Skip to content

Commit d8ea10b

Browse files
zhang-progzhang-prog
authored
update high_performance_inference.en.md (#2534)
* update high_performance_inference.en.md * update
1 parent a81f88b commit d8ea10b

File tree

1 file changed

+156
-55
lines changed

1 file changed

+156
-55
lines changed

‎docs/pipeline_deploy/high_performance_inference.en.md

Lines changed: 156 additions & 55 deletions
Original file line numberDiff line numberDiff line change
@@ -178,147 +178,248 @@ PaddleX combines model information and runtime environment information to provid
178178
<table>
179179
<tr>
180180
<th>Pipeline</th>
181-
<th>Pipeline Module</th>
182-
<th>Specific Models</th>
181+
<th>Module</th>
182+
<th>Model Support List</th>
183183
</tr>
184+
184185
<tr>
185-
<td>General Image Classification</td>
186-
<td>Image Classification</td>
187-
<td>ResNet18<br/>ResNet34<details>
188-
<summary><b>more</b></summary>ResNet50<br/>ResNet101<br/>ResNet152<br/>ResNet18_vd<br/>ResNet34_vd<br/>ResNet50_vd<br/>ResNet101_vd<br/>ResNet152_vd<br/>ResNet200_vd<br/>PP-LCNet_x0_25<br/>PP-LCNet_x0_35<br/>PP-LCNet_x0_5<br/>PP-LCNet_x0_75<br/>PP-LCNet_x1_0<br/>PP-LCNet_x1_5<br/>PP-LCNet_x2_0<br/>PP-LCNet_x2_5<br/>PP-LCNetV2_small<br/>PP-LCNetV2_base<br/>PP-LCNetV2_large<br/>MobileNetV3_large_x0_35<br/>MobileNetV3_large_x0_5<br/>MobileNetV3_large_x0_75<br/>MobileNetV3_large_x1_0<br/>MobileNetV3_large_x1_25<br/>MobileNetV3_small_x0_35<br/>MobileNetV3_small_x0_5<br/>MobileNetV3_small_x0_75<br/>MobileNetV3_small_x1_0<br/>MobileNetV3_small_x1_25<br/>ConvNeXt_tiny<br/>ConvNeXt_small<br/>ConvNeXt_base_224<br/>ConvNeXt_base_384<br/>ConvNeXt_large_224<br/>ConvNeXt_large_384<br/>MobileNetV1_x0_25<br/>MobileNetV1_x0_5<br/>MobileNetV1_x0_75<br/>MobileNetV1_x1_0<br/>MobileNetV2_x0_25<br/>MobileNetV2_x0_5<br/>MobileNetV2_x1_0<br/>MobileNetV2_x1_5<br/>MobileNetV2_x2_0<br/>SwinTransformer_tiny_patch4_window7_224<br/>SwinTransformer_small_patch4_window7_224<br/>SwinTransformer_base_patch4_window7_224<br/>SwinTransformer_base_patch4_window12_384<br/>SwinTransformer_large_patch4_window7_224<br/>SwinTransformer_large_patch4_window12_384<br/>PP-HGNet_small<br/>PP-HGNet_tiny<br/>PP-HGNet_base<br/>PP-HGNetV2-B0<br/>PP-HGNetV2-B1<br/>PP-HGNetV2-B2<br/>PP-HGNetV2-B3<br/>PP-HGNetV2-B4<br/>PP-HGNetV2-B5<br/>PP-HGNetV2-B6<br/>CLIP_vit_base_patch16_224<br/>CLIP_vit_large_patch14_224</details></td>
186+
<td rowspan="2">OCR</td>
187+
<td>Text Detection</td>
188+
<td>✅</td>
189189
</tr>
190190

191191
<tr>
192-
<td>General Object Detection</td>
193-
<td>Object Detection</td>
194-
<td>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<details>
195-
<summary><b>more</b></summary>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>YOLOX-N<br/>YOLOX-T<br/>YOLOX-S<br/>YOLOX-M<br/>YOLOX-L<br/>YOLOX-X<br/>YOLOv3-DarkNet53<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOv3-MobileNetV3<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>PicoDet-S<br/>PicoDet-L</details></td>
192+
<td>Text Recognition</td>
193+
<td>✅</td>
196194
</tr>
197195

