MMDeteceion之系列二(基准和模型介绍概述)

基准和模型

官方文档

1、常用设置

所有FPN基准和RPN-C4基准均使用8个GPU进行训练,批处理大小为16(每个GPU 2张图像)。其他C4基线使用8个批处理大小为8的GPU进行了训练(每个GPU 1张图像)。

所有模型都在coco_2017_train上训练以及在coco_2017_val测试。

我们使用分布式训练,并且BN层统计信息是固定的。

我们采用与Detectron相同的训练时间表。1x表示12个epoch,而2x表示24个epoch,这比Detectron的迭代次数略少,并且可以忽略不计。

ImageNet上所有pytorch样式的预训练主干都来自PyTorchmodel zoo。

为了与其他代码库进行公平比较,我们将GPU内存报告 torch.cuda.max_memory_allocated()为所有8个GPU 的最大值。请注意,此值通常小于nvidia-smi显示的值。

我们将推理时间报告为总体时间,包括数据加载,网络转发和后处理。

基线
具有不同主干的更多模型将添加到model zoo。

ImageNet 预训练模型

MMDetection中常用骨干模型的详细表格如下:

Baselines

RPN

Please refer to RPN for details.

Faster R-CNN(两阶段算法）

Please refer to Faster R-CNN for details.

Mask R-CNN(两阶段算法）

Please refer to Mask R-CNN for details.

Fast R-CNN (with pre-computed proposals)(两阶段算法）

Please refer to Fast R-CNN for details.

RetinaNet

Please refer to RetinaNet for details.

Cascade R-CNN and Cascade Mask R-CNN(两阶段算法）

Please refer to Cascade R-CNN for details.

Hybrid Task Cascade (HTC)(两阶段算法）

Please refer to HTC for details.

SSD

Please refer to SSD for details.

Group Normalization (GN)

Please refer to Group Normalization for details.

Weight Standardization

Please refer to Weight Standardization for details.

Deformable Convolution v2

Please refer to Deformable Convolutional Networks for details.

CARAFE: Content-Aware ReAssembly of FEatures

Please refer to CARAFE for details.

Instaboost

Please refer to Instaboost for details.

Libra R-CNN(两阶段算法）

Please refer to Libra R-CNN for details.

Guided Anchoring

Please refer to Guided Anchoring for details.

FCOS

Please refer to FCOS for details.

FoveaBox

Please refer to FoveaBox for details.

RepPoints

Please refer to RepPoints for details.

FreeAnchor

Please refer to FreeAnchor for details.

Grid R-CNN (plus)

Please refer to Grid R-CNN for details.

GHM

Please refer to GHM for details.

GCNet

Please refer to GCNet for details.

HRNet

Please refer to HRNet for details.

Mask Scoring R-CNN(两阶段算法）

Please refer to Mask Scoring R-CNN for details.

Train from Scratch

Please refer to Rethinking ImageNet Pre-training for details.

NAS-FPN

Please refer to NAS-FPN for details.

ATSS

Please refer to ATSS for details.

FSAF

Please refer to FSAF for details.

RegNetX

Please refer to RegNet for details.

Res2Net

Please refer to Res2Net for details.

GRoIE

Please refer to GRoIE for details.

Dynamic R-CNN(两阶段算法）

Please refer to Dynamic R-CNN for details.

PointRend

Please refer to PointRend for details.

DetectoRS

Please refer to DetectoRS for details.

Generalized Focal Loss

Please refer to Generalized Focal Loss for details.

CornerNet

Please refer to CornerNet for details.

YOLOv3（单阶段）

Please refer to YOLOv3 for details.

PAA

Please refer to PAA for details.

SABL
Please refer to SABL for details.

CentripetalNet

Please refer to CentripetalNet for details.

ResNeSt

Please refer to ResNeSt for details.

DETR(transform)

Please refer to DETR for details.

Deformable DETR

Please refer to Deformable DETR for details.

AutoAssign

Please refer to AutoAssign for details.

YOLOF(单阶段)

Please refer to YOLOF for details.

Seesaw Loss

Please refer to Seesaw Loss for details.

CenterNet

Please refer to CenterNet for details.

YOLOX（单阶段）

Please refer to YOLOX for details.

PVT

Please refer to PVT for details.

SOLO

Please refer to SOLO for details.

QueryInst

Please refer to QueryInst for details.

PanopticFPN

Please refer to PanopticFPN for details.

MaskFormer

Please refer to MaskFormer for details.

DyHead

Please refer to DyHead for details.

Mask2Former

Please refer to Mask2Former for details.

Efficientnet

Please refer to Efficientnet for details.