mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-05-25 18:22:18 +08:00

Jerry Jiarui XU 0529952270

* Add chinese doc base (#593)

* [Doc] Add Chinese doc for useful_tools_md (#642)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* pipeline

* cus_model

* cus_model

* cus_model

* runtime_md

* dataset_prepare

* useful_tools

* refine

* Update useful_tools.md

* Update useful_tools.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for get_started (#615)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* get_started_md

* refine_get_started_md

* [Doc] Add Chinese doc for tutorial03_tutorial_datapipeline_md (#629)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* pipeline

* refine

* Update data_pipeline.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for tutorials04_customized_models_md (#630)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* pipeline

* cus_model

* cus_model

* cus_model

* refine

* refine

* Update customize_models.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for dataset_prepare_md (#640)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* pipeline

* cus_model

* cus_model

* cus_model

* runtime_md

* dataset_prepare

* Update dataset_prepare.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for tutorials05_training_tricks_md (#631)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* pipeline

* cus_model

* cus_model

* cus_model

* traning tricks md

* traning tricks md

* refine

* refine

* refine

* Update training_tricks.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for tutorials06_customized_runtime_md (#637)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* pipeline

* cus_model

* cus_model

* cus_model

* runtime_md

* Update customize_runtime.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for tutorials01_config_md (#628)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* new_config_md

* new_config_md1

* new_config_md1

* refine

* refine

* Update config.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese for modelzoo (#597)

* [Doc] Add Chinese for modelzoo

* add missing

* [Doc] Add Chinese doc for tutorial02_customized_dataset_md (#620)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* tutorial_customized_dataset

* refine

* Update customize_datasets.md

* fixconflict

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Doc] Add Chinese doc for train.md (#616)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* train_md

* refine

* refine_last

* refine_last

* refine_last

* refine_last

* refine_last

* temp

* refine_last

* qwe

Co-authored-by: yuanzhang <yuanzhang@yuanzhangdeMacBook-Pro.local>

* [Doc] Add Chinese doc for inference.md (#617)

* get_started_docs_zh

* inference_zh.md

* train_zh.md

* get_started_zh.md

* train_zh.md

* get_started_zh

* fix nospace between ZH and ENG

* change README_zh-CN link

* checkout space again

* checkout space again

* checkout space again

* inference_zh_md

* Update docs_zh-CN/inference.md

Directly delete this sentence?

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* qwe

* temp

* qw

* Update docs_zh-CN/inference.md

* Update docs_zh-CN/inference.md

* Update docs_zh-CN/inference.md

* Update docs_zh-CN/inference.md

* Update docs_zh-CN/inference.md

* Update inference.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* fixed some dir

* fixed typo

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: yuanzhang <yuanzhang@yuanzhangdeMacBook-Pro.local>

2021-07-03 08:54:32 -07:00

5.8 KiB

Raw Blame History

标准与模型库

共同设定

我们默认使用 4 卡分布式训练
所有 PyTorch 风格的 ImageNet 预训练网络由我们自己训练，和论文保持一致。我们的 ResNet 网络是基于 ResNetV1c 的变种，在这里输入层的 7x7 卷积被 3个 3x3 取代。
为了在不同的硬件上保持一致，我们以 torch.cuda.max_memory_allocated() 的最大值作为 GPU 占用率，同时设置 torch.backends.cudnn.benchmark=False。注意，这通常比 nvidia-smi 显示的要少。
我们以网络 forward 和后处理的时间加和作为推理时间，除去数据加载时间。我们使用脚本 tools/benchmark.py 来获取推理时间，它在 torch.backends.cudnn.benchmark=False 的设定下，计算 200 张图片的平均推理时间。
在框架中，有两种推理模式。
- slide 模式（滑动模式）：测试的配置文件字段 test_cfg 会是 dict(mode='slide', crop_size=(769, 769), stride=(513, 513)). 在这个模式下，从原图中裁剪多个小图分别输入网络中进行推理。小图的大小和小图之间的距离由 crop_size 和 stride 决定，重合区域会进行平均。
- whole 模式（全图模式）:测试的配置文件字段 test_cfg 会是 dict(mode='whole'). 在这个模式下，全图会被直接输入到网络中进行推理。对于 769x769 下训练的模型，我们默认使用 slide 进行推理，其余模型用 whole 进行推理。
对于输入大小为 8x+1 （比如769），我们使用 align_corners=True。其余情况，对于输入大小为 8x+1 (比如 512，1024)，我们使用 align_corners=False。

基线

FCN

请参考 FCN for details.

PSPNet

请参考 PSPNet for details.

DeepLabV3

请参考 DeepLabV3 for details.

PSANet

请参考 PSANet for details.

DeepLabV3+

请参考 DeepLabV3+ for details.

UPerNet

请参考 UPerNet for details.

NonLocal Net

请参考 NonLocal Net for details.

EncNet

请参考 EncNet for details.

CCNet

请参考 CCNet for details.

DANet

请参考 DANet for details.

APCNet

请参考 APCNet for details.

HRNet

请参考 HRNet for details.

GCNet

请参考 GCNet for details.

DMNet

请参考 DMNet for details.

ANN

请参考 ANN for details.

OCRNet

请参考 OCRNet for details.

Fast-SCNN

请参考 Fast-SCNN for details.

ResNeSt

请参考 ResNeSt for details.

Semantic FPN

请参考 Semantic FPN for details.

PointRend

请参考 PointRend for details.

MobileNetV2

请参考 MobileNetV2 for details.

MobileNetV3

请参考 MobileNetV3 for details.

EMANet

请参考 EMANet for details.

DNLNet

请参考 DNLNet for details.

CGNet

请参考 CGNet for details.

Mixed Precision (FP16) Training

Please refer Mixed Precision (FP16) Training for details.

速度标定

硬件

8 NVIDIA Tesla V100 (32G) GPUs
Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz

软件环境

Python 3.7
PyTorch 1.5
CUDA 10.1
CUDNN 7.6.03
NCCL 2.4.08

训练速度

为了公平比较，我们全部使用 ResNet-101V1c 进行标定。输入大小为 1024x512，批量样本数为 2。

训练速度如下表，指标为每次迭代的时间，以秒为单位，越低越快。

Implementation	PSPNet (s/iter)	DeepLabV3+ (s/iter)
MMSegmentation	0.83	0.85
SegmenTron	0.84	0.85
CASILVision	1.15	N/A
vedaseg	0.95	1.25

注意：DeepLabV3+ 的输出步长为 8。

5.8 KiB Raw Blame History Unescape Escape