mmclassification/configs/fp16
whcao 5a86288f1f
[Fix]Fix metafile (#335)
* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* add mobilenet_v3.yml

* fix ymal

* rename model_zoo.yml to model-index.yml

* replace imagenet with imagenet-1k
2021-07-01 20:50:42 +08:00
..
README.md [Docs] Change tag into comment (#226) 2021-04-28 17:08:57 +08:00
metafile.yml [Fix]Fix metafile (#335) 2021-07-01 20:50:42 +08:00
resnet50_b32x8_fp16_dynamic_imagenet.py [Feature] Support fp16 training (#178) 2021-03-17 15:53:55 +08:00
resnet50_b32x8_fp16_imagenet.py [Feature] Support fp16 training (#178) 2021-03-17 15:53:55 +08:00

README.md

Mixed Precision Training

Introduction

@article{micikevicius2017mixed,
  title={Mixed precision training},
  author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others},
  journal={arXiv preprint arXiv:1710.03740},
  year={2017}
}

Results and models

Model Params(M) Flops(G) Mem (GB) Top-1 (%) Top-5 (%) Config Download
ResNet-50 25.56 4.12 1.9 76.32 93.04 config model | log