Spaces:
Running
Running
File size: 1,431 Bytes
dd33bd5 c8081ec dd33bd5 c8081ec 56b9e35 d52fc21 c8081ec dd33bd5 56b9e35 c8081ec b072469 c8081ec dd33bd5 c8081ec dd33bd5 947217a dd33bd5 8bbfb69 c8081ec df55b81 cddddab c8081ec cddddab c8081ec cddddab c8081ec ea5afdb c8081ec |
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 39 40 41 |
import torch
import re
import gradio as gr
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel
device='cpu'
encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
model_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
def predict(image,max_length=64, num_beams=3):
image = image.convert('RGB')
image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
caption_ids = model.generate(image, max_length = max_length)[0]
caption_text = clean_text(tokenizer.decode(caption_ids))
return caption_text
input = gr.inputs.Image(label="Upload any Image", type = 'pil', optional=True)
output = gr.outputs.Textbox(type="auto",label="Captions")
examples = [f"example{i}.jpg" for i in range(1,7)]
title = "Image Captioning "
description = "Made by : shreyasdixit.tech"
interface = gr.Interface(
fn=predict,
description=description,
inputs = input,
theme="grass",
outputs=output,
examples = examples,
title=title,
)
interface.launch(debug=True) |