開発スタッフがアプリ関連の最新技術やニュースをご紹介します。

OpenAIのGPT APIは今話題のChatGPTやAutoGPTにも組み込まれています。
OpenAIのAPIを普段の業務に役立つ使用方法や既存のWebシステムにAIを導入してより便利にする方法などを模索しながらブログを更新していければと思います。
今回は初回ということでOpenAIのAPI Keyの取得方法からPythonの開発環境構築までを紹介したいと思います。

Tweet

AutoGPTとは
OpenAIのChatGPTのAPIを利用した自律的に情報を処理できるPythonアプリケーションです。

Tweet

Today, I would like to share how to rotate and crop the images in Python using opencv.

Rotating and cropping are common image processing techniques used to manipulate digital images. Python OpenCV is a powerful library for image processing that provides numerous tools for image manipulation. In this tutorial, we will learn how to rotate and crop images using Python OpenCV.

1. Installing OpenCV

First, we need to install OpenCV in our system. If you haven’t installed OpenCV yet, you can install it using pip:

pip install opencv-python

2. Loading an Image

After installing OpenCV, we can load an image using the imread() function. The imread() function takes the image file path as an argument and returns an array representing the image.

import cv2

# Load image

image = cv2.imread('path/to/image.jpg')

3. Rotating an Image

Rotating an image involves changing the orientation of the image. We can use the cv2.rotate() function to rotate an image. The cv2.rotate() function takes three arguments: the image, the rotation type, and the angle of rotation.

# Rotate image

rotated_image = cv2.rotate(image, cv2.cv2.ROTATE_90_CLOCKWISE)

In the above example, we have rotated the image 90 degrees clockwise.

4. Cropping an Image

Cropping an image involves selecting a portion of the image and discarding the rest. We can use array slicing to crop an image. The array slicing notation is [start_row:end_row, start_column:end_column].

# Crop image

cropped_image = image[start_row:end_row, start_column:end_column]

In the above example, we have cropped the image from start_row to end_row and start_column to end_column.

5. Displaying Images

After rotating or cropping an image, we can display the images using the cv2.imshow() function. The cv2.imshow() function takes two arguments: the name of the window and the image.

# Display images

cv2.imshow('Original Image', image)

cv2.imshow('Rotated Image', rotated_image)

cv2.imshow('Cropped Image', cropped_image)

# Wait for a key press and close all windows

cv2.waitKey(0)

cv2.destroyAllWindows()

6. Saving an Image

We can save the rotated or cropped image using the cv2.imwrite() function. The cv2.imwrite() function takes two arguments: the name of the file and the image.

# Save image

cv2.imwrite('path/to/saved/image.jpg', rotated_image)

In the above example, we have saved the rotated image to a file named ‘saved_image.jpg’ in the specified path.

Conclusion

In this tutorial, we have learned how to rotate and crop images using Python OpenCV. We have also learned how to display and save images. These are just a few of the many image processing techniques that can be performed using OpenCV. With OpenCV, we can perform a wide range of image processing tasks, from simple operations like cropping and rotating to more complex operations like edge detection and object recognition.

This is all for now. Hope you enjoy that.

By Asahi

Tweet

Hugging Face, an AI startup backed by tens of millions of venture capitalists, has released an open-source alternative to OpenAI’s AI-powered viral chatbot ChatGPT called HuggingChat.

HuggingChat can be tested via a web interface or integrated with existing apps and services via the Hugging Face API. HuggingChat can handle many of the same tasks as ChatGPT, such as writing code, writing emails, and writing song lyrics.

The AI model that powers HuggingChat was developed by Open Assistant. This is a project sponsored by LAION, a German non-profit organization responsible for creating the datasets on which Stable Diffusion, a text-to-image AI model, was trained.

HuggingChat joins a growing family of open source alternatives to ChatGPT. Last week, Stability AI released StableLM. This is a suite of models that can generate code and text with basic instructions.

Some researchers have criticized the release of open source models similar to StableLM in the past, claiming they are flawed and can be used for malicious purposes such as crafting phishing emails. claim. However, some point out that many of the policed business models like ChatGPT, with their filtering and moderation systems, have proven to be flawed and exploitable.

Tweet

Stable DiffusionをローカルPCで比較的簡単に実行することができる
Stable Diffusion WebUI（Automatic1111）を試してみました。

Tweet