Charlie Li
build all
4697797
raw history blame
No virus
3.41 kB
import gradio as gr
from utils import *
file_url = "https://storage.googleapis.com/derendering_model/derendering_supp.zip"
filename = "derendering_supp.zip"
download_file(file_url, filename)
unzip_file(filename)
print("Downloaded and unzipped the file.")
diagram = get_svg_content("derendering_supp/derender_diagram.svg")
org = get_svg_content("org/cor.svg")
org_content = f"""
{org}
"""
def demo(Dataset, Model):
if Model == "Small-i":
inkml_path = f"./derendering_supp/small-i_{Dataset}_inkml"
elif Model == "Small-p":
inkml_path = f"./derendering_supp/small-p_{Dataset}_inkml"
elif Model == "Large-i":
inkml_path = f"./derendering_supp/large-i_{Dataset}_inkml"
path = f"./derendering_supp/{Dataset}/images_sample"
samples = os.listdir(path)
# Randomly pick a sample
picked_samples = random.sample(samples, min(1, len(samples)))
query_modes = ["d+t", "r+d", "vanilla"]
plot_title = {"r+d": "Recognized: ", "d+t": "OCR Input: ", "vanilla": ""}
text_outputs = []
for name in picked_samples:
img_path = os.path.join(path, name)
img = load_and_pad_img_dir(img_path)
for mode in query_modes:
example_id = name.strip(".png")
inkml_file = os.path.join(inkml_path, mode, example_id + ".inkml")
text_field = parse_inkml_annotations(inkml_file)["textField"]
output_text = f"{plot_title[mode]}{text_field}"
text_outputs.append(output_text) # Append text output for the current mode
ink = inkml_to_ink(inkml_file)
plot_ink_to_video(ink, mode + ".mp4", input_image=img)
return (
img,
text_outputs[0],
"d+t.mp4",
text_outputs[1],
"r+d.mp4",
text_outputs[2],
"vanilla.mp4",
)
with gr.Blocks() as app:
gr.HTML(org_content)
gr.Markdown(
f"""
# InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write<br>
<div>{diagram}</div>
๐Ÿ”” This demo showcases the outputs of <b>Small-i</b>, <b>Small-p</b>, and <b>Large-i</b> on three public datasets (100 samples each).<br>
โ„น๏ธ Choose a model variant and dataset, then click 'Sample' to see an input with its corresponding outputs for all three inference types..<br>
"""
)
with gr.Row():
dataset = gr.Dropdown(
["IMGUR5K", "IAM", "HierText"], label="Dataset", value="HierText"
)
model = gr.Dropdown(
["Small-i", "Large-i", "Small-p"],
label="InkSight Model Variant",
value="Small-i",
)
im = gr.Image(label="Input Image")
with gr.Row():
d_t_text = gr.Textbox(
label="OCR recognition input to the model", interactive=False
)
r_d_text = gr.Textbox(label="Recognition from the model", interactive=False)
vanilla_text = gr.Textbox(label="Vanilla", interactive=False)
with gr.Row():
d_t = gr.Video(label="Derender with Text", autoplay=True)
r_d = gr.Video(label="Recognize and Derender", autoplay=True)
vanilla = gr.Video(label="Vanilla", autoplay=True)
with gr.Row():
btn_sub = gr.Button("Sample")
btn_sub.click(
fn=demo,
inputs=[dataset, model],
outputs=[im, d_t_text, d_t, r_d_text, r_d, vanilla_text, vanilla],
)
app.launch()