.onnx

Installation

Install the package via pip:

pip install "qai-hub-models[depth-anything-v2]"

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_v2.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_v2.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_v2.export

Profiling Results
------------------------------------------------------------
Depth-Anything-V2
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 274.9                                
Estimated peak memory usage (MB): [1, 584]                             
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_v2 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_v2.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.depth_anything_v2.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 Depth-Anything-V2's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month
103
Inference Providers NEW
Depth Estimation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support