Model Libraries and Baselines

Test Environment

Python 3.7
PaddlePaddle Daily version
CUDA 10.1
cuDNN 7.5
NCCL 2.4.8

General Settings

All models were trained and tested in the COCO17 dataset.
Unless special instructions, all the ResNet backbone network using ResNet-B structure.
Inference time (FPS): The reasoning time was calculated on a Tesla V100 GPU by tools/eval.py testing all validation sets in FPS (number of pictures/second). CuDNN version is 7.5, including data loading, network forward execution and post-processing, and Batch size is 1.

Training strategy

We adopt and Detectron in the same training strategy.
1x strategy indicates that when the total batch size is 8, the initial learning rate is 0.01, and the learning rate decreases by 10 times after 8 epoch and 11 epoch, respectively, and the final training is 12 epoch.
2X strategy is twice as much as strategy 1X, and the learning rate adjustment position is twice as much as strategy 1X.

ImageNet pretraining model

Paddle provides a skeleton network pretraining model based on ImageNet. All pre-training models were trained by standard Imagenet 1K dataset. Res Net and Mobile Net are high-precision pre-training models obtained by cosine learning rate adjustment strategy or SSLD knowledge distillation training. Model details are available at PaddleClas.

Baseline

Faster R-CNN

Please refer toFaster R-CNN

Mask R-CNN

Please refer toMask R-CNN

Cascade R-CNN

Please refer toCascade R-CNN

YOLOv3

Please refer toYOLOv3

SSD

Please refer toSSD

FCOS

Please refer toFCOS

SOLOv2

Please refer toSOLOv2

PP-YOLO

Please refer toPP-YOLO

TTFNet

请参考TTFNet

Group Normalization

Please refer toGroup Normalization

Deformable ConvNets v2

Please refer toDeformable ConvNets v2

HRNets

Please refer toHRNets

Res2Net

Please refer toRes2Net

GFL

Please refer toGFL

PicoDet

Please refer toPicoDet

PP-YOLOE

Please refer toPP-YOLOE

YOLOX

Please refer toYOLOX

Rotating frame detection

S2ANet

Please refer toS2ANet

KeyPoint Detection

PP-TinyPose

Please refer to PP-TinyPose

HRNet

Please refer to HRNet

HigherHRNet

Please refer to HigherHRNet

Multi-Object Tracking

DeepSORT

Please refer to DeepSORT

JDE

Please refer to JDE

FairMOT

Please refer to FairMOT

ByteTrack

Please refer to ByteTrack

MODEL_ZOO_en.md 4.6 KB Permalink History Raw