File size: 14,481 Bytes
3b057c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
deef83a
3b057c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr

from helper.examples.examples import DemoImages
from src.htr_pipeline.gradio_backend import CustomTrack, SingletonModelLoader

model_loader = SingletonModelLoader()

custom_track = CustomTrack(model_loader)

images_for_demo = DemoImages()

with gr.Blocks() as stepwise_htr_tool_tab:
    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=5,
                            )

                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)

    # 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,
        ],
    )