- 15 2月, 2019 4 次提交
-
-
由 Cheng-Yang Fu 提交于
* Add RetinetNet parameters in cfg. * hot fix. * Add the retinanet head module now. * Add the function to generate the anchors for RetinaNet. * Add the SigmoidFocalLoss cuda operator. * Fix the bug in the extra layers. * Change the normalizer for SigmoidFocalLoss * Support multiscale in training. * Add retinannet training script. * Add the inference part of RetinaNet. * Fix the bug when building the extra layers in retinanet. Update the matching part in retinanet_loss. * Add the first version of the inference of RetinaNet. Need to check it again to see if is there any room for speed improvement. * Remove the retinanet_R-50-FPN_2x.yaml first. * Optimize the retinanet postprocessing. * quick fix. * Add script for training RetinaNet with ResNet101 backbone. * Move cfg.RETINANET to cfg.MODEL.RETINANET * Remove the variables which are not used. * revert boxlist_ops. Generate Empty BoxLists instead of [] in retinanet_infer * Remove the not used commented lines. Add NUM_DETECTIONS_PER_IMAGE * remove the not used codes. * Move retinanet related files under Modeling/rpn/retinanet * Add retinanet_X_101_32x8d_FPN_1x.yaml script. This model is not fully validated. I only trained it around 5000 iterations and everything is fine. * set RETINANET.PRE_NMS_TOP_N as 0 in level5 (p7), because previous setting may generate zero detections and could cause the program break. This part is used in original Detectron setting. * Fix the rpn only bug when the training ends. * Minor improvements * Comments and add Python-only implementation * Bugfix and remove commented code * keep the generalized_rcnn same. Move the build_retinanet inside build_rpn. * Add USE_C5 in the MODEL.RETINANET * Add two configs using P5 to generate P6. * fix the bug when loading the Caffe2 ImageNet pretrained model. * Reduce the code depulication of RPN loss and RetinaNet loss. * Remove the comment which is not used. * Remove the hard coded number of classes. * share the foward part of rpn inference. * fix the bug in rpn inference. * Remove the conditional part in the inference. * Bug fix: add the utils file for permute and flatten of the box prediction layers. * Update the comment. * quick fix. Adding import cat. * quick fix: forget including import. * Adjust the normalization part according to Detectron's setting. * Use the bbox reg normalization term. * Clean the code according to recent review. * Using CUDA version for training now. And the python version for training on cpu. * rename the directory to retinanet. * Make the train and val datasets are consistent with mask r-cnn setting. * add comment.
-
由 Himanshu Pandey 提交于
-
由 CoinCheung 提交于
-
由 Levi Viana 提交于
* Adding support to Caffe2 ResNeXt-152-32x8d-FPN-IN5k backbone for Mask R-CNN * Clean up * Fixing path_catalogs.py * Back to old ROIAlign_cpu.cpp file
-
- 13 2月, 2019 2 次提交
-
-
由 Rodrigo Berriel 提交于
-
由 Francisco Massa 提交于
-
- 12 2月, 2019 2 次提交
-
-
由 Francisco Massa 提交于
* Add RPN config files * Add more RPN models
-
由 Francisco Massa 提交于
* [WIP] Keypoints inference on C2 models work * Training seems to work Still gives slightly worse results * e2e training works but gives 3 and 5 mAP less * Add modification proposed by @ChangErgou Improves mAP by 1.5 points, to 0.514 and 0.609 * Keypoints reproduce expected results * Clean coco.py * Linter + remove unnecessary code * Merge criteria for empty bboxes in has_valid_annotation * Remove trailing print * Add demo support for keypoints Still need further cleanups and improvements, like adding fields support for the other ops in Keypoints * More cleanups and misc improvements * Fixes after rebase * Add information to the readme * Fix md formatting
-
- 07 2月, 2019 1 次提交
-
-
由 Tong Xiao 提交于
* Registry for RoI Box Predictors - Add a registry ROI_BOX_PREDICTOR - Use the registry in roi_box_predictors.py, replacing the local factory - Minor changes in structures/bounding_box.py: when copying a box with fields, check if the field exists - Minor changes in logger.py: make filename a optional argument with default value of "log.txt" * Add Argument skip_missing=False
-
- 06 2月, 2019 1 次提交
-
-
由 Alexander Pacha 提交于
Fixing build-errors on Windows due to invalid types when calling THCCeilDiv. Adding type-cast to (long) to first parameter to fix the errors. (#409)
-
- 05 2月, 2019 2 次提交
-
-
由 Akiomi KAMAKURA 提交于
-
由 zimenglan 提交于
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed * add GroupNorm * add GroupNorm -- sort out yaml files * use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes * modification on 'group_norm' and 'conv_with_kaiming_uniform' function * modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication * use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead * agnostic-regression for bbox
-
- 04 2月, 2019 1 次提交
-
-
由 Levi Viana 提交于
-
- 01 2月, 2019 1 次提交
-
-
由 Sameer Indarapu 提交于
Since IMS_PER_BATCH is global, it shouldn't be multiplied with the # of GPUs.
