Spaces:
Runtime error
Runtime error
File size: 1,526 Bytes
797b64f 4045aa3 797b64f 00ca6f9 797b64f 00ca6f9 52ccae8 00ca6f9 797b64f 58572c5 797b64f ecda335 797b64f 52ccae8 797b64f 52ccae8 797b64f 7110ce4 d8ec7b6 86b2682 ed498b4 7110ce4 56c2bd0 7110ce4 56c2bd0 |
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 42 43 44 |
import torch
import re
import gradio as gr
from pathlib import Path
from transformers import AutoTokenizer, AutoFeatureExtractor, VisionEncoderDecoderModel
def predict(image, max_length=64, num_beams=4):
image = image.convert('RGB')
pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device)
with torch.no_grad():
text = tokenizer.decode(model.generate(pixel_values.cpu())[0])
text = text.replace('<|endoftext|>', '').split('\n')
return text[0]
model_path = "team-indain-image-caption/hindi-image-captioning"
device = "cpu"
# Load model.
model = VisionEncoderDecoderModel.from_pretrained(model_path)
model.to(device)
print("Loaded model")
feature_extractor = AutoFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
print("Loaded feature_extractor")
tokenizer = AutoTokenizer.from_pretrained(model_path)
print("Loaded tokenizer")
title = "Hindi Image Captioning"
description = ""
input = gr.inputs.Image(label="Image to search", type = 'pil', optional=False)
output = gr.outputs.Textbox(type="auto",label="Captions")
article = "This HuggingFace Space presents a demo for Image captioning in Hindi built with VIT Encoder and GPT2 Decoder"
example = ["./examples/example_{i}.jpg" for i in range(1,6)]
interface = gr.Interface(
fn=predict,
inputs = input,
theme="grass",
outputs=output,
title=title,
description=article,
)
interface.launch(share = True) |