File size: 1,227 Bytes
b716bcc 93ffbec b716bcc 93ffbec b716bcc 93ffbec b716bcc 93ffbec b716bcc 000d1ec b716bcc 93ffbec b716bcc 93ffbec |
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 |
import torch
import re
import gradio as gr
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel
device='cpu'
encoder_checkpoint = "jaimin/image_caption"
decoder_checkpoint = "jaimin/image_caption"
model_checkpoint = "jaimin/image_caption"
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=4):
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 your Image", type = 'pil', optional=True)
output = gr.outputs.Textbox(label="Captions")
examples = [f"example{i}.jpg" for i in range(1,7)]
title = "Image To Text"
interface = gr.Interface(
fn=predict,
inputs = input,
outputs=output,
title=title,
)
interface.launch(debug=True) |