gaotingquan d7014129f1 tipc: set DataLoader.Train.sampler.shuffle=False ...

benchmark needs the field to set Global.print_batch_step=1. Check file "./test_tipc/benchmark_train.sh#L76" for details.

2022-10-17 11:24:57 +08:00

..

AlexNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

ConvNeXt

tipc: turn off mkldnn and trt

2022-09-29 05:22:44 +00:00

CSPNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

CSWinTransformer

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

DarkNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

DeiT

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

DenseNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

Distillation

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

DLA

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

DPN

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

EfficientNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

ESNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

GeneralRecognition

fix typo in config files

2022-09-04 13:52:58 +00:00

GeneralRecognitionV2

fix benchmark train's config for GeneralRecognitionV2, and polish TIPC docs

2022-09-14 08:54:22 +00:00

GhostNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

HarDNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

HRNet

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

Inception

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

LeViT

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

MixNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

MobileNetV1

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

MobileNetV2

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

MobileNetV3

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

MobileViT

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

PeleeNet

mv

2022-08-05 14:34:14 +08:00

PP-ShiTu

skip python inference when test for mainbody_det

2022-07-13 18:07:50 +08:00

PP-ShiTuV2

fix typo in config files

2022-09-04 13:52:58 +00:00

PPHGNet

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

PPLCNet

tipc: set bs=256 to avoid oom

2022-08-05 14:34:14 +08:00

PPLCNetV2

tipc: set DataLoader.Train.sampler.shuffle=False

2022-10-17 11:24:57 +08:00

PVTV2

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

RedNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

Res2Net

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

ResNeSt

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

ResNet

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

ResNeXt

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

ReXNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

SENet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

ShuffleNet

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

SqueezeNet

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

SwinTransformer

tipc: rm useless bs

2022-08-05 14:34:14 +08:00

TNT

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

Twins

tipc: support benchmark with fp32/fp16 training

2022-08-05 14:34:14 +08:00

VAN

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

VGG

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

VisionTransformer

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00

Xception

set eval_during_train=False and save_interval=2 to reduce checkpoint storage

2022-07-13 19:36:32 +08:00