Metadata-Version: 2.1
Name: mmdet
Version: 2.11.0
Summary: OpenMMLab Detection Toolbox and Benchmark
Home-page: https://github.com/open-mmlab/mmdetection
Author: OpenMMLab
Author-email: openmmlab@gmail.com
License: Apache License 2.0
Keywords: computer vision,object detection
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Description-Content-Type: text/markdown
Provides-Extra: all
Provides-Extra: tests
Provides-Extra: build
Provides-Extra: optional
License-File: LICENSE

# CAMDet
* 这是一个简单粗暴的README...

## Config: 
* 主要修改字段: 
  * backbone{type='...', type_name='...', ...}
  * type字段选择: CAMDet(w/o skip connection), MultiCAMDet(with skip connection)
  * type_name字段选择参见**Backbone**代码中的**specification**
* mask_rcnn:
  * 包含FPN: ./configs/levit/mask_rcnn_camdet_neck4_1x.py
  * 不包含FPN: ./configs/levit/mask_rcnn_camdet_noneck_1x.py
* retinaNet:
  * 包含FPN: ./configs/levit/retinanet_camdet_neck4_1x.py
  * 不包含FPN: ./configs/levit/retinanet_camdet_noneck_1x.py

## Backbone：
* 配置字段：specification
* Baseline: 不包含skip connection
  * ./mmdet/models/backbones/camdet_baseline.py
* Multi-scale CAMDet: 包含skip connection
  * ./mmdet/models/backbones/camdet_multiscale.py
  * blocks设置代码: ./mmdet/models/backbones/camdet_blocks.py
  * layer层代码: ./mmdet/models/backbones/camdet_layer.py



