espressif/esp-dl

Health v2 · maintenance only

Adoption not part of the score

1125 stars · 222 forks observed · 2026-09-01

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ESP-DL is Espressif's lightweight neural network inference framework for ESP-series chips, with a custom .espdl model format, quantization tooling (ESP-PPQ), and optimized operators for on-device AI. It includes a static memory planner, dual-core scheduling, and prebuilt models such as OCR for running inference directly on microcontrollers.

Use cases

• run neural network inference on esp32
• deploy quantized models on microcontrollers
• on-device ocr for embedded systems
• build aiot applications with esp chips
• convert onnx pytorch tensorflow models for esp32
• image recognition on edge devices

When to choose

• you are developing AI applications on Espressif ESP32-series SoCs
• you need efficient, memory-optimized inference on resource-constrained hardware
• you want to quantize standard models (ONNX, PyTorch, TensorFlow) for embedded deployment

When to avoid

• you need training or fine-tuning rather than inference
• your target hardware is not an Espressif chip
• you need a full-featured deep learning framework like PyTorch or TensorFlow

Facets

library · maturity active

machine-learning llm-inference image-processing ocr computer-vision machine-learning deep-learning iot embedded-systems artificial-intelligence embedded iot cpp c esp32 neural-network-inference model-quantization on-device-ai flatbuffers aiot microcontroller edge-ai

Member repositories

For agents

markdown · JSON · MCP: product_card(name="espressif/esp-dl")