ESP-DL is a library for high-performance deep learning resources dedicated to ESP32, ESP32-S2, ESP32-S3 and ESP32-C3. Please read ESP-DL User Guide for more information about ESP-DL.

ESP-DL provides APIs for Neural Network (NN) Inference, Image Processing, Math Operations and some Deep Learning Models. With ESP-DL, you can use Espressif's SoCs for AI applications easily and fast.

As ESP-DL does not need any peripherals, it can be used as a component of some projects. For example, you can use it as a component of ESP-WHO, which contains several project-level examples of image application. The figure below shows what ESP-DL consists of and how ESP-DL is implemented as a component in a project.

For setup instructions to get started with ESP-DL, please read Get Started.

Please use ESP-IDF release/v5.0 or above.

ESP-DL provides some model APIs in the Model Zoo, such as Human Face Detection, Human Face Recognition, Cat Face Detection, etc. You can use these models in the table below out of box.

We recommend using TVM to deploy your models, for details please refer to ESP-DL/tutorial/tvm_example.

For feature requests or bug reports, please submit an issue. We will prioritize the most anticipated features.