espressif/esp-dl

3.3.7

Latest
uploaded 1 day ago
esp-dl is a lightweight and efficient neural network inference framework designed specifically for ESP series chips.

19 examples

  • how_to_deploy_streaming_model 1
  • cat_detect
    A simple image inference example using a pre-defined image to demonstrate detection results on ESP32-P4.
    226.87 KB
  • color_detect
    A simple image inference example.
    13.26 KB
  • dog_detect
    A simple image inference example using dog.jpg for testing, demonstrating detection results on the ESP32-P4.
    634.21 KB
  • hand_detect
    A simple image inference example that detects hand positions using specified models on ESP32 hardware.
    367.67 KB
  • hand_gesture_recognition
    A simple image inference example for hand gesture recognition supporting 10 gestures plus a 'no_hand' category.
    751.48 KB
  • how_to_run_model
    12.84 KB
  • human_face_detect
    A simple image inference example for human face detection using ESP-IDF. See full example in esp-who.
    43.03 KB
  • human_face_recognition
    A simple image inference example for human face recognition using ESP32 devices.
    103.18 KB
  • mobilenetv2_cls
    A simple image inference example classifying a built-in cat image and benchmarking average inference latency.
    40.58 KB
  • model_in_sdcard
    10.71 KB
  • motion_detect
    52.64 KB
  • pedestrian_detect
    A simple image inference example for pedestrian detection, with configurable options for different models.
    97.44 KB
  • speaker_verification
    A simple audio inference example that verifies speaker identity using cosine similarity score between audio samples.
    683.06 KB
  • yolo11_detect
    A simple image inference example using Yolo11 for object detection with configurable options for different models.
    399.39 KB
  • yolo11_pose
    A simple image inference example using Yolo11 pose detection on ESP32 devices.
    267.49 KB
  • yolo26_detect
    This example demonstrates running quantized YOLOv26n inference on Espressif SoCs with optimizations and flexible model loading.
    3.21 MB