Tags: justinokamoto/gluon-cv
Tags
Github Actions for CI (dmlc#1541) * [WIP] Github Actions (dmlc#1) * incorporate autodatasets (dmlc#1496) * Add torch clarification (dmlc#1495) * Add torch clarification * fix * Fix auto detectors (dmlc#1497) * fix yolo predictor * fix predict * fix config (dmlc#1498) * Added support for AWS Batch. Added support for docker (dmlc#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 * fix imports (dmlc#1499) * fix imports * fix * fix image classification * fix * fix width height * fix * fix batch size * fix * fix * none to empty string (dmlc#1502) * [WIP] Tinycoco (dmlc#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 <[email protected]> * Fix rcnn target generator (dmlc#1508) * fix not used rcnn target generator * fix lint * fix * fix * add get flops (dmlc#1509) * warmup scheduler for video torch (dmlc#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 * update torchvideo model zoo (dmlc#1513) * add ir-csn-152 into torchvideo model zoo (dmlc#1515) * Revise danet.py (dmlc#1507) The dropout layer should be placed before the classification layer. * icnet missing background class (dmlc#1518) * Add CSN model to torch video model zoo (dmlc#1517) * add ircsn * update model zoo * fix lint * Improve auto tasks (dmlc#1523) * use in-memory pickle instead of disk file * add feature extractor for image classification * add tests * fix * fix lint * more unittests * fix * fix * Added github action and workflow for sanity check * Removed container and actions. * Added unit test * Added build docs * Fix * Fix * Fix * Fix * Test * test * Update unit test * fix * fix * fix * fix * fix * fix * fix * subclass coco * fix * fix * fix * fix * rebase conflict * fix rebase * fix * fix * add aws authentication * add aws authentication * test * test * test * test * test * fix log * test * test * test * test * test * test * fix * rebase * add tiny motorbike * fix * model zoo * test * fix docker * parallel jobs * parallel jobs * fix * add torch * add torch * fix * fix * fix * full test * full test * test build docs * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * test branch * test branch * fix * test * test * add comment Co-authored-by: Joshua Z. Zhang <[email protected]> Co-authored-by: Yi Zhu <[email protected]> Co-authored-by: Xinyu Li <[email protected]> Co-authored-by: Chunhui Liu <[email protected]> Co-authored-by: YANYI ZHANG <[email protected]> Co-authored-by: BebDong <[email protected]> Co-authored-by: Kuang Haofei <[email protected]> * [WIP] Test PR (dmlc#3) * Added github action and workflow for sanity check * Removed container and actions. * Added unit test * Added build docs * Fix * Fix * Fix * Fix * Test * test * Update unit test * fix * fix * fix * fix * fix * fix * fix * subclass coco * fix * fix * fix * fix * rebase conflict * fix rebase * fix * fix * add aws authentication * add aws authentication * test * test * test * test * test * fix log * test * test * test * test * test * test * fix * rebase * add tiny motorbike * fix * model zoo * test * fix docker * parallel jobs * parallel jobs * fix * add torch * add torch * fix * fix * fix * full test * full test * test build docs * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * test branch * test branch * fix * test * test * add comment * test * full test * full test * full test * test (dmlc#5) * test * fix * change to 12x * test comments * change to pr_target * [WIP] Full Test (dmlc#6) * full test * test model zoo * test model zoo * full test * full test * add auto * add gpu_test.sh * test efs modelzoo * test efs modelzoo * test efs modelzoo * test without auto * test repo name * test repo name * test repo name * test repo name * test sharemem * full test (dmlc#8) * [WIP] Github Actions (dmlc#1) * incorporate autodatasets (dmlc#1496) * Add torch clarification (dmlc#1495) * Add torch clarification * fix * Fix auto detectors (dmlc#1497) * fix yolo predictor * fix predict * fix config (dmlc#1498) * Added support for AWS Batch. Added support for docker (dmlc#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 * fix imports (dmlc#1499) * fix imports * fix * fix image classification * fix * fix width height * fix * fix batch size * fix * fix * none to empty string (dmlc#1502) * [WIP] Tinycoco (dmlc#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 <[email protected]> * Fix rcnn target generator (dmlc#1508) * fix not used rcnn target generator * fix lint * fix * fix * add get flops (dmlc#1509) * warmup scheduler for video torch (dmlc#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 * update torchvideo model zoo (dmlc#1513) * add ir-csn-152 into torchvideo model zoo (dmlc#1515) * Revise danet.py (dmlc#1507) The dropout layer should be placed before the classification layer. * icnet missing background class (dmlc#1518) * Add CSN model to torch video model zoo (dmlc#1517) * add ircsn * update model zoo * fix lint * Improve auto tasks (dmlc#1523) * use in-memory pickle instead of disk file * add feature extractor for image classification * add tests * fix * fix lint * more unittests * fix * fix * Added github action and workflow for sanity check * Removed container and actions. * Added unit test * Added build docs * Fix * Fix * Fix * Fix * Test * test * Update unit test * fix * fix * fix * fix * fix * fix * fix * subclass coco * fix * fix * fix * fix * rebase conflict * fix rebase * fix * fix * add aws authentication * add aws authentication * test * test * test * test * test * fix log * test * test * test * test * test * test * fix * rebase * add tiny motorbike * fix * model zoo * test * fix docker * parallel jobs * parallel jobs * fix * add torch * add torch * fix * fix * fix * full test * full test * test build docs * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * test branch * test branch * fix * test * test * add comment Co-authored-by: Joshua Z. Zhang <[email protected]> Co-authored-by: Yi Zhu <[email protected]> Co-authored-by: Xinyu Li <[email protected]> Co-authored-by: Chunhui Liu <[email protected]> Co-authored-by: YANYI ZHANG <[email protected]> Co-authored-by: BebDong <[email protected]> Co-authored-by: Kuang Haofei <[email protected]> * [WIP] Test PR (dmlc#3) * Added github action and workflow for sanity check * Removed container and actions. * Added unit test * Added build docs * Fix * Fix * Fix * Fix * Test * test * Update unit test * fix * fix * fix * fix * fix * fix * fix * subclass coco * fix * fix * fix * fix * rebase conflict * fix rebase * fix * fix * add aws authentication * add aws authentication * test * test * test * test * test * fix log * test * test * test * test * test * test * fix * rebase * add tiny motorbike * fix * model zoo * test * fix docker * parallel jobs * parallel jobs * fix * add torch * add torch * fix * fix * fix * full test * full test * test build docs * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * fix * test branch * test branch * fix * test * test * add comment * test * full test * full test * full test * test (dmlc#5) * test * fix * change to 12x * test comments * change to pr_target * [WIP] Full Test (dmlc#6) * full test * test model zoo * test model zoo * full test * full test * add auto * add gpu_test.sh * test efs modelzoo * test efs modelzoo * test efs modelzoo * test without auto * test repo name * test repo name * test repo name * test repo name * test sharemem * test pr only on yinweisu * test pr only on yinweisu * update repo name * test pr only on yinweisu (dmlc#9) * full test on pr only yinweisu (dmlc#10) * ready to pr * fix * change doc env name * add torch to env * add yacs to env * fix path Co-authored-by: Joshua Z. Zhang <[email protected]> Co-authored-by: Yi Zhu <[email protected]> Co-authored-by: Xinyu Li <[email protected]> Co-authored-by: Chunhui Liu <[email protected]> Co-authored-by: YANYI ZHANG <[email protected]> Co-authored-by: BebDong <[email protected]> Co-authored-by: Kuang Haofei <[email protected]>
fix both document and a bug for RandomCrop (dmlc#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
metrics for pre-trained FPN RCNN (dmlc#693) * number of gpus * syncbn * pylint * resnetv1c * merge * indent * unitest * trigger * norm args * indent * resnet v1d +0.5% * style * update docs * fix args * trigger build * add test * resolve conflict * Add FPN model * Add FPN train scripts * Fix FPN error, Stay tuned Training on VOC is still going on, I will report the result and log later. * Revert "Sync from dmlc/master" * Revert "Revert "Sync from dmlc/master"" * Update gluoncv/model_zoo/fpn/fpn.py * Fix `FPN` Bugs mAP on VOC07 is 58%, stay tuned. * add faster_rcnn_fpn_resnet50_v1b model * Update gluoncv/model_zoo/fpn/fpn.py * Update gluoncv/model_zoo/fpn/fpn.py * Create Readme.md * Update Readme.md * Update Readme.md * Update Readme.md * Update Readme.md * Update Readme.md * Rename Readme.md to README.md * Update Train and Eval script, Support Eval VOC12 Test. * Update scripts/detection/fpn/eval_fpn_voc12.py * Update scripts/detection/fpn/eval_fpn_voc12.py * Update README.md * Update README.md * Update fpn.py * Update gluoncv/model_zoo/model_zoo.py * Update gluoncv/model_zoo/model_zoo.py * default not to use static alloc to save memory, speed is not significantly impacted. added dilated faster_rcnn_resnet50_v1b added mask_rcnn_resnet101_v1b * fix missing args * small fix * docs * rm unneeded file * rm debug log * Faster RCNN with FPN * rm unnecessary files pylint rm Non-ASCII fix syntax lint rm from .fpn import * stride => strides rm syncbn in rpn rm syncbn arg mask rcnn arg fix missing "s" * rm 's' in anchor_generators * old model compatibility fix * not using RPNHead to keep backward compatibility with old models * _strides * mask rcnn compatibility * docs * rm dilated faster rcnn * mask rcnn w/ fpn * rm undefined functions * change default roi mode to 'align' * trigger build * change name of the fpn networks * model store update * Fix typo (dmlc#622) * Improve custo coco compatible detection dataset (dmlc#624) * coco det improve for custom datasets * allow flexible image path parser * fix pycocotools _isArrayLike * better comment * clean * Add assertions for invalid class names for VOCDetection (dmlc#614) * Add assertions for invalid class names * Add assertions for invalid class names (revision1) * Add assertions/warnings for invalid class names (revision2) * Add assertions/warnings for invalid class names (revision3) * Add assertions/warnings for invalid class names (revision4) * add detection paper (dmlc#628) * add bibtex * rephrase * update bibtex * Update PSP Params (dmlc#629) * update psp params * update with pin-device_id (dmlc#630) * sync bn faster rcnn * pylint * change roi from 7 to 14, since the last fpn model we trained use 14 * add pretrained faster rcnn fpn bn * Update model_zoo.py * Update model_zoo.py * fpn RCNN docs
Add static alloc and fix load/save_params (dmlc#183) * fix save_params * add warmup lr * add static alloc * tune coco settings * fix load_params * add logging to saving parameters * tune coco param num_sample, test_post_nms * fix params doc * add coco settings to eval * change coco to 2x lr schedule * fix load_params in eval, pretrained backbone is still unchanged