- 26 11月, 2018 1 次提交
-
-
由 zimenglan 提交于
-
- 23 11月, 2018 5 次提交
-
-
由 Francisco Massa 提交于
* add support for pascal voc dataset and evaluate * optimization for adding voc dataset * make inference.py dataset-agnostic; add use_difficult option to voc dataset * handle voc difficult objects correctly * Remove dependency on lxml plus minor improvements * More cleanups * More comments and improvements * Lint fix * Move configs to their own folder
-
由 Miguel Varela Ramos 提交于
-
由 archdyn 提交于
-
由 Miguel Varela Ramos 提交于
-
由 keineahnung2345 提交于
* add opencv support to Dockerfile cv2 is used by predictor.py, so it's required * install opencv-python from conda
-
- 21 11月, 2018 2 次提交
-
-
由 keineahnung2345 提交于
-
由 Francisco Massa 提交于
-
- 20 11月, 2018 2 次提交
-
-
由 Francisco Massa 提交于
-
由 Francisco Massa 提交于
* Add an option to postprocess masks during inference * Fix COCO evaluation to resize masks ony if needed. * Fix casting * Fix minor issues in paste_mask_in_image * Cast mask to uint8 * Make Masker batch compatible * Remove warnings and stylistic changes
-
- 19 11月, 2018 1 次提交
-
-
由 Francisco Massa 提交于
-
- 17 11月, 2018 1 次提交
-
-
由 keineahnung2345 提交于
* fix some minor issues in dockerfile RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections fixes debconf: unable to initialize frontend: Dialog debconf: (TERM is not set, so the dialog frontend is not usable.) debconf: falling back to frontend: Readline debconf: unable to initialize frontend: Readline debconf: (This frontend requires a controlling tty.) debconf: falling back to frontend: Teletype dpkg-preconfigure: unable to re-open stdin: RUN apt-get update -y && apt-get install -y apt-utils fixes debconf: delaying package configuration, since apt-utils is not installed * remove redundant command * add -y to conda install and pip install * remove -y from pip install
-
- 16 11月, 2018 1 次提交
-
-
由 Miguel Varela Ramos 提交于
* added Dockerfile * intructions for installation with docker * INSTALL.md: added note to inform nvidia-docker only works with Linux * dockerfile nccl2 hotfix * INSTALL.md update * removes explicit install of NCCL2 as it is included in the CUDA image
-
- 15 11月, 2018 1 次提交
-
-
由 Jimmy Wu 提交于
-
- 14 11月, 2018 2 次提交
- 13 11月, 2018 1 次提交
-
-
由 Miguel Varela Ramos 提交于
* added Dockerfile * intructions for installation with docker * adds nccl to dockerfile * Update Dockerfile * Update INSTALL.md
-
- 05 11月, 2018 2 次提交
-
-
由 Hadrien Mary 提交于
-
由 Guoxia Wang 提交于
## Bug When I repeatedly invoke build_detection_model function to build the model, I will get the error: `AttributeError: 'ResNet' object has no attribute 'layer1'`. ## To Reproduce ``` model = build_detection_model(cfg) model = build_detection_model(cfg) ``` ## The reason The variable `ResNet50StagesTo4` is a global generator expression, so when we build the model secondly, the code executes to Line 82 `for stage_spec in stage_specs:` and `stage_specs` will return empty leading to do not add any stage. Finally, `self._freeze_backbone` try to freeze the backbone by executing `m = getattr(self, "layer" + str(stage_index))` firstly. At the moment, it will throw the AttributeError `AttributeError: 'ResNet' object has no attribute 'layer1'`. I guess you want to define ResNet50StagesTo4 as the tuple, so I try to fix by add tuple type qualifier. ## The solution Add the tuple type to `ResNet50StagesTo5`, `ResNet50StagesTo4`, `ResNet50FPNStagesTo5`, `ResNet101FPNStagesTo5`. I do not know whether there are similar bug existing, so you need to review my solution. Thank you!
-
- 02 11月, 2018 2 次提交
-
-
由 Yan Li 提交于
* quick fix for area * Update bounding_box.py
-
由 Jiayuan Gu 提交于
use cuda version torch.randperm to avoid copy from gpu to cpu and a fatal bug in multi-thread cpu version
-
- 01 11月, 2018 3 次提交
-
-
由 Yan Li 提交于
-
由 Mitchell Below 提交于
Replace BoxList argument size with image_size.
-
由 Mitchell Below 提交于
Replace baseline with benchmark
-
- 31 10月, 2018 1 次提交
-
-
由 Stefan Otte 提交于
-
- 30 10月, 2018 1 次提交
-
-
由 Francisco Massa 提交于
-
- 27 10月, 2018 3 次提交
-
-
由 Soumith Chintala 提交于
Fix BoxList constructor call in README.md
-
由 Nikolay Shebanov 提交于
-
由 Maxim Berman 提交于
-
- 26 10月, 2018 8 次提交
-
-
由 Francisco Massa 提交于
-
由 Francisco Massa 提交于
-
由 Francisco Massa 提交于
-
由 Francisco Massa 提交于
* Add missing __init__.py files * Add packages * Rename logging.py to logger.py Import rules from Python2 makes this a bad idea * Make import_file py2 compatible * list does not have .copy() in py2 * math.log2 does not exist in py2 * Miscellaneous fixes for py2 * Address comments
-
由 Lê Khắc Hồng Phúc 提交于
-
由 Jean-Marie Prigent 提交于
-
由 Soumith Chintala 提交于
Access repos via https in INSTALL.md
-
由 Nikolay Shebanov 提交于
It is simpler and requires less effort (i.e. no auth) compared to SSH
-
- 25 10月, 2018 3 次提交
-
-
由 Kongsea 提交于
-
由 Francisco Massa 提交于
-
由 vfdev 提交于
Fix a small typo
-