v0.1.1

What's Changed

• fix setup by @liangxhao in #172
• fix some import path for inference by @liangxhao in #175
• update requirements by @SamitHuang in #176
• fix data_sink_mode freeze, adjust DBNet augmentation pipeline by @hadipash in #178
• fix typo by @HaoyangLee in #179
• Add group params support by @SamitHuang in #177
• update model readmes for mindir download urls by @SamitHuang in #181
• add mslite support for inference by @liangxhao in #132
• Add gradient accumulation, gradient clip, and add tests by @SamitHuang in #182
• Add mindir export for trained models and related docs, tests; Rename dbnet_r50 -> dbnet_resnet50, crnn_r34 -> crnn_resnet34 for consistency by @SamitHuang in #184
• warning bug fix by @hadipash in #188
• solve download fail bugs in some servers by @SamitHuang in #185
• fix export dbnet input shape from 640x640 to 732x1280. change crnn he… by @SamitHuang in #189
• Del gradient accumulation for potential loss unconvergence in dbnet by @SamitHuang in #192
• add SynthText dataset support by @hadipash in #193
• add logger module by @MaigeWhite in #180
• DBNet output changed in inference mode for faster speed - only binary map is output by @SamitHuang in #196
• fix requirements on imgaug by @SamitHuang in #198
• Network head output type changed to fix CoreSegment error in graph mo… by @SamitHuang in #199
• modify MLT2017_Converter to support official dataset labels by @hadipash in #200
• fix shared memory usage increasing bug and disenable drop_remainder i… by @SamitHuang in #202
• Add a data converter for SVT by @hqkate in #201
• fix eval by @SamitHuang in #205
• Improve postprocess APIs to receive more data info for processing; add batch size refinement in validation while training by @SamitHuang in #207
• Add gradient accumulation and grad clip and update readme (grad reduce after accumulate, make lr scheduling consistent) by @SamitHuang in #210
• Extend evaluator to allow reload different datasets by @SamitHuang in #211
• Datasets Conversion Support and Fixing Bugs by @wtomin in #206
• support feature extraction of mindcv backbone: resnet and mobiletnet v3 by @zhtmike in #213
• add ResNet-18 support for detection by @hadipash in #214
• add inference demo for mindir by @liangxhao in #209
• improve select layer by @SamitHuang in #218
• better error msg for empty lmdb dataset by @zhtmike in #245
• add automapping function in load_pretrain to fix load weight erorr from mindcv when the feature encoder is unfolded to extract intermediate features by @SamitHuang in #246
• add illustration for annotation format for inference by @liangxhao in #244
• add det+rec ckpt prediction pipeline by @HaoyangLee in #216
• revert det_metric to commit cec7102 because commit 837ff68 incurs bug in distributed evaluation by @SamitHuang in #249
• fix bugs in mixed precision training by @SamitHuang in #247
• add td500 dataset convert by @Songyuanwei in #248
• add ema and improve log by @SamitHuang in #251
• improve detection augmentation pipeline by @hadipash in #250
• Add pretrained ckpt loading (via local path or url) to support finetuning by @SamitHuang in #252
• update docs for predict_system by @HaoyangLee in #256
• update readme by @SamitHuang in #255
• Add Rec Seq2seq components and configure file, change all config files due to interface change by @zhtmike in #253
• use proxy when upgrading pip on modelart by @zhtmike in #259
• Update CRNN readme by @hqkate in #191
• Add eval script for benchmarking multiple datasets by @hqkate in #217
• fixed dataset null annotation bug by @Songyuanwei in #258
• Change the default value of the label indices from [1] to [1:] by @zhtmike in #265
• fix export.py to support loading either local or online ckpt by @HaoyangLee in #260
• Update DBNet ic15 performance and yaml; update crnn ic15 finetune yaml by @SamitHuang in #269
• fix list index out of range error for detection dataset by @hadipash in #270
• add DBNet++ support by @hadipash in #268
• add DBNet++ CN doc by @HaoyangLee in #273
• add ctw1500 dataset convert by @Songyuanwei in #266
