0xalivecow/senju
1
0
Fork 0
mirror of https://github.com/senju1337/senju.git synced 2025-12-24 07:39:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update image_reco.py

Browse source 
shortend some lines
This commit is contained in:
Amrasil 2025-03-27 15:36:46 +01:00 • committed by GitHub
parent a02e6ccb42
commit bfd52423b7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 21 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

34
senju/image_reco.py
View file

@ -2,10 +2,13 @@
Senju Image Recognition Module Senju Image Recognition Module
============================= =============================
A module providing image description generation capabilities for the Senju haiku application. A module providing image description generation capabilities for the Senju
haiku application.
This module leverages pre-trained vision-language models (specifically BLIP) to generate This module leverages pre-trained vision-language models (specifically BLIP)
textual descriptions of uploaded images. These descriptions can then be used as input to generate
textual descriptions of uploaded images. These descriptions can then be
used as input
for the haiku generation process, enabling image-to-haiku functionality. for the haiku generation process, enabling image-to-haiku functionality.
Classes Classes
@ -43,11 +46,13 @@ from transformers import BlipProcessor, BlipForConditionalGeneration
class ImageDescriptionGenerator: class ImageDescriptionGenerator:
""" """
A class for generating textual descriptions of images using a vision-language model. A class for generating textual descriptions of images using
a vision-language model.
This class handles the loading of a pre-trained BLIP model, image preprocessing, This class handles the loading of a pre-trained BLIP model, image
and caption generation. It provides an interface for converting raw image data preprocessing, and caption generation. It provides an interface for
into natural language descriptions that can be used for haiku inspiration. converting raw image data into natural language descriptions that can
be used for haiku inspiration.
:ivar processor: The BLIP processor for handling image inputs :ivar processor: The BLIP processor for handling image inputs
:type processor: BlipProcessor :type processor: BlipProcessor
@ -75,14 +80,16 @@ class ImageDescriptionGenerator:
""" """
Generate a descriptive caption for the given image. Generate a descriptive caption for the given image.
This method processes the raw image data, runs inference with the BLIP model, This method processes the raw image data, runs inference with
and returns a structured response with the generated description. the BLIP model, and returns a structured response with the
generated description.
:param image_data: Raw binary image data :param image_data: Raw binary image data
:type image_data: bytes :type image_data: bytes
:param max_length: Maximum token length for the generated caption :param max_length: Maximum token length for the generated caption
:type max_length: int :type max_length: int
:return: Dictionary containing the generated description and confidence score :return: Dictionary containing the generated description and
confidence score
:rtype: dict :rtype: dict
""" """
# Convert uploaded bytes to image # Convert uploaded bytes to image
@ -120,12 +127,13 @@ def gen_response(image_data) -> dict:
""" """
Generate a description for an image using the global description generator. Generate a description for an image using the global description generator.
This function provides a simplified interface to the image description functionality This function provides a simplified interface to the image
for use in API endpoints. description functionality for use in API endpoints.
:param image_data: Raw binary image data :param image_data: Raw binary image data
:type image_data: bytes :type image_data: bytes
:return: Dictionary containing the image description and confidence information :return: Dictionary containing the image description and
confidence information
:rtype: dict :rtype: dict
:raises Exception: If image processing or description generation fails :raises Exception: If image processing or description generation fails
""" """