Spaces:
Build error
Build error
import gradio as gr | |
import torch | |
import os | |
from PIL import Image | |
import pandas as pd | |
from transformers import CLIPProcessor, CLIPModel | |
checkpoint = "vincentclaes/emoji-predictor" | |
# x_, _, files = next(os.walk("./emojis")) | |
# no_of_emojis = range(len(files)) | |
# emojis_as_images = [Image.open(f"emojis/{i}.png") for i in no_of_emojis] | |
adjectives = pd.read_table("./adjectives.txt", header=None)[0].to_list() | |
K = 4 | |
processor = CLIPProcessor.from_pretrained(checkpoint) | |
model = CLIPModel.from_pretrained(checkpoint) | |
def concat_images(*images): | |
"""Generate composite of all supplied images. | |
https://stackoverflow.com/a/71315656/1771155 | |
""" | |
# Get the widest width. | |
width = max(image.width for image in images) | |
# Add up all the heights. | |
height = max(image.height for image in images) | |
# set the correct size of width and heigtht of composite. | |
composite = Image.new("RGB", (2 * width, 2 * height)) | |
assert K == 4, "We expect 4 suggestions, other numbers won't work." | |
for i, image in enumerate(images): | |
if i == 0: | |
composite.paste(image, (0, 0)) | |
elif i == 1: | |
composite.paste(image, (width, 0)) | |
elif i == 2: | |
composite.paste(image, (0, height)) | |
elif i == 3: | |
composite.paste(image, (width, height)) | |
return composite | |
def get_tag(emoji, tags, model=model, processor=processor, K=4): | |
if tags: | |
tags = tags.strip().split(",") | |
else: | |
tags = adjectives | |
inputs = processor( | |
text=tags, images=emoji, return_tensors="pt", padding=True, truncation=True | |
) | |
outputs = model(**inputs) | |
# we take the softmax to get the label probabilities | |
probs = outputs.logits_per_text.softmax(dim=0) | |
probs_formatted = torch.tensor([prob[0] for prob in probs]) | |
values, indices = probs_formatted.topk(K) | |
return "Tag (confidence): " + ", ".join( | |
[f"{tags[i]} ({round(v.item(), 2)})" for v, i in zip(values, indices)] | |
) | |
title = "Tagging an Emoji" | |
description = """You provide an Emoji and our few-shot fine tuned CLIP model will suggest some tags that are appropriate.\n | |
We use the 228 most common adjectives in english](https://grammar.yourdictionary.com/parts-of-speech/adjectives/list-of-adjective-words.html).\n | |
You can also specify your own custom tags, for example; love,hate,fun,bitterness. | |
""" | |
examples = [[f"emojis/{i}.png"] for i in range(32)] | |
text = gr.inputs.Textbox( | |
placeholder="Enter a text and we will try to predict an emoji..." | |
) | |
gr.Interface( | |
fn=get_tag, | |
inputs=[ | |
gr.components.Image(type="pil", label="emoji"), | |
gr.components.Textbox( | |
label="tags", | |
placeholder="Provide a comma seperated list of tags; tag1,tag2,tag3,...", | |
), | |
], | |
outputs=gr.Textbox(), | |
examples=examples, | |
examples_per_page=32, | |
title=title, | |
description=description, | |
).launch() | |