Update README.md

README.md

@@ -38,7 +38,7 @@ You can use this model for image captioning tasks with the Hugging Face transfor
 # Installation
 
 To use this model, you need to install the following libraries:
-
+```python
 bash
 Copy code
 pip install torch torchvision transformers
@@ -48,20 +48,20 @@ Copy code
 from transformers import VisionEncoderDecoderModel, ViTImageProcessor, GPT2Tokenizer
 import torch
 from PIL import Image
-
+```
 # Load the fine-tuned model and tokenizer
-
+```python
 model = VisionEncoderDecoderModel.from_pretrained("ashok2216/vit-gpt2-image-captioning_COCO_FineTuned")
 processor = ViTImageProcessor.from_pretrained("ashok2216/vit-gpt2-image-captioning_COCO_FineTuned")
 tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
-
+```
 # Preprocess the image
-
+```python
 image = Image.open("path_to_image.jpg")
 inputs = processor(images=image, return_tensors="pt")
-
+```
 # Generate caption
-
+```python
 pixel_values = inputs.pixel_values
 output = model.generate(pixel_values)
 caption = tokenizer.decode(output[0], skip_special_tokens=True)
@@ -72,7 +72,7 @@ Image Input: The input should be an image file. Supported formats include .jpg,
 Output: A text string representing the generated caption for the image.
 Example
 For an input image, the model might generate a caption like:
-
+```
 # Input Image:
 
 Generated Caption: