# -*- coding: utf-8 -*-
"""Copy of caption.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1nybx9b_W5IsJz9G0GHvDx6KQKiTv_gt3

## Image Caption Generator 

We are going to use Transformers model to generate caption from an Image.

### Installation



1.   Transformers
2.   Pytorch
3. Image 


@misc {nlp_connect_2022,

	author       = { {NLP Connect} },
	title        = { vit-gpt2-image-captioning (Revision 0e334c7) },
	year         = 2022,
	url          = { https://huggingface.co/nlpconnect/vit-gpt2-image-captioning },
	doi          = { 10.57967/hf/0222 },
	publisher    = { Hugging Face }
} *italicized text*
"""

#!pip install transformers

from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
import torch
from PIL import Image
import pandas as pd

model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTFeatureExtractor.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 = 8
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}

def cap_generation(img,Num_of_captions):
  images = []
  Num_of_captions = int(Num_of_captions)
  if img.mode != "RGB":
    img = img.convert(mode="RGB")
  width, height = img.size

  new_size = (int(width/4), int(height/4))

# Resize the image for faster computation.
  img = img.resize(new_size)

  images.append(img)

  pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
  pixel_values = pixel_values.to(device)
  if(Num_of_captions==1):
    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]
    result = [s.capitalize() + '.' for s in preds]
    data = {"No.": range(1, len(result)+1), "Captions": result}
    df = pd.DataFrame(data)
    return df
    
  else:
    output_ids = model.generate(pixel_values,max_length = 100,num_return_sequences=Num_of_captions,do_sample=True)
    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
    preds = [pred.strip() for pred in preds]
    result = [s.capitalize() + '.' for s in preds]
    data = {"No.": range(1, len(result)+1), "Captions": result}
    df = pd.DataFrame(data)
    return df

#!pip install gradio
import gradio as gr

import gradio as gr
inputs = [
    gr.inputs.Image(type='pil',label = 'Original Image'),
    gr.inputs.Number(default = 1, label="Number Of Captions")
]
outputs=[gr.outputs.Dataframe(type="pandas")]

title = "Image Captioning Using VIT-GPT2 "
description = "Image Captioning with vit-gpt2"
article = " <a href  = 'https://huggingface.co/nlpconnect/vit-gpt2-image-captioning'> Model </a>"
'''examples = [
    ['Image3.png']
]'''

interface = gr.Interface(
    cap_generation,
    inputs,
    outputs=outputs,
    title=title,
    description=description,
    article=article,
    theme="huggingface",
    )

interface.launch()