933f2ea | Yi Zhu | 20 November 2020, 19:33:23 UTC | update feature extraction (#1534) | 20 November 2020, 19:33:23 UTC |
dce2f28 | Yi Zhu | 19 November 2020, 23:36:37 UTC | Support feature extraction (#1532) * feat ext * rename * format | 19 November 2020, 23:36:37 UTC |
9b97ff2 | Yi Zhu | 19 November 2020, 01:52:45 UTC | custom model for torchvideo (#1530) * add custom * lint | 19 November 2020, 01:52:45 UTC |
76a219b | Weisu Yin | 18 November 2020, 03:56:37 UTC | add torch tutorials (#1522) * add torch tutorials * i3d inference Co-authored-by: bryanzhu <yizhu59@gmail.com> | 18 November 2020, 03:56:37 UTC |
3fa9613 | Joshua Z. Zhang | 16 November 2020, 06:48:06 UTC | Improve auto tasks (#1523) * use in-memory pickle instead of disk file * add feature extractor for image classification * add tests * fix * fix lint * more unittests * fix * fix | 16 November 2020, 06:48:06 UTC |
7e7135f | Yi Zhu | 12 November 2020, 03:54:25 UTC | Add CSN model to torch video model zoo (#1517) * add ircsn * update model zoo * fix lint | 12 November 2020, 03:54:25 UTC |
d4f2893 | Kuang Haofei | 12 November 2020, 03:19:42 UTC | icnet missing background class (#1518) | 12 November 2020, 03:19:42 UTC |
9f6578e | BebDong | 11 November 2020, 23:38:35 UTC | Revise danet.py (#1507) The dropout layer should be placed before the classification layer. | 11 November 2020, 23:38:35 UTC |
0863296 | YANYI ZHANG | 11 November 2020, 18:48:37 UTC | add ir-csn-152 into torchvideo model zoo (#1515) | 11 November 2020, 18:48:37 UTC |
85deba5 | Yi Zhu | 11 November 2020, 03:26:45 UTC | update torchvideo model zoo (#1513) | 11 November 2020, 03:26:45 UTC |
57831fc | Chunhui Liu | 10 November 2020, 22:53:20 UTC | warmup scheduler for video torch (#1510) 1. refine warmup logic, now using cfg.CONFIG.TRAIN.USE_WARMUP to control open warmup or not. 2. fix bug in gluoncv/torch/utils/lr_policy.py 3. change training configs 4. change ddp_train_pytorch and ddp_train_shortonly_pytorch, This is tested on ec2 machines | 10 November 2020, 22:53:20 UTC |
a85be06 | Xinyu Li | 10 November 2020, 22:43:56 UTC | add get flops (#1509) | 10 November 2020, 22:43:56 UTC |
75aae80 | Joshua Z. Zhang | 10 November 2020, 06:27:05 UTC | Fix rcnn target generator (#1508) * fix not used rcnn target generator * fix lint * fix * fix | 10 November 2020, 06:27:05 UTC |
7e4f77a | Weisu Yin | 06 November 2020, 21:59:37 UTC | [WIP] Tinycoco (#1501) * Add minicoco * update jenkins for minicoco * fix * renamed mini to tiny * fix * fix * fix, add VOCDetectionTiny * fix * fix env * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * test * test * test * clean up Co-authored-by: Joshua Z. Zhang <cheungchih@gmail.com> | 06 November 2020, 21:59:37 UTC |
f0327d0 | Yi Zhu | 05 November 2020, 04:51:12 UTC | none to empty string (#1502) | 05 November 2020, 04:51:12 UTC |
37c41e4 | Joshua Z. Zhang | 05 November 2020, 00:41:28 UTC | fix imports (#1499) * fix imports * fix * fix image classification * fix * fix width height * fix * fix batch size * fix * fix | 05 November 2020, 00:41:28 UTC |
5c248f3 | Weisu Yin | 04 November 2020, 19:14:55 UTC | Added support for AWS Batch. Added support for docker (#1474) * Added support for AWS Batch. Added support for docker * Fixed style. Removed code in commet. Updated README to include boto3 usage * Renamed template file. Removed gluon aws id * fix readme * fix | 04 November 2020, 19:14:55 UTC |
0a178f3 | Yi Zhu | 04 November 2020, 18:37:44 UTC | fix config (#1498) | 04 November 2020, 18:37:44 UTC |
6c1a584 | Joshua Z. Zhang | 04 November 2020, 01:01:03 UTC | Fix auto detectors (#1497) * fix yolo predictor * fix predict | 04 November 2020, 01:01:03 UTC |
218007a | Weisu Yin | 03 November 2020, 23:54:42 UTC | Add torch clarification (#1495) * Add torch clarification * fix | 03 November 2020, 23:54:42 UTC |
6ff50a8 | Joshua Z. Zhang | 03 November 2020, 00:58:53 UTC | incorporate autodatasets (#1496) | 03 November 2020, 00:58:53 UTC |
