YOLOv3 - Continue on #1695

README.md

@@ -97,6 +97,7 @@ Supported methods:
 - [x] [DetectoRS](configs/detectors/README.md)
 - [x] [Generalized Focal Loss](configs/gfl/README.md)
 - [x] [CornerNet](configs/cornernet/README.md)
+- [x] [YOLOv3](configs/yolo/README.md)
 
 Some other methods are also supported in [projects using MMDetection](./docs/projects.md).
 

configs/yolo/README.md

@@ -0,0 +1,25 @@
+# YOLOv3
+
+## Introduction
+```
+@misc{redmon2018yolov3,
+    title={YOLOv3: An Incremental Improvement},
+    author={Joseph Redmon and Ali Farhadi},
+    year={2018},
+    eprint={1804.02767},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+## Results and Models
+
+|    Backbone     |  Scale  | Lr schd | Mem (GB) | Inf time (fps) | box AP | Download  |
+| :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-------: |
+|   DarkNet-53    |   320   |   273e  |   2.7    |      50.9      |  28.6  | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection/v2.0/yolo/yolov3_d53_320_273e_coco/yolov3_d53_320_273e_coco-421362b6.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection/v2.0/yolo/yolov3_d53_320_273e_coco/yolov3_d53_320_273e_coco-20200819_172101.log.json) |
+|   DarkNet-53    |   416   |   273e  |   3.8    |      50.9      |  30.7  | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection/v2.0/yolo/yolov3_d53_mstrain-416_273e_coco/yolov3_d53_mstrain-416_273e_coco-2b60fcd9.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection/v2.0/yolo/yolov3_d53_mstrain-416_273e_coco/yolov3_d53_mstrain-416_273e_coco-20200819_173424.log.json) |
+|   DarkNet-53    |   608   |   273e  |   7.1    |      47.1      |  33.6  | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection/v2.0/yolo/yolov3_d53_mstrain-608_273e_coco/yolov3_d53_mstrain-608_273e_coco-139f5633.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmdetection/v2.0/yolo/yolov3_d53_mstrain-608_273e_coco/yolov3_d53_mstrain-608_273e_coco-20200819_170820.log.json) |
+
+
+## Credit
+This implementation originates from the project of Haoyu Wu(@wuhy08) at Western Digital.

configs/yolo/yolov3_d53_320_273e_coco.py

@@ -0,0 +1,42 @@
+_base_ = './yolov3_d53_mstrain-608_273e_coco.py'
+# dataset settings
+img_norm_cfg = dict(mean=[0, 0, 0], std=[255., 255., 255.], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Expand',
+        mean=img_norm_cfg['mean'],
+        to_rgb=img_norm_cfg['to_rgb'],
+        ratio_range=(1, 2)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=(320, 320), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(320, 320),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))

configs/yolo/yolov3_d53_mstrain-416_273e_coco.py

@@ -0,0 +1,42 @@
+_base_ = './yolov3_d53_mstrain-608_273e_coco.py'
+# dataset settings
+img_norm_cfg = dict(mean=[0, 0, 0], std=[255., 255., 255.], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Expand',
+        mean=img_norm_cfg['mean'],
+        to_rgb=img_norm_cfg['to_rgb'],
+        ratio_range=(1, 2)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=[(320, 320), (416, 416)], keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(416, 416),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))

configs/yolo/yolov3_d53_mstrain-608_273e_coco.py

@@ -0,0 +1,117 @@
+_base_ = [
+    '../_base_/default_runtime.py',
+]
+# model settings
+model = dict(
+    type='YOLOV3',
+    pretrained='open-mmlab://darknet53',
+    backbone=dict(
+        type='Darknet',
+        depth=53,
+        out_indices=(3, 4, 5),
+    ),
+    neck=dict(
+        type='YOLOV3Neck',
+        num_scales=3,
+        in_channels=[1024, 512, 256],
+        out_channels=[512, 256, 128],
+    ),
+    bbox_head=dict(
+        type='YOLOV3Head',
+        num_classes=80,
+        in_channels=[512, 256, 128],
+        out_channels=[1024, 512, 256],
+        anchor_generator=dict(
+            type='YOLOAnchorGenerator',
+            base_sizes=[
+                [(116, 90), (156, 198), (373, 326)],
+                [(30, 61), (62, 45), (59, 119)],
+                [(10, 13), (16, 30), (33, 23)],
+            ],
+            strides=[32, 16, 8]),
+        bbox_coder=dict(type='YOLOBBoxCoder'),
+        featmap_strides=[32, 16, 8]))
+# training and testing settings
+train_cfg = dict(
+    assigner=dict(
+        type='GridAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0))
+test_cfg = dict(
+    nms_pre=1000,
+    min_bbox_size=0,
+    score_thr=0.05,
+    conf_thr=0.005,
+    nms=dict(type='nms', iou_thr=0.45),
+    max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(mean=[0, 0, 0], std=[255., 255., 255.], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile', to_float32=True),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Expand',
+        mean=img_norm_cfg['mean'],
+        to_rgb=img_norm_cfg['to_rgb'],
+        ratio_range=(1, 2)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=[(320, 320), (608, 608)], keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(608, 608),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=train_pipeline,
+    ),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline,
+    ),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline,
+    ))
+# optimizer
+optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=2000,  # same as burn-in in darknet
+    warmup_ratio=0.1,
+    step=[218, 246])
+# runtime settings
+total_epochs = 273
+evaluation = dict(interval=1, metric=['bbox'])

docs/model_zoo.md

@@ -147,6 +147,9 @@ Please refer to [Generalized Focal Loss](https://github.com/open-mmlab/mmdetecti
 ### CornerNet
 Please refer to [CornerNet](https://github.com/open-mmlab/mmdetection/blob/master/configs/cornernet) for details.
 
+### YOLOv3
+Please refer to [YOLOv3](https://github.com/open-mmlab/mmdetection/blob/master/configs/yolo) for details.
+
 ### Other datasets
 
 We also benchmark some methods on [PASCAL VOC](https://github.com/open-mmlab/mmdetection/blob/master/configs/pascal_voc), [Cityscapes](https://github.com/open-mmlab/mmdetection/blob/master/configs/cityscapes) and [WIDER FACE](https://github.com/open-mmlab/mmdetection/blob/master/configs/wider_face).

mmdet/core/anchor/__init__.py

@@ -1,10 +1,11 @@
-from .anchor_generator import AnchorGenerator, LegacyAnchorGenerator
+from .anchor_generator import (AnchorGenerator, LegacyAnchorGenerator,
+                               YOLOAnchorGenerator)
 from .builder import ANCHOR_GENERATORS, build_anchor_generator
 from .point_generator import PointGenerator
 from .utils import anchor_inside_flags, calc_region, images_to_levels
 
 __all__ = [
     'AnchorGenerator', 'LegacyAnchorGenerator', 'anchor_inside_flags',
     'PointGenerator', 'images_to_levels', 'calc_region',
-    'build_anchor_generator', 'ANCHOR_GENERATORS'
+    'build_anchor_generator', 'ANCHOR_GENERATORS', 'YOLOAnchorGenerator'
 ]