AntoineH/BU_Stoch_pool
1
0
Fork 0
mirror of https://github.com/AntoineHX/BU_Stoch_pool.git synced 2025-05-02 08:40:45 +02:00
Code Issues Projects Releases Packages Wiki Activity
No description
10 commits 1 branch 0 tags 161 KiB
Find a file
Exact
Marco Pedersoli 5504ca67ab fixed problem with inference with MyLeNetNoceil
2020-06-30 11:56:51 -04:00
jobs Benchmark NoCeil 2020-06-24 01:57:32 -07:00
models fixed problem with inference with MyLeNetNoceil 2020-06-30 11:56:51 -04:00
res Benchmark NoCeil 2020-06-24 01:57:32 -07:00
.gitignore Benchmark NoCeil 2020-06-24 01:57:32 -07:00
LICENSE Initial commit 2020-06-12 01:42:08 -07:00
main.py fixed problem with inference with MyLeNetNoceil 2020-06-30 11:56:51 -04:00
process_res.py fixed problem with inference with MyLeNetNoceil 2020-06-30 11:56:51 -04:00
README.md Initial commit 2020-06-12 01:42:08 -07:00
utils.py Initial commit 2020-06-12 01:42:08 -07:00

README.md

BU_Stoch_pool

Train CIFAR10 with PyTorch

I'm playing with PyTorch on the CIFAR10 dataset.

Prerequisites

  • Python 3.6+
  • PyTorch 1.0+

Accuracy

Model Acc.
VGG16 92.64%
ResNet18 93.02%
ResNet50 93.62%
ResNet101 93.75%
RegNetX_200MF 94.24%
RegNetY_400MF 94.29%
MobileNetV2 94.43%
ResNeXt29(32x4d) 94.73%
ResNeXt29(2x64d) 94.82%
DenseNet121 95.04%
PreActResNet18 95.11%
DPN92 95.16%

Learning rate adjustment

I manually change the lr during training:

  • 0.1 for epoch [0,150)
  • 0.01 for epoch [150,250)
  • 0.001 for epoch [250,350)

Resume the training with python main.py --resume --lr=0.01