espressif/esp-dl

3.3.3

Latest
uploaded 3 hours 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 cat detection. It demonstrates detection results before and after int8 quantization.
    226.87 KB
  • color_detect
    A simple image inference example.
    13.26 KB
  • dog_detect
    A simple image inference example for detecting dogs using a specified image and configurable options.
    634.21 KB
  • hand_detect
    A simple image inference example for hand detection using the ESP32-P4 with quantization results provided.
    366.08 KB
  • hand_gesture_recognition
    A simple image inference example for recognizing 10 hand gestures plus a 'no_hand' category using the ESP-IDF framework.
    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, with configurable model options.
    43.03 KB
  • human_face_recognition
    A simple image inference example for human face recognition using models for detection and feature extraction.
    103.18 KB
  • mobilenetv2_cls
    A simple image inference example for IMAGENET classification with configurable model options.
    39.50 KB
  • model_in_sdcard
    10.71 KB
  • motion_detect
    52.61 KB
  • pedestrian_detect
    A simple image inference example for pedestrian detection, usable with ESP-IDF v5.3 and v5.4.
    97.44 KB
  • speaker_verification
    A simple audio inference example with three audio samples to verify speaker identity based on cosine similarity.
    682.25 KB
  • yolo11_detect
    A simple image inference example using Yolo11 for object detection, demonstrating results before and after int8 quantization.
    670.85 KB
  • yolo11_pose
    A simple image inference example using Yolo11 for pose estimation on ESP32-P4, tested with 'bus.jpg'.
    267.49 KB
  • yolo26_detect
    This example enables running quantized YOLOv26n inference on Espressif SoCs with flexible model loading.
    3.21 MB