-
- 31 1月, 2019 1 次提交
-
-
由 Rodrigo Berriel 提交于
-
- 30 1月, 2019 1 次提交
-
-
由 夜阑听风 提交于
-
- 25 1月, 2019 1 次提交
-
-
由 wat3rBro 提交于
-
- 23 1月, 2019 4 次提交
-
-
由 zimenglan 提交于
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed * add GroupNorm * add GroupNorm -- sort out yaml files * use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes * modification on 'group_norm' and 'conv_with_kaiming_uniform' function * modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication * use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead
-
由 Forest 提交于
-
由 Cheng-Yang Fu 提交于
* Add new section "Projects using maskrcnn-benchmark". * Update README.md update the format. * Update README.md * Add coco_2017_train and coco_2017_val * Update README.md Add the instructions about COCO_2017
-
由 Cheng-Yang Fu 提交于
* Add new section "Projects using maskrcnn-benchmark". * Update README.md update the format. * Update README.md
-
- 22 1月, 2019 1 次提交
-
-
由 Aaron Lelevier 提交于
fixes #339
-
- 21 1月, 2019 4 次提交
-
-
由 Francisco Massa 提交于
This reverts commit 6cbb3d27.
-
由 图波列夫 提交于
-
由 zimenglan 提交于
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed * add GroupNorm * add GroupNorm -- sort out yaml files * use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes * modification on 'group_norm' and 'conv_with_kaiming_uniform' function * modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication
-
由 图波列夫 提交于
-
- 14 1月, 2019 2 次提交
-
-
由 guanfuchen 提交于
-
由 任广辉 提交于
-
- 30 12月, 2018 1 次提交
-
-
由 夜阑听风 提交于
sort keys before reduction
-
- 22 12月, 2018 1 次提交
-
-
由 Francisco Massa 提交于
-
- 21 12月, 2018 2 次提交
-
-
由 Lei Yang 提交于
* Update checkpoint.py if edit "{save_dir}/last_checkpoint" by vim, "\n" will auto append to the end of file. which will raise ``` FileNotFoundError: [Errno 2] No such file or directory: 'save_dir/model_0060000.pth\n' ``` * Update checkpoint.py if edit "{save_dir}/last_checkpoint" by vim, "\n" will auto append to the end of file. which will raise ``` FileNotFoundError: [Errno 2] No such file or directory: 'save_dir/model_0060000.pth\n' ```
-
由 benjaminrwilson 提交于
-
- 18 12月, 2018 1 次提交
-
-
由 Gu Wang 提交于
-
- 17 12月, 2018 1 次提交
-
-
由 Francisco Massa 提交于
-
- 14 12月, 2018 2 次提交
- 06 12月, 2018 2 次提交
-
-
由 Yuxin Wu 提交于
* Fix indexing error in nms kernel Here it is indexing a cuda tensor with CPU indices. It used to work, but after https://github.com/pytorch/pytorch/commit/006505bb8f9dcf0f38b32518308d071c8a1ccec6 it results in memory corruption. * Use the device of other tensors
-
由 Henry Wang 提交于
* add force json option * fix the same issue as #185 * bug fix * cityscapes config * update paths catalog * discard config change * organize code for more-datasets * use better representation for coco-style datasets * rename coco-style config * remove import * chmod 644 * make the config more verbose * update readme * rename * chmod
-
- 05 12月, 2018 2 次提交
-
-
由 CoinCheung 提交于
-
由 zimenglan 提交于
* make pixel indexes 0-based for bounding box in pascal voc dataset * replacing all instances of torch.distributed.deprecated with torch.distributed * replacing all instances of torch.distributed.deprecated with torch.distributed
-