app.py

import torch
from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
from PIL import Image
from torchvision import transforms

model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}

def predict_step(image_paths):
  images = []
  for image_path in image_paths:
    i_image = Image.open(image_path)
    if i_image.mode != "RGB":
      i_image = i_image.convert(mode="RGB")

    images.append(i_image)

  pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
  pixel_values = pixel_values.to(device)

  output_ids = model.generate(pixel_values, **gen_kwargs)

  preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
  preds = [pred.strip() for pred in preds]
  return preds

target_object = 'Desk'

def predict_step(image_paths):
    images = []
    for image_path in image_paths:
        i_image = Image.open(image_path)
        if i_image.mode != "RGB":
            i_image = i_image.convert(mode="RGB")

        images.append(i_image)

    pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
    pixel_values = pixel_values.to(device)

    output_ids = model.generate(pixel_values, **gen_kwargs)

    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
    preds = [pred.strip() for pred in preds]

    

    # Check if the target object is mentioned in the captions
    object_found = any(target_object.lower() in caption.lower() for caption in preds)


    return object_found

    # Check if the target object is present in the image


result = predict_step(['D:\Sushant.jpg'])

if result:
    print(f"The object "+ target_object + " is present in the image.")
else:
    print(f"The object "+ target_object + " is not present in the image.")