Skip to content
Snippets Groups Projects
Unverified Commit 5bf935e1 authored by Kai Chen's avatar Kai Chen Committed by GitHub
Browse files

update version to v1.0rc0 (#1068)

parent 1c28e669
No related branches found
Tags v1.0rc0
No related merge requests found
......@@ -38,6 +38,13 @@ This project is released under the [Apache 2.0 license](LICENSE).
## Updates
v1.0rc0 (27/07/2019)
- Implement lots of new methods and components (Mixed Precision Training, HTC, Libra R-CNN, Guided Anchoring, Empirical Attention, Mask Scoring R-CNN, Grid R-CNN (Plus), GHM, GCNet, FCOS, HRNet, Weight Standardization, etc.). Thank all collaborators!
- Support two additional datasets: WIDER FACE and Cityscapes.
- Refactoring for loss APIs and make it more flexible to adopt different losses and related hyper-parameters.
- Speed up multi-gpu testing.
- Integrate all compiling and installing in a single script.
v0.6.0 (14/04/2019)
- Up to 30% speedup compared to the model zoo.
- Support both PyTorch stable and nightly version.
......@@ -93,7 +100,7 @@ Results and models are available in the [Model zoo](MODEL_ZOO.md).
| GHM | ✓ | ✓ | ☐ | ✗ | ✓ |
| Mask Scoring R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| FCOS | ✓ | ✓ | ☐ | ✗ | ✓ |
| Grid R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Grid R-CNN (Plus) | ✓ | ✓ | ☐ | ✗ | ✓ |
| Hybrid Task Cascade| ✓ | ✓ | ☐ | ✗ | ✓ |
| Libra R-CNN | ✓ | ✓ | ☐ | ✗ | ✓ |
| Guided Anchoring | ✓ | ✓ | ☐ | ✗ | ✓ |
......
......@@ -15,10 +15,10 @@ def readme():
return content
MAJOR = 0
MINOR = 6
PATCH = 0
SUFFIX = ''
MAJOR = 1
MINOR = 0
PATCH = ''
SUFFIX = 'rc0'
SHORT_VERSION = '{}.{}.{}{}'.format(MAJOR, MINOR, PATCH, SUFFIX)
version_file = 'mmdet/version.py'
......@@ -143,7 +143,7 @@ if __name__ == '__main__':
setup_requires=['pytest-runner', 'cython', 'numpy'],
tests_require=['pytest'],
install_requires=[
'mmcv>=0.2.6', 'numpy', 'matplotlib', 'six', 'terminaltables',
'mmcv>=0.2.10', 'numpy', 'matplotlib', 'six', 'terminaltables',
'pycocotools', 'torch>=1.1'
],
ext_modules=[
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment