Spaces:
Running
on
T4
Running
on
T4
File size: 25,728 Bytes
417b347 5ebeb73 417b347 5ebeb73 417b347 20103df 5ebeb73 417b347 5ebeb73 125e166 5ebeb73 125e166 5ebeb73 125e166 5ebeb73 417b347 5ebeb73 417b347 5ebeb73 417b347 5ebeb73 417b347 5ebeb73 417b347 5ebeb73 417b347 5ebeb73 417b347 5ebeb73 417b347 |
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 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 |
import os
import shutil
import gradio as gr
from helper.examples.examples import DemoImages
from helper.gradio_config import css, js, theme
from helper.text import TextAbout, TextApp, TextHowTo, TextRiksarkivet, TextRoadmap
from src.htr_pipeline.gradio_backend import CustomTrack, FastTrack, SingletonModelLoader
model_loader = SingletonModelLoader()
fast_track = FastTrack(model_loader)
custom_track = CustomTrack(model_loader)
images_for_demo = DemoImages()
with gr.Blocks(title="HTR Riksarkivet", theme=theme, css=css) as demo:
gr.Markdown(" ")
gr.Markdown(TextApp.title_markdown)
with gr.Tabs():
with gr.Tab("HTR Tool"):
with gr.Row():
with gr.Column(scale=2):
with gr.Row():
fast_track_input_region_image = gr.Image(
label="Image to run HTR on", type="numpy", tool="editor", elem_id="image_upload"
).style(height=395)
with gr.Row(equal_height=False):
# with gr.Group():
# callback = gr.CSVLogger()
# # hf_writer = gr.HuggingFaceDatasetSaver(HF_API_TOKEN, "htr_pipelin_flags")
# flagging_button = gr.Button(
# "Flag",
# variant="secondary",
# visible=True,
# ).style(full_width=True)
# radio_file_input = gr.Radio(
# value="Text file", choices=["Text file ", "Page XML file "], label="What kind file output?"
# )
radio_file_input = gr.CheckboxGroup(
choices=["Txt", "Page XML"],
value=["Txt"],
label="Output file extension",
# info="Only txt and page xml is supported for now!",
)
htr_pipeline_button = gr.Button(
"Run HTR",
variant="primary",
visible=True,
elem_id="run_pipeline_button",
).style(full_width=False)
with gr.Group():
with gr.Row():
fast_file_downlod = gr.File(label="Download output file", visible=False)
with gr.Row():
with gr.Accordion("Example images to use:", open=False) as fast_example_accord:
fast_name_files_placeholder = gr.Markdown(visible=False)
gr.Examples(
examples=images_for_demo.examples_list,
inputs=[fast_name_files_placeholder, fast_track_input_region_image],
label="Example images",
examples_per_page=3,
)
with gr.Column(scale=4):
with gr.Row():
fast_track_output_image = gr.Image(
label="HTR results visualizer",
type="numpy",
tool="editor",
).style(height=650)
with gr.Row(visible=False) as api_placeholder:
htr_pipeline_button_api = gr.Button(
"Run pipeline",
variant="primary",
visible=False,
).style(full_width=False)
xml_rendered_placeholder_for_api = gr.Textbox(visible=False)
with gr.Tab("Stepwise HTR Tool"):
with gr.Tabs():
with gr.Tab("1. Region Segmentation"):
with gr.Row():
with gr.Column(scale=2):
vis_data_folder_placeholder = gr.Markdown(visible=False)
name_files_placeholder = gr.Markdown(visible=False)
with gr.Row():
input_region_image = gr.Image(
label="Image to Region segment",
# type="numpy",
tool="editor",
).style(height=350)
with gr.Accordion("Region segment settings:", open=False):
with gr.Row():
reg_pred_score_threshold_slider = gr.Slider(
minimum=0.4,
maximum=1,
value=0.5,
step=0.05,
label="P-threshold",
info="""Filter and determine the confidence score
required for a prediction score to be considered""",
)
reg_containments_threshold_slider = gr.Slider(
minimum=0,
maximum=1,
value=0.5,
step=0.05,
label="C-threshold",
info="""The minimum required overlap or similarity
for a detected region or object to be considered valid""",
)
with gr.Row():
region_segment_model_dropdown = gr.Dropdown(
choices=["Riksarkivet/RmtDet_region"],
value="Riksarkivet/RmtDet_region",
label="Region segment model",
info="Will add more models later!",
)
with gr.Row():
clear_button = gr.Button("Clear", variant="secondary", elem_id="clear_button")
region_segment_button = gr.Button(
"Segment Region",
variant="primary",
elem_id="region_segment_button",
) # .style(full_width=False)
with gr.Row():
with gr.Accordion("Example images to use:", open=False) as example_accord:
gr.Examples(
examples=images_for_demo.examples_list,
inputs=[name_files_placeholder, input_region_image],
label="Example images",
examples_per_page=2,
)
with gr.Column(scale=3):
output_region_image = gr.Image(label="Segmented regions", type="numpy").style(height=600)
##############################################
with gr.Tab("2. Line Segmentation"):
image_placeholder_lines = gr.Image(
label="Segmented lines",
# type="numpy",
interactive="False",
visible=True,
).style(height=600)
with gr.Row(visible=False) as control_line_segment:
with gr.Column(scale=2):
with gr.Box():
regions_cropped_gallery = gr.Gallery(
label="Segmented regions",
show_label=False,
elem_id="gallery",
).style(
columns=[2],
rows=[2],
# object_fit="contain",
height=400,
preview=True,
container=False,
)
input_region_from_gallery = gr.Image(
label="Region segmentation to line segment", interactive="False", visible=False
).style(height=400)
with gr.Row():
with gr.Accordion("Line segment settings:", open=False):
with gr.Row():
line_pred_score_threshold_slider = gr.Slider(
minimum=0.3,
maximum=1,
value=0.4,
step=0.05,
label="Pred_score threshold",
info="""Filter and determine the confidence score
required for a prediction score to be considered""",
)
line_containments_threshold_slider = gr.Slider(
minimum=0,
maximum=1,
value=0.5,
step=0.05,
label="Containments threshold",
info="""The minimum required overlap or similarity
for a detected region or object to be considered valid""",
)
with gr.Row().style(equal_height=False):
line_segment_model_dropdown = gr.Dropdown(
choices=["Riksarkivet/RmtDet_lines"],
value="Riksarkivet/RmtDet_lines",
label="Line segment model",
info="Will add more models later!",
)
with gr.Row():
clear_line_segment_button = gr.Button(
" ",
variant="Secondary",
# elem_id="center_button",
).style(full_width=True)
line_segment_button = gr.Button(
"Segment Lines",
variant="primary",
# elem_id="center_button",
).style(full_width=True)
with gr.Column(scale=3):
# gr.Markdown("""lorem ipsum""")
output_line_from_region = gr.Image(
label="Segmented lines",
type="numpy",
interactive="False",
).style(height=600)
###############################################
with gr.Tab("3. Transcribe Text"):
image_placeholder_htr = gr.Image(
label="Transcribed lines",
# type="numpy",
interactive="False",
visible=True,
).style(height=600)
with gr.Row(visible=False) as control_htr:
inputs_lines_to_transcribe = gr.Variable()
with gr.Column(scale=2):
image_inputs_lines_to_transcribe = gr.Image(
label="Transcribed lines",
type="numpy",
interactive="False",
visible=False,
).style(height=470)
with gr.Row():
with gr.Accordion("Transcribe settings:", open=False):
transcriber_model = gr.Dropdown(
choices=["Riksarkivet/SATRN_transcriber", "microsoft/trocr-base-handwritten"],
value="Riksarkivet/SATRN_transcriber",
label="Transcriber model",
info="Will add more models later!",
)
with gr.Row():
clear_transcribe_button = gr.Button(" ", variant="Secondary", visible=True).style(
full_width=True
)
transcribe_button = gr.Button(
"Transcribe lines", variant="primary", visible=True
).style(full_width=True)
donwload_txt_button = gr.Button(
"Download text", variant="secondary", visible=False
).style(full_width=True)
with gr.Row():
txt_file_downlod = gr.File(label="Download text", visible=False)
with gr.Column(scale=3):
with gr.Row():
transcribed_text_df = gr.Dataframe(
headers=["Transcribed text"],
max_rows=15,
col_count=(1, "fixed"),
wrap=True,
interactive=False,
overflow_row_behaviour="paginate",
).style(height=600)
#####################################
with gr.Tab("4. Explore Results"):
image_placeholder_explore_results = gr.Image(
label="Cropped transcribed lines",
# type="numpy",
interactive="False",
visible=True,
).style(height=600)
with gr.Row(visible=False) as control_results_transcribe:
with gr.Column(scale=1, visible=True):
with gr.Box():
temp_gallery_input = gr.Variable()
gallery_inputs_lines_to_transcribe = gr.Gallery(
label="Cropped transcribed lines",
show_label=True,
elem_id="gallery_lines",
).style(
columns=[3],
rows=[3],
# object_fit="contain",
# height="600",
preview=True,
container=False,
)
with gr.Column(scale=1, visible=True):
mapping_dict = gr.Variable()
transcribed_text_df_finish = gr.Dataframe(
headers=["Transcribed text", "HTR prediction score"],
max_rows=15,
col_count=(2, "fixed"),
wrap=True,
interactive=False,
overflow_row_behaviour="paginate",
).style(height=600)
with gr.Tab("How to use"):
with gr.Tabs():
with gr.Tab("HTR Tool"):
with gr.Row().style(equal_height=False):
with gr.Column():
gr.Markdown(TextHowTo.htr_tool)
with gr.Column():
gr.Markdown(TextHowTo.both_htr_tool_video)
gr.Video(
value="https://github.com/Borg93/htr_gradio_file_placeholder/raw/main/eating_spaghetti.mp4",
label="How to use HTR Tool",
)
gr.Markdown(TextHowTo.reach_out)
with gr.Tab("Stepwise HTR Tool"):
with gr.Row().style(equal_height=False):
with gr.Column():
gr.Markdown(TextHowTo.stepwise_htr_tool)
with gr.Row():
with gr.Accordion("The tabs for the Stepwise HTR Tool:", open=False):
with gr.Tabs():
with gr.Tab("1. Region Segmentation"):
gr.Markdown(TextHowTo.stepwise_htr_tool_tab1)
with gr.Tab("2. Line Segmentation"):
gr.Markdown(TextHowTo.stepwise_htr_tool_tab2)
with gr.Tab("3. Transcribe Text"):
gr.Markdown(TextHowTo.stepwise_htr_tool_tab3)
with gr.Tab("4. Explore Results"):
gr.Markdown(TextHowTo.stepwise_htr_tool_tab4)
gr.Markdown(TextHowTo.stepwise_htr_tool_end)
with gr.Column():
gr.Markdown(TextHowTo.both_htr_tool_video)
gr.Video(
value="https://github.com/Borg93/htr_gradio_file_placeholder/raw/main/eating_spaghetti.mp4",
label="How to use Stepwise HTR Tool",
)
gr.Markdown(TextHowTo.reach_out)
with gr.Tab("About"):
with gr.Tabs():
with gr.Tab("Project"):
with gr.Row():
with gr.Column():
gr.Markdown(TextAbout.intro_and_pipeline_overview_text)
with gr.Row():
with gr.Tabs():
with gr.Tab("I. Binarization"):
gr.Markdown(TextAbout.binarization)
with gr.Tab("II. Region Segmentation"):
gr.Markdown(TextAbout.text_region_segment)
with gr.Tab("III. Line Segmentation"):
gr.Markdown(TextAbout.text_line_segmentation)
with gr.Tab("IV. Transcriber"):
gr.Markdown(TextAbout.text_htr)
with gr.Row():
gr.Markdown(TextAbout.text_data)
with gr.Column():
gr.Markdown(TextAbout.filler_text_data)
gr.Markdown(TextAbout.text_models)
with gr.Row():
with gr.Tabs():
with gr.Tab("Region Segmentation"):
gr.Markdown(TextAbout.text_models_region)
with gr.Tab("Line Segmentation"):
gr.Markdown(TextAbout.text_line_segmentation)
with gr.Tab("Transcriber"):
gr.Markdown(TextAbout.text_models_htr)
with gr.Tab("Roadmap"):
with gr.Row():
with gr.Column():
gr.Markdown(TextRoadmap.roadmap)
with gr.Column():
gr.Markdown(TextRoadmap.notebook)
with gr.Tab("Riksarkivet"):
with gr.Row():
with gr.Column():
gr.Markdown(TextRiksarkivet.riksarkivet)
with gr.Column():
gr.Markdown(TextRiksarkivet.contact)
htr_pipeline_button.click(
fast_track.segment_to_xml,
inputs=[fast_track_input_region_image, radio_file_input],
outputs=[fast_track_output_image, fast_file_downlod, fast_file_downlod],
)
htr_pipeline_button_api.click(
fast_track.segment_to_xml_api,
inputs=[fast_track_input_region_image],
outputs=[xml_rendered_placeholder_for_api],
api_name="predict",
)
# fast_track_input_region_image.change(
# fn=lambda: (gr.Accordion.update(open=False)),
# outputs=[fast_example_accord],
# )
# input_region_image.change(
# fn=lambda: (gr.Accordion.update(open=False)),
# outputs=[example_accord],
# )
# callback.setup([fast_track_input_region_image], "flagged_data_points")
# flagging_button.click(lambda *args: callback.flag(args), [fast_track_input_region_image], None, preprocess=False)
# flagging_button.click(lambda: (gr.update(value="Flagged")), outputs=flagging_button)
# fast_track_input_region_image.change(lambda: (gr.update(value="Flag")), outputs=flagging_button)
# custom track
region_segment_button.click(
custom_track.region_segment,
inputs=[input_region_image, reg_pred_score_threshold_slider, reg_containments_threshold_slider],
outputs=[output_region_image, regions_cropped_gallery, image_placeholder_lines, control_line_segment],
)
regions_cropped_gallery.select(
custom_track.get_select_index_image, regions_cropped_gallery, input_region_from_gallery
)
transcribed_text_df_finish.select(
fn=custom_track.get_select_index_df,
inputs=[transcribed_text_df_finish, mapping_dict],
outputs=gallery_inputs_lines_to_transcribe,
)
line_segment_button.click(
custom_track.line_segment,
inputs=[input_region_from_gallery, line_pred_score_threshold_slider, line_containments_threshold_slider],
outputs=[
output_line_from_region,
image_inputs_lines_to_transcribe,
inputs_lines_to_transcribe,
gallery_inputs_lines_to_transcribe,
temp_gallery_input,
# Hide
transcribe_button,
image_inputs_lines_to_transcribe,
image_placeholder_htr,
control_htr,
],
)
transcribe_button.click(
custom_track.transcribe_text,
inputs=[transcribed_text_df, inputs_lines_to_transcribe],
outputs=[
transcribed_text_df,
transcribed_text_df_finish,
mapping_dict,
txt_file_downlod,
control_results_transcribe,
image_placeholder_explore_results,
],
)
donwload_txt_button.click(
custom_track.download_df_to_txt,
inputs=transcribed_text_df,
outputs=[txt_file_downlod, txt_file_downlod],
)
# def remove_temp_vis():
# if os.path.exists("./vis_data"):
# os.remove("././vis_data")
# return None
clear_button.click(
lambda: (
(shutil.rmtree("./vis_data") if os.path.exists("./vis_data") else None, None)[1],
None,
None,
None,
gr.update(visible=False),
None,
None,
None,
gr.update(visible=False),
gr.update(visible=False),
gr.update(visible=True),
None,
gr.update(visible=False),
gr.update(visible=False),
gr.update(visible=True),
gr.update(visible=True),
),
inputs=[],
outputs=[
vis_data_folder_placeholder,
input_region_image,
regions_cropped_gallery,
input_region_from_gallery,
control_line_segment,
output_line_from_region,
inputs_lines_to_transcribe,
transcribed_text_df,
control_htr,
inputs_lines_to_transcribe,
image_placeholder_htr,
output_region_image,
image_inputs_lines_to_transcribe,
control_results_transcribe,
image_placeholder_explore_results,
image_placeholder_lines,
],
)
demo.load(None, None, None, _js=js)
demo.queue(concurrency_count=5, max_size=20)
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860, show_api=False, show_error=True)
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860, show_api=False, show_error=True)
|