198196
<tr>
199-
<td>General Semantic Segmentation</td>
200-
<td>Semantic Segmentation</td>
201-
<td>Deeplabv3-R50<br/>Deeplabv3-R101<details>
202-
<summary><b>more</b></summary>Deeplabv3_Plus-R50<br/>Deeplabv3_Plus-R101<br/>PP-LiteSeg-T<br/>OCRNet_HRNet-W48<br/>OCRNet_HRNet-W18<br/>SeaFormer_tiny<br/>SeaFormer_small<br/>SeaFormer_base<br/>SeaFormer_large<br/>SegFormer-B0<br/>SegFormer-B1<br/>SegFormer-B2<br/>SegFormer-B3<br/>SegFormer-B4<br/>SegFormer-B5</details></td>
197+
<td rowspan="7">PP-ChatOCRv3</td>
198+
<td>Table Recognition</td>
199+
<td>✅</td>
203200
</tr>
204201

205202
<tr>
206-
<td>General Instance Segmentation</td>
207-
<td>Instance Segmentation</td>
208-
<td>Mask-RT-DETR-L<br/>Mask-RT-DETR-H</td>
203+
<td>Layout Detection</td>
204+
<td>✅</td>
205+
</tr>
206+
207+
<tr>
208+
<td>Text Detection</td>
209+
<td>✅</td>
209210
</tr>
210211

211212
<tr>
212-
<td rowspan="3">Seal Text Recognition</td>
213-
<td>Layout Analysis</td>
214-
<td>PicoDet-S_layout_3cls<br/>PicoDet-S_layout_17cls<details>
215-
<summary><b>more</b></summary>PicoDet-L_layout_3cls<br/>PicoDet-L_layout_17cls<br/>RT-DETR-H_layout_3cls<br/>RT-DETR-H_layout_17cls</details></td>
213+
<td>Text Recognition</td>
214+
<td>✅</td>
216215
</tr>
217216

218217
<tr>
219218
<td>Seal Text Detection</td>
220-
<td>PP-OCRv4_server_seal_det<br/>PP-OCRv4_mobile_seal_det</td>
219+
<td>✅</td>
221220
</tr>
222221

223222
<tr>
224-
<td>Text Recognition</td>
225-
<td>PP-OCRv4_mobile_rec<br/>PP-OCRv4_server_rec</td>
223+
<td>Text Image Unwarping</td>
224+
<td>✅</td>
225+
</tr>
226+
227+
<tr>
228+
<td>Document Image Orientation Classification</td>
229+
<td>✅</td>
230+
</tr>
231+
232+
<tr>
233+
<td rowspan="4">Table Recognition</td>
234+
<td>Layout Detection</td>
235+
<td>✅</td>
236+
</tr>
237+
238+
<tr>
239+
<td>Table Recognition</td>
240+
<td>✅</td>
226241
</tr>
227242

228243
<tr>
229-
<td rowspan="2">General OCR</td>
230244
<td>Text Detection</td>
231-
<td>PP-OCRv4_server_det<br/>PP-OCRv4_mobile_det</td>
245+
<td>✅</td>
232246
</tr>
233247

234248
<tr>
235249
<td>Text Recognition</td>
236-
<td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
250+
<td>✅</td>
237251
</tr>
238252

239253
<tr>
240-
<td rowspan="5">General Table Recognition</td>
241-
<td>Layout Detection</td>
242-
<td>PicoDet_layout_1x</td>
254+
<td>Object Detection</td>
255+
<td>Object Detection</td>
256+
<td>FasterRCNN-Swin-Tiny-FPN ❌<br>CenterNet-DLA-34 ❌ <br>CenterNet-ResNet50 ❌</td>
257+
</tr>
258+
259+
<tr>
260+
<td>Instance Segmentation</td>
261+
<td>Instance Segmentation</td>
262+
<td>Mask-RT-DETR-S ❌</td>
263+
</tr>
264+
265+
<tr>
266+
<td>Image Classification</td>
267+
<td>Image Classification</td>
268+
<td>✅</td>
269+
</tr>
270+
271+
<tr>
272+
<td>Semantic Segmentation</td>
273+
<td>Semantic Segmentation</td>
274+
<td>✅</td>
275+
</tr>
276+
277+
<tr>
278+
<td>Time Series Forecasting</td>
279+
<td>Time Series Forecasting</td>
280+
<td>❌</td>
281+
</tr>
282+
283+
<tr>
284+
<td>Time Series Anomaly Detection</td>
285+
<td>Time Series Anomaly Forecasting</td>
286+
<td>❌</td>
243287
</tr>
244288

245289
<tr>
246-
<td rowspan="2">Table Recognition</td>
247-
<td>SLANet</td>
290+
<td>Time Series Classification</td>
291+
<td>Time Series Classification</td>
292+
<td>❌</td>
248293
</tr>
249294