2da042f | Joshua Z. Zhang | 02 November 2020, 20:58:40 UTC | Merge branch estimator into master (#1492) * [WIP] Fit api with sacred config (#1331) * config using sacred * update * update base * allow attribute access, add warning to config modification (#1348) * Faster R-CNN estimator (#1338) * move rcnn forward backward task to model zoo * revert https://github.com/dmlc/gluon-cv/pull/1249 * fix * fix * docstring * fix style * add docs * faster rcnn estimator * refactor * move dataset to init * lint * merge * disable sacred config for now * logger fix * fix fit * update full centernet example (#1349) * Autogluon Integration (#1355) * move rcnn forward backward task to model zoo * revert https://github.com/dmlc/gluon-cv/pull/1249 * fix * fix * docstring * fix style * add docs * faster rcnn estimator * refactor * move dataset to init * lint * merge * disable sacred config for now * logger fix * fix fit * autogluon integration * fix small bug. training working * lint * sacred config for faster rcnn (#1358) * move rcnn forward backward task to model zoo * revert https://github.com/dmlc/gluon-cv/pull/1249 * fix * fix * docstring * fix style * add docs * faster rcnn estimator * refactor * move dataset to init * lint * merge * disable sacred config for now * logger fix * fix fit * autogluon integration * fix small bug. training working * lint * sacred config for faster rcnn * Finish centernet fit estimator (#1359) * add voc detection pipeline * update * fix errors * Add docs for Faster R-CNN config (#1361) * move rcnn forward backward task to model zoo * revert https://github.com/dmlc/gluon-cv/pull/1249 * fix * fix * docstring * fix style * add docs * faster rcnn estimator * refactor * move dataset to init * lint * merge * disable sacred config for now * logger fix * fix fit * autogluon integration * fix small bug. training working * lint * sacred config for faster rcnn * add config docs * Estimator rcnn (#1366) * move rcnn forward backward task to model zoo * revert https://github.com/dmlc/gluon-cv/pull/1249 * fix * fix * docstring * fix style * add docs * faster rcnn estimator * refactor * move dataset to init * lint * merge * disable sacred config for now * logger fix * fix fit * autogluon integration * fix small bug. training working * lint * sacred config for faster rcnn * add config docs * move all logging into base estimator logdir * raise key error when config is not found in freezed config (#1367) * auto object detection refactor (#1371) * auto object detection refactor * change logdir and common config * centernet config change * autogluon * fix auto object detection task * add mask_rcnn estimator (#1398) * fix typo (#1378) Co-authored-by: Ubuntu <ubuntu@ip-172-31-0-100.us-west-2.compute.internal> * add ssd estimator (#1394) * add ssd estimator * modify ssd estimator * provide options to customize network structure * minor changes * minor changes * add auto detection using ssd * add auto detection using ssd * add custom model for ssd * minor changes * add tiny dataset for testing; fix errors in training auto detector * [WIP] Add estimator(yolo) (#1380) * yolo * yolo * add yolo * [chore] update name, add fit script Co-authored-by: Ubuntu <ubuntu@ip-172-31-0-100.us-west-2.compute.internal> * auto register args (#1419) * Auto detector (#1425) * auto detector * auto detector * auto detector * auto detector * auto detector * auto detector Co-authored-by: Joshua Z. Zhang <cheungchih@gmail.com> * update auto detection (#1436) * auto detector * auto detector * auto detector * auto detector * auto detector * auto detector * update auto detection * add a framework for automatic suggestion of hyperparameter search space * 1) change auto_resume default to False; 2) change input config to estimator is a pure dict * [fix] bugs for test_auto_detection (#1438) Co-authored-by: Ubuntu <ubuntu@ip-172-31-31-97.us-west-2.compute.internal> * add cls (#1381) * update auto suggest (#1443) * update auto suggest * update auto suggest * fix yolo errors (#1445) * remove dependencies on AutoGluon non-core functions (#1452) * remove dependency to autogluon non-core functions * fix errors on importing estimators * [Lint] fix pylint for estimator branch (#1451) * fix pylint * update mxnet build * remove py2 * remove py2.yml * fix jenkinsfile * fix post_nms in rcnn * fix * fix doc build * fix lint con't * add sacred * no tutorial yet * estimator prototype for save/load (#1458) * prototype for save/load * add type check * handle ctx * fix * collect * fix classmethod self * fix * pickle only init args * cast to numpy to avoid ctypes * fix get data * base estimator * [WIP] Add detailed logging information for auto estimator (#1470) * add detailed logging information for auto estimator * fix lint error * [WIP] Estimator data (#1471) * dataframe for object detection * fix pack and unpack for bboxes * update * refactor fit * fix * update pickle behavior * update * fix __all__ * Dataset as class property not module * fix centernet, add image classification dataset * fix * fix * fix logger not inited before init_network * reuse weights from known classes * add predict * fix index * format returned prediction * fix id to int * improve predict with pd.dataframe * add numpy * reset index * clean up * update image classification dataset * dataset improvements * valid url checker * setup.py improve * fix * fix import utils * add display to object detection * fix * change fit functions * add coco import * fix lint * fix lint * fix lint * fix * Estimator con't improvements (#1484) * allow ssd/faster-rcnn to take in train/val dataset * update * fix * update ssd * fix ctx * fix ctx * fix self.datasets * fix self.epoch * remove async_net * fix predict * debug predict * fix predict scores * filter out invalid predictions * fix faster_rcnn * fix * fix * fix deepcopy * fix fpn anchor generator * fix ctx * fix frcnn predict * fix * fix skipping logic * fix yolo3 * fix import * fix rename yoloestimator * fix import * fix yolo3 train * fix * fix * fix * fix * fix * fix * fix * fix ctx * fix trainer * fix num_class < 5 for topk * fix unpickable batch_fn * fix print * add predict * fix cls predict * fix cls predict * fix cls predict * fix cls predict * improve auto fit * improve auto fit * fix * fix * fix * fix * fix * debug * fix * fix * fix * fix * fix * fix * fix reporter pickle * change epochs to smaller * update image cls search space * fix * fix * fix * fix * fix * fix * fix * replace sacred with autocfg * fix * fix tuple type * fix * fix * fix * clean up * remove sacred * fix import * fix import * add types * fix * fix * defaults for object detection * fix * fix * update image classification * change lr * update * Fix pylint * Fix pylint * fit summary * pprint summary * fix * update * fix single trial * fix sample_config * fix sample_config * fix sample_config * fix lint * fix lint * adjust batch size * fix * stacktrace * fix * fix traceback * fix traceback * fix train evaluation * default networks * default networks * improves * fix * fix lint Co-authored-by: tmwangcas <tmwang428@outlook.com> * update script to master * add unittests for auto * update conda * pin autogluon * fix test * fix * fix ssd/yolo * fix * update defaults * fix kv_store being overwriten * fix rcnn batch size Co-authored-by: Jerry Zhang <zhangz6@cs.washington.edu> Co-authored-by: Tianming Wang <tmwang428@outlook.com> Co-authored-by: Chongruo Wu <chongruo@gmail.com> Co-authored-by: Ubuntu <ubuntu@ip-172-31-0-100.us-west-2.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-31-97.us-west-2.compute.internal> | 02 November 2020, 20:58:40 UTC |
60d82b3 | Yi Zhu | 01 November 2020, 23:02:01 UTC | Add doc to default config (#1491) | 01 November 2020, 23:02:01 UTC |
177204e | Yi Zhu | 01 November 2020, 05:50:01 UTC | Add more model configs (#1490) | 01 November 2020, 05:50:01 UTC |
679acab | Yi Zhu | 01 November 2020, 02:25:40 UTC | [WIP] Test Torch installation and model zoo (#1489) * new branch * fix dataset * Added torch docs * change config and add torch model zoo prototype * change config and model zoo table * add warmup cosine lr schedule * upgrade pip * lint * trigger ci * reformat table * fix toc * Reorganize structure. Fix reference * Reorganize reference * fix Co-authored-by: yinweisu <wyin@ucdavis.edu> | 01 November 2020, 02:25:40 UTC |
213c65a | Yi Zhu | 30 October 2020, 03:17:45 UTC | [WIP] Add video action recognition models in PyTorch (#1485) * add video action recognition models in pytorch * fix lint1 * Modified Jenkinsfile to support pytorch * pylint fix * fix lint model zoo * lint fix * pylint 4 * pylint 5 * lint 6 * disable gcvdataset lint * Fix cv2 pip install * add videotorch unittest * Add model zoo unit test to jenkins pipeline * jenkins fix * fix import * fix lint * fix * fix tuple * reference * setup.py Co-authored-by: yinweisu <wyin@ucdavis.edu> Co-authored-by: Joshua Z. Zhang <cheungchih@gmail.com> | 30 October 2020, 03:17:45 UTC |
0e97aaa | Kuang Haofei | 15 October 2020, 03:52:32 UTC | Fix monodepth2 issue (#1472) * init repo * fix lr decay bug; fix posenet hybridiz bug * fix logdir bug * remove Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 15 October 2020, 03:52:32 UTC |