• add dbnet yaml for synthtext dataset and td500 dataset by @Songyuanwei in #257
• loss averaging across multiple devices by @hadipash in #254
• Improve log, save origin yaml, and fix adan by @SamitHuang in #272
• Support downloading multi data in modelart by @zhtmike in #275
• fix the formatting error by @zhtmike in #277
• Add RARE (CRNN-seq2seq) README and support O2 training by @zhtmike in #274
• add mobilenet v3 support for text detection by @hadipash in #263
• Add checkpoint manager to save latest or top k checkpoints in history by @SamitHuang in #279
• fix amp for crnn with CTCLoss by @SamitHuang in #284
• Add loss average meter by @zhtmike in #285
• refactor inference by @liangxhao in #267
• fix errors in validate polygons (temp solution) by @SamitHuang in #286
• Support relative path of config file in ModelArt and fix bug by @zhtmike in #287
• Update readme by @SamitHuang in #288
• fix setup and some filename by @liangxhao in #291
• Update dbnet readme by @SamitHuang in #293
• Add Seq2Seq Chinese model support by @zhtmike in #289
• Add CRNN Chinese Support by @zhtmike in #298
• improve docs for chinese text dataset training by @SamitHuang in #299
• fix bug when set label_file: null by @SamitHuang in #303
• handle the softmax error form ms_2.0alpha and clean warning by @zhtmike in #304
• Update CRNN-CH config and fix readme format bug by @hqkate in #301
• fix neck Select bug in graph mode by @HaoyangLee in #307
• add DBNet++ for lite inference by @liangxhao in #305
• Add ppocr series models by @VictorHe-1 in #302
• Add a unified resize operation for detection and a resize op for recognition inference by @SamitHuang in #295
• Add SVTR Tiny model by @zhtmike in #308
• Re-organize online inferene, support more models, add demo results, update docs, add test by @SamitHuang in #311
• Add PSENet det model by @VictorHe-1 in #290
• fix the transform bug and raise the exception when return is null by @zhtmike in #313
• update readme for inference by @liangxhao in #297
• Add cpplint check to ci.yml by @jianyunchao in #314
• Unify Postprocessing APIs, update PSE Postprocess to follow, change key shape to shape_list, change arg name output_polygon to box_type for consistency, support new added models for online inferenece, improve main readme by @SamitHuang in #316
• Refactor evaluation flow by @hadipash in #309
• Fix bugs in psenet evaluation, fix typo in docs by @SamitHuang in #317
• refactor export.py to support customize the data_shape of mindir by @HaoyangLee in #310
• support non-strict checkpoint loading by @zhtmike in #320
• update model support list and inference environment setup guide by @VictorHe-1 in #319
• Fix db/db++/pse evaluation bugs and results, rescale polygons in postproc by default using shape_list; New arg parser to support changing config arg from CLI (e.g. -o eval.ckpt_load_path=db_r50.ckpt); Impr code format and guideline docs by @SamitHuang in #321
• fix the local checkpoint loading by @zhtmike in #324
• Fix modelart after new CLI change and remove redudant import by @zhtmike in #325
• add dbnet yaml for synthtext, mlt2017, td500, totaltext and ctw1500 dataset by @Songyuanwei in #276
• modify transform op output variable name to avoid mindir conversion bug by @HaoyangLee in #327
• unify data process for inference by @liangxhao in #323
• add east det model by @tonytonglt in #264
• support PSENet MindIR inference by @VictorHe-1 in #329
• fix EAST MindIR inference postprocess by @tonytonglt in #330
• update main readme for supporting EAST model; improve readme_cn of EAST; add readme_en of EAST by @tonytonglt in #331
• add ut tests for inference by @liangxhao in #332
• fix metric bugs for lower, support mindir export with model yaml config by @SamitHuang in #334
• add resume training by @Songyuanwei in #312
• fix main page docs and dbpp docs bug by @HaoyangLee in #338
• fix det inference bug when empty by @liangxhao in #335
• [feat] cpp infer with mindx and lite by @heepengpeng in #261
• PSEDiceLoss support any input shape (fix issue#333) by @VictorHe-1 in #339
• Small fixes to post-processing pipeline by @hadipash in #336
