Spaces:
Build error
Build error
File size: 2,247 Bytes
691b58e ab4fd24 774d35a b1af48e 774d35a cc48c86 6042ee3 bfc4942 1613060 6042ee3 b1af48e 6042ee3 1613060 cc48c86 1613060 cc48c86 6042ee3 |
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 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import torch
import gradio as gr
from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
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 = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
def predict_step(image_paths):
images = []
for image_path in image_paths:
i_image = Image.open(image_path)
if i_image.mode != "RGB":
i_image = i_image.convert(mode="RGB")
images.append(i_image)
pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device)
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]
return preds
#torch.hub.download_url_to_file('https://github.com/AaronCWacker/Yggdrasil/blob/main/images/35-Favorite-Games.jpg', '35-Favorite-Games.jpg')
#result = predict_step(['35-Favorite-Games.jpg'])
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
description= "NLP Image Understanding"
title = "NLP Image Understanding"
article = "nlpconnect vit-gpt2-image-captioning"
input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
output = gr.outputs.Textbox(type="auto",label="Captions")
#examples = [['35-Favorite-Games.jpg']]
examples = [f"{i}.jpg" for i in range(1,10)]
interface = gr.Interface(
fn=predict,
inputs = input,
outputs=output,
examples = examples,
title=title,
description=description,
article = article,
)
interface.launch()
|