f9a8a28 | Joshua Z. Zhang | 06 October 2020, 20:21:02 UTC | Fix sphinx gallery (#1457) * fix extension * ignore demo failure * fix * fix * fix * fix tutorials * fix * fix path * fix tutorials * fix tutorials | 06 October 2020, 20:21:02 UTC |
4a2e2ae | Weisu Yin | 30 September 2020, 20:19:33 UTC | refactored table in csv form for better readability and organization (#1465) * refactored table in csv form for better readability and organization * Added table auto-resize. Updated table column width ratio | 30 September 2020, 20:19:33 UTC |
9eeeb17 | Joshua Z. Zhang | 29 September 2020, 19:49:21 UTC | Add Deeplab resnest200 ade pretrained weights (#1456) * add pretrained weights deeplab resnest200 ade * add unittest * add numbers | 29 September 2020, 19:49:21 UTC |
ea22187 | Joshua Z. Zhang | 29 September 2020, 05:17:05 UTC | fix install tab (#1463) | 29 September 2020, 05:17:05 UTC |
c109792 | Kuang Haofei | 25 September 2020, 21:11:19 UTC | Fix monodepth2 tutorials (#1459) * init * comments dataset part Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 25 September 2020, 21:11:19 UTC |
cf767a1 | Xueqing Deng | 17 September 2020, 02:27:47 UTC | StyleGAN training (#1446) * scripts/segmentation/train.py * gluoncv/loss.py * attention.py * danet.py * fix bug * fix bug * add stylegan * fix demo name * Delete demo.py * fix debug * fix bug * fix debug * add README * stylegan: README * Add sample images * fix README * fix README * add description * fix README * fix final * fix README * add training * add training * stylegan: add training * stylegan: add prepare data * stylegan: modity README * stylegan: add training sample image * stylegan: fix README * delete image * fix README * add image * fix README * stylegan: fix minor changes * stylegan:fix minor changes Co-authored-by: Yi Zhu <yizhu59@gmail.com> | 17 September 2020, 02:27:47 UTC |
10970ae | Kuang Haofei | 10 September 2020, 06:24:19 UTC | Monodepth2 video demo (#1442) * init video demo * add basic prediction pipline * add video saving & pred results saving * add args; fix disp2depth bug * code ready; init tutorial * rename demo.py * add monodepth2 videos demo; fix bugs * fix bug & grammar error * fix bugs * fix bugs * fix typo Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 10 September 2020, 06:24:19 UTC |
3c59fba | BebDong | 09 September 2020, 22:14:04 UTC | Update deeplabv3b_plus.py (#1441) * Update deeplabv3b_plus.py add the 'evaluate' function to keep consistency with MultiEvalModel and SegBaseModel defined in segbase.py | 09 September 2020, 22:14:04 UTC |
65db073 | Chaitanya Prakash Bapat | 07 September 2020, 21:52:04 UTC | add resnext, resnest, mobilenet, squeezenet, densenet to API reference (#1430) * add resnext, resnest, mobilenet, squeezenet, densenet * import resne*t | 07 September 2020, 21:52:04 UTC |
b4af720 | Kuang Haofei | 05 September 2020, 05:05:41 UTC | Monodepth2 fix getmodel (#1440) * fix get_model bugs (mono+stereo) * update model * unified model naming Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 05 September 2020, 05:05:41 UTC |
e9f2ec1 | Kuang Haofei | 03 September 2020, 16:28:35 UTC | Monodepth2 tutorials (#1435) * init * add mono mode to train monodepth2 tutorials; add posenet tutorials * fix build bugs; add posenet model zoo * fix bugs * fix bugs * fix bugs and grammatical errors * fix bugs * fix typo * test Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 03 September 2020, 16:28:35 UTC |
1c88c73 | Yi Zhu | 02 September 2020, 18:15:50 UTC | fix conflict between kitti utils and mxnet version (#1432) * fix conflict * move amp inside | 02 September 2020, 18:15:50 UTC |
6337577 | Yi Zhu | 01 September 2020, 04:57:26 UTC | update monodepth2 model zoo (#1431) * update model zoo * remove linetoolong * change table | 01 September 2020, 04:57:26 UTC |
330bcb1 | Kuang Haofei | 31 August 2020, 05:54:25 UTC | Monodepth2 mono (#1428) * init pose net * fix bugs, add posenet, add eval_pose * fix bugs * finish posenet test(use transfered weights from pytorch) * fix bugs (remove unnecessary arguments) * mono training: posene module * save model part: add posenet * fix bugs * add posenet: combine encoder and decoder * add name_scope to split depthnet and posenet * fix bugs * add resnet pretrained model with multiple inputs * fix bugs: in-place error * fix bugs * fix bugs * fix bugs * fix bugs * fix bugs; record inference time of depth model * update * fix test bugs * mono training debug * fix bugs * fix mono training bugs * update model zoo * fix bugs * small change * add posenet to model_zoo; add comments * fix bugs * fix bugs * fix bugs * fix bugs * fix sanity check * fix coding style * fix sanity check * fix unit test bug Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 31 August 2020, 05:54:25 UTC |
dcac2d0 | Joshua Z. Zhang | 25 August 2020, 18:17:02 UTC | update readme (#1426) | 25 August 2020, 18:17:02 UTC |
e351306 | Karthikeyan Singaravelan | 14 August 2020, 01:28:18 UTC | Fix syntax warning over comparison of literals using is. (#1376) | 14 August 2020, 01:28:18 UTC |
ad9a9e3 | chinakook | 14 August 2020, 01:26:10 UTC | Fix HRNet bottleneck stride schema (#1383) * Fix HRNet bottleneck stride schema After this fix, the result is always same to the torch original implementation in every forward pass. There were sometimes different before. The params has no need to update. * CachedOp on GPU may be fail with add change it to broadcast_add to solve the problem even. I think it's a bug with _FusedOp with GPU because CPU is OK. https://github.com/apache/incubator-mxnet/issues/18624 | 14 August 2020, 01:26:10 UTC |
8f58c26 | Joshua Z. Zhang | 11 August 2020, 22:06:25 UTC | bump up to 0.9 pre (#1412) * bump up to 0.9 pre * fix nightly build mxnet | 11 August 2020, 22:06:25 UTC |
1e90f7e | Neutron3529 | 10 August 2020, 00:44:22 UTC | fix both document and a bug for RandomCrop (#1389) * fix both document and a bug for RandomCrop `RandomCrop` pad first and then crop, not what is said in the document or even CIFAR tutorials. further, an error occurs with the default `pad=None` ``` >>> for i in train_data:break ... multiprocessing.pool.RemoteTraceback: """ Traceback (most recent call last): File "/usr/lib/python3.8/multiprocessing/pool.py", line 125, in worker result = (True, func(*args, **kwds)) File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/data/dataloader.py", line 450, in _worker_fn batch = batchify_fn([_worker_dataset[i] for i in samples]) File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/data/dataloader.py", line 450, in <listcomp> batch = batchify_fn([_worker_dataset[i] for i in samples]) File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/data/dataset.py", line 219, in __getitem__ return self._fn(*item) File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/data/dataset.py", line 230, in __call__ return (self._fn(x),) + args File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/block.py", line 693, in __call__ out = self.forward(*args) File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/nn/basic_layers.py", line 55, in forward x = block(x) File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/block.py", line 693, in __call__ out = self.forward(*args) File "/home/neutron/.local/lib/python3.8/site-packages/gluoncv/data/transforms/block.py", line 75, in forward return image.random_crop(nd.array(x_pad), *self._args)[0] UnboundLocalError: local variable 'x_pad' referenced before assignment """ The above exception was the direct cause of the following exception: Traceback (most recent call last): File "<stdin>", line 1, in <module> File "/home/neutron/.local/lib/python3.8/site-packages/mxnet/gluon/data/dataloader.py", line 505, in __next__ batch = pickle.loads(ret.get(self._timeout)) File "/usr/lib/python3.8/multiprocessing/pool.py", line 771, in get raise self._value UnboundLocalError: local variable 'x_pad' referenced before assignment ``` This PR is intend to fix both the document and the BUG which caused `pad` cannot be optional. * make pylint happy. make pylint happy. * happy-2 happy-2 * remove monkey patch I just think monkey patch may goes faster than the useless switch in the forward step * make checkers happy | 10 August 2020, 00:44:22 UTC |
481019b | Yi Zhu | 07 August 2020, 19:35:33 UTC | Fastscnn improve (#1407) * add new fastscnn model * pip sanity check * change python | 07 August 2020, 19:35:33 UTC |
c73116d | Yuxin Tian | 06 August 2020, 19:17:36 UTC | modify bn (#1406) modify fastscnn with better performance | 06 August 2020, 19:17:36 UTC |
6d87315 | Yi Zhu | 05 August 2020, 05:36:29 UTC | Add depth to readme (#1405) * add depth to readme * add png | 05 August 2020, 05:36:29 UTC |
a0d2486 | Karan Jariwala | 05 August 2020, 02:22:28 UTC | Fixed amp parameter that required in class ForwardBackwardTask (#1404) * Fixed amp parameter that required in class ForwardBackwardTask * Removed unnecessary variable | 05 August 2020, 02:22:28 UTC |
4dde00b | Yi Zhu | 04 August 2020, 21:40:37 UTC | Add doc for stylegan (#1403) * add doc * style | 04 August 2020, 21:40:37 UTC |
2d19e5e | Xueqing Deng | 04 August 2020, 17:55:35 UTC | StyleGAN (#1395) * scripts/segmentation/train.py * gluoncv/loss.py * attention.py * danet.py * fix bug * fix bug * add stylegan * fix demo name * Delete demo.py * fix debug * fix bug * fix debug * add README * stylegan: README * Add sample images * fix README * fix README * add description * fix README * fix final * fix README | 04 August 2020, 17:55:35 UTC |
b9c0683 | Joshua Z. Zhang | 04 August 2020, 00:22:34 UTC | [CI] deprecate python2 (#1399) * deprecate python2 finally * remove yml | 04 August 2020, 00:22:34 UTC |
4c60fef | Kuang Haofei | 02 August 2020, 00:49:37 UTC | Monodepth2 tutorials (#1388) * init * update monodepth2 demo * update dataset path * fix bug * fix bug * fix path bug * train_monodepth2 init, add monodepth2 to model_zoo __ini__.py * fix kitti bugs * kitti rearrangement * fix bugs * monodepth2_tutorials test dataloader * fix bugs * submit train_monodepth2 tutorials * fix typo * fix sanity check * fix bugs * fix bugs * update pr * fix bugs * fix typo * fix bugs * fix bugs * fix bugs * add kitti preparation, fix bugs * fix bugs Co-authored-by: Kuang <haofeik@f8ffc22b1e09.ant.amazon.com> | 02 August 2020, 00:49:37 UTC |
4d8f5c7 | Joshua Z. Zhang | 30 July 2020, 04:02:12 UTC | fix root for backbones in Deeplab models (#1385) * fix root for backbones * fix root * remove root in head | 30 July 2020, 04:02:12 UTC |
1c41c89 | Yi Zhu | 21 July 2020, 00:25:28 UTC | Add depth model zoo and tutorial (template) (#1379) * add depth model zoo * test | 21 July 2020, 00:25:28 UTC |
a860b0e | YoungChan | 20 July 2020, 00:21:51 UTC | Object tracking data (#1334) * tracking dataloader * fix pylint * fix pylint * pylint * pylint * pylint * adjust function position * add try_import_colorama and arguments,and fix subDataset and Dataset description * pylint * pylint * pylint * bug fixed * add train siamron tutorial * fix tutorials * add single object tracking data * pylint * fix EOF * fix dataset path * fix dataset style Co-authored-by: Ubuntu <ubuntu@ip-172-31-7-157.us-east-2.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-22-213.us-east-2.compute.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-73-46.ec2.internal> Co-authored-by: Ubuntu <ubuntu@ip-172-31-76-51.ec2.internal> | 20 July 2020, 00:21:51 UTC |
e071f8b | Kuang Haofei | 19 July 2020, 02:33:57 UTC | Monodepth2 (#1360) * init depth * kitti dataset * add dict_batchify_fn * depth decoder * test with transfered weights * multi-GPUs test * train init * train dataloader * fix bugs * visulization * trainer init * image reconstruction * train loss * training update * train pipeline: first version * train * monodepthv2 train stereo * record train log * fix bugs * fix bugs * fix bugs * fixed bugs * init * fix bugs * fix bugs * fix bugs * update code style to gluoncv style * fix bugs * fixed sanity check * resolve comments * fix sanity check * fix module missing * fixed CI bug (No skimage module) * fix sanity check * fix CI bug * fix sanity check * fix bug () * add hybridize mode, change best model criterion (delta_1) * fix sanity check * fix sanity check * fix relative import bug, add hybridize argument * fix typo, add hybridize choice in test.py * add resume method in train.py * fix bug Co-authored-by: Kuang <haofeik@a483e7462c67.ant.amazon.com> | 19 July 2020, 02:33:57 UTC |
20a2ed3 | David | 16 July 2020, 22:53:58 UTC | fixed issue #1363 (#1372) fix issue #1363 | 16 July 2020, 22:53:58 UTC |
d939a6f | Joshua Z. Zhang | 14 July 2020, 22:53:15 UTC | [CI] separate tests to reduce memory (#1369) * separate tests * reuse common * fix | 14 July 2020, 22:53:15 UTC |
fa5e2e4 | Karan Sindwani | 12 July 2020, 19:09:31 UTC | UCF101 data prep comment added (#1365) | 12 July 2020, 19:09:31 UTC |
b64ecca | Joshua Z. Zhang | 07 July 2020, 21:26:57 UTC | [Website] Guide for contributing new algo (#1354) * contribute new algo * fix syntax * update | 07 July 2020, 21:26:57 UTC |
