| """ | |
| Ollama Light Assistant | |
| Test the ability for LLMs to call tools (i.e. functions) from within the Ollama | |
| environment on a Raspberry Pi with speech-to-text. Tested with a Raspberry Pi 5 | |
| (8 GB) and this USB microphone: https://www.adafruit.com/product/3367. | |
| Connect an LED to GPIO 17 (physical pin 11 on the board) in an active high | |
| configuration: |
To perform object detection inference using a TensorFlow Lite model (.tflite) on a JPG image with tflite-runtime, you need to follow several steps including installation of the necessary packages, loading the model, preprocessing the input image, running inference, and handling the output. Here's a comprehensive guide:
You'll need to install tflite-runtime and Pillow for image processing. If you haven't installed these, you can do so using pip:
pip install tflite-runtime pillow
| #!/usr/bin/env python | |
| import device_patches # Device specific patches for Jetson Nano (needs to be before importing cv2) | |
| import cv2 | |
| import os | |
| import sys, getopt | |
| import numpy as np | |
| from edge_impulse_linux.image import ImageImpulseRunner |
| # This works for gym 0.26.2. It might not work on previous versions. | |
| import gym | |
| import cv2 | |
| fps = 30 | |
| # Create environment | |
| env = gym.make('CartPole-v1', render_mode='rgb_array') |
| /** | |
| * Magic Wand Inference Demo | |
| * | |
| * Attach a button to pin 2. Press button to start collection. Raw data will be | |
| * collected and fed to the impulse for inference. Inference results are printed | |
| * to the serial terminal. | |
| * | |
| * Author: Shawn Hymel (EdgeImpulse, Inc.) | |
| * Date: October 10, 2022 | |
| * License: Apache-2.0 (apache.org/licenses/LICENSE-2.0) |
| """ | |
| PyGame Display Test | |
| Run to see if you can draw things in Pygame. Press 'esc` to exit. Run with | |
| root privileges to draw on external monitor (e.g. from SSH). | |
| """ | |
| import pygame | |
| # Initialize pygame |
| #include <stdarg.h> | |
| // Makeshift printf for the Serial terminal | |
| void aprintf(const char *format, ...) { | |
| static char print_buf[1024] = { 0 }; | |
| va_list args; | |
| va_start(args, format); | |
| int r = vsnprintf(print_buf, sizeof(print_buf), format, args); | |
| va_end(args); |
| # TFLite quantized inference example | |
| # | |
| # Based on: | |
| # https://www.tensorflow.org/lite/performance/post_training_integer_quant | |
| # https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/Tensor.QuantizationParams | |
| import numpy as np | |
| import tensorflow as tf | |
| # Location of tflite model file (float32 or int8 quantized) |