File size: 1,433 Bytes
4b4c90a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
import os
from PIL import Image
import numpy as np
import torch as T
import transformers
# Assuming necessary model and tokenizer are already set up
PATH_LLAVA = '_ckpt/LLaVA-7B-v1'
tokenizer = transformers.AutoTokenizer.from_pretrained(PATH_LLAVA)
model = transformers.AutoModelForCausalLM.from_pretrained(PATH_LLAVA).cuda()
def remove_alter(s): # Simplify expressive instruction
if 'ASSISTANT:' in s: s = s[s.index('ASSISTANT:')+10:].strip()
if '</s>' in s: s = s[:s.index('</s>')].strip()
if 'alternative' in s.lower(): s = s[:s.lower().index('alternative')]
if '[IMG0]' in s: s = s[:s.index('[IMG0]')]
s = '.'.join([s.strip() for s in s.split('.')[:2]])
if s[-1]!='.': s += '.'
return s.strip()
def load_image_and_generate_instruction(image_path):
# Load the image
img = Image.open(image_path)
img.show()
# Example: Generate a simple instruction based on the image
# This is a placeholder. You would replace this with your own method
# to analyze the image and generate a textual description or instruction.
instruction = "Describe what to do with this image."
# Simplify and generate expressive instruction
expressive_instruction = remove_alter(instruction)
print("Expressive Instruction:", expressive_instruction)
# Example usage
image_path = './path/to/your/image.jpg' # Update this path to your image
load_image_and_generate_instruction(image_path)
|