04baf39 | Xinyu Chen | 25 June 2020, 19:32:52 UTC | enable ssd-resnet34-v1b (#1352) * add definitions * add ssd-resnet34v1b to modelzoo * fix lint * fix lint * add docstring * add licsence file * update coco model * fix import error * fix duplicate args Co-authored-by: Joshua Z. Zhang <cheungchih@gmail.com> | 25 June 2020, 19:32:52 UTC |
766c67b | Manu Seth | 18 June 2020, 20:19:45 UTC | add jetson object detection tutorial (#1346) * add jetson object detection tutorial * fix line separation for code blocks | 18 June 2020, 20:19:45 UTC |
461289d | Joshua Z. Zhang | 14 June 2020, 21:16:29 UTC | reduce memory by disable multiprocessing (#1343) | 14 June 2020, 21:16:29 UTC |
ac54c57 | Yi Zhu | 10 June 2020, 16:50:43 UTC | Improve video train.py (#1339) * add train_only * minor | 10 June 2020, 16:50:43 UTC |
7a402c1 | Joshua Z. Zhang | 08 June 2020, 17:03:12 UTC | fix relay export version error (#1335) * fix relay export version error * fix lint | 08 June 2020, 17:03:12 UTC |
c9037ce | chinakook | 29 May 2020, 01:13:11 UTC | fix hrnet relu layer (#1312) | 29 May 2020, 01:13:11 UTC |
fb1b89c | Joshua Z. Zhang | 26 May 2020, 18:19:31 UTC | update pwc badges (#1320) | 26 May 2020, 18:19:31 UTC |
921a5d4 | chinakook | 26 May 2020, 07:40:21 UTC | Fix PAM and CAM (#1317) DANet cannot be hybridized. So fix it. | 26 May 2020, 07:40:21 UTC |
8076ecb | Chongruo Wu | 26 May 2020, 06:06:32 UTC | fix a typo in docs #1301 (#1302) | 26 May 2020, 06:06:32 UTC |
2b6f382 | Joshua Z. Zhang | 21 May 2020, 23:32:17 UTC | Pin mxnet version in response to mx.metric reorg (#1310) * mx.metric * pin version * fix lint * reduce parallel test iter/bs | 21 May 2020, 23:32:17 UTC |
ba7052d | Drogba78 | 21 May 2020, 18:28:34 UTC | fix problem when accumulate > 1 (#1313) | 21 May 2020, 18:28:34 UTC |
3c4150a | Joshua Z. Zhang | 19 May 2020, 00:30:00 UTC | fix nightly install url (#1309) | 19 May 2020, 00:30:00 UTC |
48d171c | Joshua Z. Zhang | 18 May 2020, 21:41:05 UTC | add mxnet 2.0 backward compatibility (#1308) * add mxnet 2.0 backward compatibility * fix lint * fix cyclic import in utils module * fix lint | 18 May 2020, 21:41:05 UTC |
c058147 | Joshua Z. Zhang | 18 May 2020, 20:21:38 UTC | [WIP] Tvm exporter (#673) * init tvm export * add tvm exporter * test * clean up * add test * update * replace nnvm with relay * fix lint | 18 May 2020, 20:21:38 UTC |
2ab67a7 | Joshua Z. Zhang | 12 May 2020, 22:06:30 UTC | fix lint (#1303) * fix lint * fix doc build | 12 May 2020, 22:06:30 UTC |
623cd98 | Laurent Thomas | 11 May 2020, 19:12:52 UTC | Complete doc for SSDLoss method (#1228) * Complete doc for forward method of SSDloss * rename "expected" to "ground-truth" | 11 May 2020, 19:12:52 UTC |
a4367a5 | tmyapple | 11 May 2020, 18:12:17 UTC | Visdrone dataset (#1267) * * Add VisDrone-2019-DET dataset * * fix merge * * fix * * Fix CI * * fix * * Fix lint Co-authored-by: Tamir Tapuhi <tamirt@hlo-gpu041.qb.hailotech> Co-authored-by: Tamir Tapuhi <tamirt@hlo-gpu042.qb.hailotech> | 11 May 2020, 18:12:17 UTC |
7a74537 | Xiaolin Wang | 10 May 2020, 23:20:05 UTC | fix typo (#1291) | 10 May 2020, 23:20:05 UTC |
e043d56 | Jerry Zhang | 06 May 2020, 07:43:18 UTC | move rcnn forward backward task to model zoo (#1288) * move rcnn forward backward task to model zoo * revert https://github.com/dmlc/gluon-cv/pull/1249 * fix * fix * docstring * fix style * add docs | 06 May 2020, 07:43:18 UTC |
2716ec9 | Nick Lee | 03 May 2020, 21:28:51 UTC | Fix market1501 dataset (#1227) | 03 May 2020, 21:28:51 UTC |
c5149f5 | Yi Zhu | 03 May 2020, 19:02:28 UTC | model zoo for danet and fastscnn (#1284) * add model store * code style * fix lint * revert back | 03 May 2020, 19:02:28 UTC |
985bbfb | Joshua Z. Zhang | 03 May 2020, 04:39:10 UTC | try to fix pylint (#1285) * try to fix pylint * fix | 03 May 2020, 04:39:10 UTC |
7c1bb35 | Yuxin Tian | 01 May 2020, 23:49:37 UTC | Fast-SCNN (#1278) * test * Add Fast-SCNN model * add comments * Update README.md * add syncbn * fix README.md * add get_model fucntion * bug fixed * fix bug when test with model-zoo * bug fixed * py2 test * py2 test * py2 test * py2 test Co-authored-by: Yuxin Tian <yuxin@Yuxins-MacBook-Pro.local> | 01 May 2020, 23:49:37 UTC |
