- 22 4月, 2019 3 次提交
- 20 4月, 2019 3 次提交
- 17 4月, 2019 1 次提交
-
-
由 Tian Zhi 提交于
Create inference_single_cvimage.py to inference on the single image.
-
- 16 4月, 2019 4 次提交
- 12 4月, 2019 7 次提交
-
-
由 chhshen 提交于
-
由 Hao Chen 提交于
Fix typo: tpye() --> type()
-
由 cclauss 提交于
[flake8](http://flake8.pycqa.org) testing of https://github.com/tianzhi0549/FCOS on Python 3.7.1 $ __flake8 . --count --select=E9,F63,F72,F82 --show-source --statistics__ ``` ./maskrcnn_benchmark/structures/segmentation_mask.py:70:74: F821 undefined name 'tpye' "Type of `masks` argument could not be interpreted:%s" % tpye(masks) ^ ./docker/docker-jupyter/jupyter_notebook_config.py:5:5: F821 undefined name 'get_config' c = get_config() ^ 2 F821 undefined name 'get_config' 2 ``` __E901,E999,F821,F822,F823__ are the "_showstopper_" [flake8](http://flake8.pycqa.org) issues that can halt the runtime with a SyntaxError, NameError, etc. These 5 are different from most other flake8 issues which are merely "style violations" -- useful for readability but they do not effect runtime safety. * F821: undefined name `name` * F822: undefined name `name` in `__all__` * F823: local variable name referenced before assignment * E901: SyntaxError or IndentationError * E999: SyntaxError -- failed to compile a file into an Abstract Syntax Tree
-
由 Zhi Tian 提交于
-
由 Zhi Tian 提交于
-
由 Zhi Tian 提交于
-
由 Zhi Tian 提交于
-
- 09 4月, 2019 1 次提交
-
-
由 Csaba Botos 提交于
* support RLE and binary mask * do not convert to numpy * be consistent with Detectron * delete wrong comment * [WIP] add tests for segmentation_mask * update tests * minor change * Refactored segmentation_mask.py * Add unit test for segmentation_mask.py * Add RLE support for BinaryMaskList * PEP8 black formatting * Minor patch * Use internal that handles 0 channels * Fix polygon slicing
-
- 05 4月, 2019 1 次提交
-
-
由 Zhang Liliang 提交于
add tqdm in line32 : RUN pip install ninja yacs cython matplotlib opencv-python tqdm
-
- 04 4月, 2019 1 次提交
-
-
由 Zhang Liliang 提交于
Fix a bug. Romove the echo command in line 36: RUN conda install pytorch-nightly cudatoolkit=${CUDA} -c pytorch To enable conda installation of pytorch-nightly.
-
- 02 4月, 2019 1 次提交
-
-
由 Yihui_He 提交于
-
- 31 3月, 2019 1 次提交
-
-
由 Ouail 提交于
* add a FORCE_CUDA flag Following discussion [here](https://github.com/facebookresearch/maskrcnn-benchmark/issues/167), this seemed the best solution * Update Dockerfile * Update setup.py * add FORCE_CUDA as an ARG * modified: docker/Dockerfile modified: setup.py * small fix to readme of demo * remove test print * keep ARG_CUDA * remove env value and use the one from ARG * keep same formatting as source * change proposed by @miguelvr * Update INSTALL.md
-
- 27 3月, 2019 1 次提交
-
-
由 Francisco Massa 提交于
This reverts commit f0318794.
-
- 26 3月, 2019 3 次提交
-
-
由 Miguel Varela Ramos 提交于
* fixes to dockerfile * replaces local installation by git clone
-
由 Miguel Varela Ramos 提交于
* Merge branch 'master' of /home/braincreator/projects/maskrcnn-benchmark with conflicts. * rolls back the breaking AT dispatch changes (#555) * revert accidental docker changes * revert accidental docker changes (2)
-
由 kaiJIN 提交于
* support for any one cuda device * Revert "support for any one cuda device" This reverts commit 0197e4e2ef18ec41cc155f3ae2a0face5b77e1e9. * support runnning for anyone cuda device * using safe CUDAGuard rather than intrinsic CUDASetDevice * supplement a header dependency (test passed) * Support for arbitrary GPU device. * Support for arbitrary GPU device. * add docs for two method to control devices
-
- 25 3月, 2019 1 次提交
-
-
由 Bernhard Schäfer 提交于
-
- 13 3月, 2019 1 次提交
-
-
由 Csaba Botos 提交于
-
- 12 3月, 2019 2 次提交
-
-
由 Francisco Massa 提交于
-
由 Soumith Chintala 提交于
Fix dispatch breakage
-
- 11 3月, 2019 1 次提交
-
-
由 vishwakftw 提交于
-
- 10 3月, 2019 1 次提交
-
-
由 Bernhard Schäfer 提交于
-
- 08 3月, 2019 2 次提交
-
-
由 Stzpz 提交于
* Added a timer to benchmark model inference time in addition to total runtime. * Updated FBNet configs and included some baselines benchmark results. * Added a unit test for detectors. * Add links to the models
-
由 Francisco Massa 提交于
-
- 05 3月, 2019 2 次提交
-
-
由 Baptiste Metge 提交于
* fix INSTALL.md * fix PR * Update INSTALL.md
-
由 Bernhard Schäfer 提交于
-
- 01 3月, 2019 1 次提交
-
-
由 Erik 提交于
-
- 28 2月, 2019 2 次提交
-
-
由 Alexander Pacha 提交于
Using existing get_world_size to prevent AttributeError 'torch.distributed' has no attribute 'is_initialized'. (#511)
-
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 * Update the pip install. Adding tqdm which is used in engine/inference.py
-