ESP-DL provides APIs for Neural Network (NN) Inference, Image Processing, Math Operations and Deep Learning Models. With ESP-DL, developers can use Espressif's SoCs for neural network inference easily and quickly. Thus far, our data show that, in comparison to ESP32, when ESP-DL runs on ESP32-S3 the acceleration of a 16-bit detection model is increased by 4.5 times, or 6.25 times in the case of a face recognition model. In addition, the 8-bit face recognition model is 2.5 times faster than the 16-bit model on ESP32-S3. Furthermore, we offer a tool that can help developers make their own model compatible with our platform.

Since ESP-DL does not need any peripherals, it can be used as a project component. For example, if it is added to the esp-who/components/ directory, ESP-DL can be used as a submodule of ESP-WHO, which contains several project-level examples of image-based applications. The figure below shows what ESP-DL consists of, and how ESP-DL is implemented as a project component.

Platform Conversion

ESP-DL provides tools that can help developers convert their own model (possibly developed with a third-party platform, such as TensorFlow, PyTorch, MXNet, etc.) into an 8-bit or 16-bit model, and evaluate the performance of the quantized model.

Model Zoo

ESP-DL also provides certain easy-to-use models, such as Human Face Detection, Human Face Recognition, Cat Face Detection, etc., in the so-called Model Zoo. You can now use these models out-of-the-box. Other models, such as those regarding color detection and hand-pose recognition, will be released soon.

Customizing a Model

In our GitHub tutorial entitled “How to Customize a Model Step by Step” you can find all relevant instructions with a runnable example which will help you implement your model quickly and easily.

Variety of APIs

ESP-DL contains sufficient APIs for developers to build their own model, such as Neural Network (NN), Image Processing, Matrix Operations. Meanwhile, developers can customize layers and provide us with their feedback if they have any special requirements about the API utility.

Software and Hardware Boost

ESP-DL implements quantized computation and brings about a more efficient kind of software by optimizing the assembly and architecture of the C/C++ code. It is worth mentioning that ESP32-S3, with its vector instructions, high-speed SPI interface and configurable cache memory, achieves a much faster acceleration in AI applications.

More details about ESP-DL can be found on our relevant GitHub page.