250295
<tr>
251-
<td>SLANet_plus</td>
296+
<td>Small Object Detection</td>
297+
<td>Small Object Detection</td>
298+
<td>✅</td>
299+
</tr>
300+
301+
<tr>
302+
<td>Multi-Label Image Classification</td>
303+
<td>Multi-Label Image Classification</td>
304+
<td>✅</td>
305+
</tr>
306+
307+
<tr>
308+
<td>Image Anomaly Detection</td>
309+
<td>Unsupervised Anomaly Detection</td>
310+
<td>✅</td>
311+
</tr>
312+
313+
<tr>
314+
<td rowspan="8">Layout Parsing</td>
315+
<td>Table Structure Recognition</td>
316+
<td>✅</td>
317+
</tr>
318+
319+
<tr>
320+
<td>Layout Region Analysis</td>
321+
<td>✅</td>
252322
</tr>
253323

254324
<tr>
255325
<td>Text Detection</td>
256-
<td>PP-OCRv4_server_det<br/>PP-OCRv4_mobile_det</td>
326+
<td>✅</td>
257327
</tr>
258328

259329
<tr>
260330
<td>Text Recognition</td>
261-
<td>PP-OCRv4_server_rec<br/>PP-OCRv4_mobile_rec<br/>ch_RepSVTR_rec<br/>ch_SVTRv2_rec</td>
331+
<td>✅</td>
332+
</tr>
333+
334+
<tr>
335+
<td>Formula Recognition</td>
336+
<td>❌</td>
262337
</tr>
263338

264339
<tr>
265-
<td rowspan="15">Document Scene Information Extraction v3</td>
266-
<td rowspan="2">Table Recognition</td>
267-
<td>SLANet</td>
340+
<td>Seal Text Detection</td>
341+
<td>✅</td>
268342
</tr>
269343

270344
<tr>
271-
<td>SLANet_plus</td>
345+
<td>Text Image Unwarping</td>
346+
<td>✅</td>
347+
</tr>
348+
349+
<tr>
350+
<td>Document Image Orientation Classification</td>
351+
<td>✅</td>
272352
</tr>
273353

274354
<tr>
355+
<td rowspan="2">Formula Recognition</td>
275356
<td>Layout Detection</td>
276-
<td>PicoDet_layout_1x</td>
357+
<td>❌</td>
277358
</tr>
278359

279360
<tr>
280-
<td rowspan="2">Text Detection</td>
281-
<td>PP-OCRv4_server_det</td>
361+
<td>Formula Recognition</td>
362+
<td>❌</td>
282363
</tr>
283364

284365
<tr>
285-
<td>PP-OCRv4_mobile_det</td>
366+
<td rowspan="3">Seal Recognition</td>
367+
<td>Layout Region Analysis</td>
368+
<td>✅</td>
286369
</tr>
287370

288371
<tr>
289-
<td rowspan="4">Text Recognition</td>
290-
<td>PP-OCRv4_server_rec</td>
372+
<td>Seal Text Detection</td>
373+
<td>✅</td>
291374
</tr>
292375

293376
<tr>
294-
<td>PP-OCRv4_mobile_rec</td>
377+
<td>Text Recognition</td>
378+
<td>✅</td>
295379
</tr>
296380

297381
<tr>
298-
<td>ch_RepSVTR_rec</td>
382+
<td rowspan="2">Image Recognition</td>
383+
<td>Subject Detection</td>
384+
<td>✅</td>
299385
</tr>
300386

301387
<tr>
302-
<td>ch_SVTRv2_rec</td>
388+
<td>Image Feature</td>
389+
<td>✅</td>
303390
</tr>
304391

305392
<tr>
306-
<td rowspan="2">Seal Text Detection</td>
307-
<td>PP-OCRv4_server_seal_det</td>
393+
<td rowspan="2">Pedestrian Attribute Recognition</td>
394+
<td>Pedestrian Detection</td>
395+
<td>❌</td>
308396
</tr>
309397

310398
<tr>
311-
<td>PP-OCRv4_mobile_seal_det</td>
399+
<td>Pedestrian Attribute Recognition</td>
400+
<td>❌</td>
312401
</tr>
313402

314403
<tr>
315-
<td>Text Image Rectification</td>
316-
<td>UVDoc</td>
404+
<td rowspan="2">Vehicle Attribute Recognition</td>
405+
<td>Vehicle Detection</td>
406+
<td>❌</td>
317407
</tr>
318408

319409
<tr>
320-
<td>Document Image Orientation Classification</td>
321-
<td>PP-LCNet_x1_0_doc_ori</td>
410+
<td>Vehicle Attribute Recognition</td>
411+
<td>❌</td>
412+
</tr>
413+
414+
<tr>
415+
<td rowspan="2">Face Recognition</td>
416+
<td>Face Detection</td>
417+
<td>✅</td>
418+
</tr>
419+
420+
<tr>
421+
<td>Face Feature</td>
422+
<td>✅</td>
322423
</tr>
323424

324425
</table>

0 commit comments

Comments
 (0)