ESRGAN | Luxonis

Our new model ZOO works with DepthAI V3. Find out more in our documentation.

0 Likes

Model Details

Model Description

ESRGAN: Enhanced Super-Resolution Generative Adversarial Network enhances the resolution of low-quality images by generating high-quality, detailed versions through a combination of generative adversarial networks (GANs) and a perceptual loss function.

Developed by: Xintao et al.
Shared by:
Model type: Computer vision
License:
Resources for more information:

Training Details

Training Data

The model was trained on and datasets. The first one contains 800 images and the second one 2650 images.

For more information about training data check the .

Testing Details

Metrics

There are qualitative results described in the . Please check it out.

Technical Specifications

Input/Output Details

Input:
- Name: input
  - Info: NCHW BGR 0-255 image.
Output:
- Name: output
  - Info: Upscaled enhanced image.

Model Architecture

ESRGAN is composed of Residual-in-Residual Dense Block (RRDB), Generator Network, Discriminator Network, and Perceptual Loss.

Please consult the for more information on model architecture.

Throughput

Model variant: esrgan:256x256

• Input shape: [1, 3, 256, 256] • Output shape: [1, 3, 1024, 1024]

• Params (M): 4.468 • GFLOPs: 375.175

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC4	INT8	24.57	8.49

* Benchmarked with , using 2 threads (and the DSP runtime in balanced mode for RVC4).

* Parameters and FLOPs are obtained from the package.

Quantization

RVC4 version of the model was quantized using a HubAI General dataset.

Utilization

Models converted for RVC Platforms can be used for inference on OAK devices. DepthAI pipelines are used to define the information flow linking the device, inference model, and the output parser (as defined in model head(s)). Below, we present the most crucial utilization steps for the particular model. Please consult the docs for more information.

Install DAIv3 and depthai-nodes libraries:

pip install depthai
pip install depthai-nodes

Define model:

model_description = dai.NNModelDescription(
    "luxonis/esrgan:256x256"
)

nn = pipeline.create(ParsingNeuralNetwork).build(
    <CameraNode>, model_description
)

Inspect model head(s):

ImageOutputParser that outputs message (enhanced image).

Get parsed output(s):

while pipeline.isRuning():
    parser_output: dai.ImgFrame = parser_output_queue.get()

Example

You can quickly run the model using our script. It automatically downloads the model, creates a DepthAI pipeline, runs the inference, and displays the results using our DepthAI visualizer tool. To try it out, run:

python3 main.py \
    --model luxonis/esrgan:256x256

Super-resolution model.
License	Apache 2.0 Commercial use
Downloads	252
Tasks	Super Resolution
Model Types	ONNX

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC4	About 1 year ago