• Add SVTR Chinese.benchmark model and Update CRNN benchmark model, and others by @zhtmike in #337
• Add PP-OCR PSENet model support by @VictorHe-1 in #342
• fix readme for psenet inference by @liangxhao in #344
• fix DetBasePostprocess bug by @hadipash in #350
• Add pre-commit and lint by @jianyunchao in #346
• Update length limit of line from 120 to 160 in ci.yml by @HaoyangLee in #354
• remove pre-commit check in CI by @HaoyangLee in #356
• add some ppocr algorithm for inference by @liangxhao in #352
• update readme of EAST for MindSpore Lite inference guideline by @tonytonglt in #340
• fix bugs when inference using DBPostprocess and ScalePadImage by @VictorHe-1 in #353
• [feat] add rosetta by @heepengpeng in #357
• add new auto_scaling by @Bruce-py in #306
• Add SVTR MindIR with new input shape by @zhtmike in #345
• fix format for inference by @liangxhao in #360
• fix east for inference by @liangxhao in #361
• Improve gear strategy and fix yaml config for pp-ocr inference by @VictorHe-1 in #362
• add dbnet inference readme by @Songyuanwei in #349
• [feat] cpp infer doc by @heepengpeng in #328
• [feat] add vitstr by @heepengpeng in #366
• Add third-party model inference performance result and fix eval_rec by @VictorHe-1 in #367
• Fix static inspection issues by @jianyunchao in #365
• delete unused eval script by @liangxhao in #370
• refactor param amp_level usage when build_model, remove export.py input args.amp_level by @HaoyangLee in #351
• adapt EAST to ms2.0 by @tonytonglt in #358
• add distribute tutorials by @Songyuanwei in #371
• clean code and fix dynamic shape for svtr by @liangxhao in #372
• update what's new by @Songyuanwei in #359
• add text direction classification model (mobilenetv3_small_100) by @HaoyangLee in #322
• fix code in evaluator.py by @HaoyangLee in #374
• Add Chinese PSENet model trained on CTW1500 by @VictorHe-1 in #343
• update data_converter doc by @HaoyangLee in #375
• add sast for inference by @liangxhao in #363
• fix svtr infer by @liangxhao in #377
• Add mmocr dbnet++ and fcenet by @liangxhao in #369
• Auto-scaling converter docs by @Bruce-py in #341
• Change RecResizeImg to RecResizeNormForInfer by @VictorHe-1 in #381
• modify clspostprocess name by @HaoyangLee in #380
• fix bug in convert.py caused by flake8 check by @HaoyangLee in #379
• delete RecResizeImg from infer by @liangxhao in #382
• fix the rare postprocess error when lower is true or the image is exactly by @zhtmike in #364
• fix readme for inference by @liangxhao in #378
• change polygon preprocessing pipeline by @hadipash in #292
• remove unused demo by @liangxhao in #387
• fix infer args by @liangxhao in #384
• format inference_tutorial by @liangxhao in #391
• Fix typo and update link by @zhtmike in #388
• Update CRNN Readme by @hqkate in #383
• Add ppocr PSENet performance by @VictorHe-1 in #396
• improve EAST postprocess if detection result is empty by @tonytonglt in #397
• update version by @Songyuanwei in #402
• Update README of RARE and SVTR by @zhtmike in #399
• Re-organize readme, add two tutorials by @SamitHuang in #394
• fix format by @SamitHuang in #409
• fix infer readme by @liangxhao in #406
• [feat] add mmocr nrtr & satrn by @heepengpeng in #389
• Change rec eval resize op (RGB mode, RecResizeNormForInfer by @SamitHuang in #405
• Add configuration params description readme by @hqkate in #212
• Update readme cn by @SamitHuang in #410
• update readme cn by @SamitHuang in #413
• Update Recognition Training Doc by @zhtmike in #415
• rename inference md filename by @liangxhao in #418
• rename dataset filename by @liangxhao in #419
• update readme cn by @Songyuanwei in #414
• Update paths in yaml configuration readme to accommodate new documentation location by @hqkate in #417
• Fix docs and impr visualize by @SamitHuang in #422

New Contributors

• @Songyuanwei made their first contribution in #248
• @VictorHe-1 made their first contribution in #302
• @tonytonglt made their first contribution in #264
• @heepengpeng made their first contribution in #261
• @Bruce-py made their first contribution in #306

Full Changelog: v0.1.0...v0.1.1