3ea944a | Xueqing Deng | 01 May 2020, 19:34:17 UTC | DANet (#1280) * scripts/segmentation/train.py * scripts/segmentation/train.py * gluoncv/loss.py * gluoncv/model_zoo/segbase.py * gluoncv/loss.py * gluoncv/model_zoo/attention.py * gluoncv/model_zoo/danet.py * gluoncv/model_zoo/model_zoo.py * scripts/segmentation/train.py * attention.py * danet.py * danet.py * danet.py * loss.py * attention.py * danet.py * danet.py * gluoncv/loss.py * gluoncv/model_zoo/danet.py * gluoncv/loss.py * gluoncv/loss.py * gluoncv/model_zoo/attention.py * gluoncv/model_zoo/danet.py * gluoncv/model_zoo/model_zoo.py * scripts/segmentation/train.py * gluoncv/model_zoo/danet.py * gluoncv/model_zoo/model_store.py * gluoncv/model_zoo/danet.py * tests/unittests/test_utils_export.py * gluoncv/model_zoo/model_store.py * tests/unittests/test_utils_export.py | 01 May 2020, 19:34:17 UTC |
47c6377 | Joshua Z. Zhang | 01 May 2020, 17:13:04 UTC | SRGAN allow hybridization (#1281) * allow hybridization * pylint | 01 May 2020, 17:13:04 UTC |
f4b44e9 | Joshua Z. Zhang | 27 April 2020, 01:07:01 UTC | update benchmark urls (#1276) | 27 April 2020, 01:07:01 UTC |
c3dd20d | Jerry Zhang | 26 April 2020, 01:56:08 UTC | add resnest 14 and faster rcnn resnest269 (#1272) * add resnest 14 and 26 * fix * rm * rm * style * fix comment | 26 April 2020, 01:56:08 UTC |
773034c | Joshua Z. Zhang | 25 April 2020, 22:04:51 UTC | [New models] Add Center net mobile versions (#1142) * add mobilenetv3 center_net * fix import scipy * fix duc names * add pretrained weights for center_net_mobilenetv3 * fix whitespace * fix lint * reduce test mem | 25 April 2020, 22:04:51 UTC |
db8559f | chinakook | 25 April 2020, 02:14:01 UTC | Fix a logical error of mask rcnn training script (#1249) * Fix a logical error of mask rcnn training script After this fix, the training memory will be steady. If given a very big epoch(often with small dataset), this error will eat all GPU memory as epoch grows. The script of faster rcnn training has this problem too. I‘ll fix it later when I get some tests passed. * fix hybridize | 25 April 2020, 02:14:01 UTC |
d8601c9 | Hang Zhang | 24 April 2020, 23:11:43 UTC | Add DeepLab-ResNeSt 269 (#1271) * add deeplab-resnest-269 * add badg | 24 April 2020, 23:11:43 UTC |
8dceceb | Yi Zhu | 23 April 2020, 23:48:48 UTC | Augmentation comparison for video action recognition (#1266) * diff aug * add augv2 * add more aug * done all aug style * fix comments * tupo | 23 April 2020, 23:48:48 UTC |
447c8e8 | Jerry Zhang | 23 April 2020, 01:07:13 UTC | Add ResNeSt-26 and Fix Horovod ImageNet training (#1263) * add resnest26 fix imagenet horovod training bug fix rcnn custom model syncbn bug * fix splat fix splat fix splat fix splat * add resnest 26 | 23 April 2020, 01:07:13 UTC |
acf32fc | Joshua Z. Zhang | 22 April 2020, 06:17:25 UTC | bump up to 0.8 for pre-release (#1265) | 22 April 2020, 06:17:25 UTC |
2a1b621 | chinakook | 22 April 2020, 06:17:12 UTC | add hrnet18 and hrnet64\n add hrnet pretrained models (#1243) * add hrnet18 and hrnet64\n add hrnet pretrained models * add hashs to model_store Co-authored-by: Joshua Z. Zhang <cheungchih@gmail.com> | 22 April 2020, 06:17:12 UTC |
984039a | tmyapple | 21 April 2020, 18:25:00 UTC | * Support ssdlite (#1252) * * Support slim mobilenet v1 model - with only 6.7M weights- comparable to TF OD API model * * Support ssdlite * * fix duplicate line * * Fix duplicate line * * Fix ssd anchors order. return the additional aspect ratio to be as before * * Refactor - LiteAnchorGenerator corresponding to lighter ssd version. * Use SSDAnchorGenerator as default * * Fix * * Fix - remove is_lite argument * * Fix merge * * Fix * * Fix missing parenthesis * * Fix lint * * Remove trailing whitespaces Co-authored-by: Tamir Tapuhi <tamirt@hlo-gpu041.qb.hailotech> | 21 April 2020, 18:25:00 UTC |
18f8ab5 | Jerry Zhang | 17 April 2020, 22:49:11 UTC | add ResNeSt to Faster R-CNN (#1259) * add ResNeSt to Faster R-CNN add custom voc dataset * fix style * fix style * trigger ci * add docs * docs update * add custom voc dataset * small fix | 17 April 2020, 22:49:11 UTC |
cb07ee2 | Hang Zhang | 16 April 2020, 22:44:36 UTC | Add ResNeSt Segmentation Code (#1254) * add resnest segmentation code * add warmup for segmentation * fix typo * add pretrained and fix dilation * pretrained as args * update sha1 * model zoo page | 16 April 2020, 22:44:36 UTC |
f40e731 | Hang Zhang | 07 April 2020, 02:29:16 UTC | add ResNeSt model (#1247) | 07 April 2020, 02:29:16 UTC |