GoogLeNet is a type of convolutional neural network based on the Inception architecture. It utilises Inception modules, which allow the network to choose between multiple convolutional filter sizes in each block. An Inception network stacks these modules on top of each other, with occasional max-pooling layers with stride 2 to halve the resolution of the grid.
git clone --recursive https://github.com/PaddlePaddle/PaddleClas.git
cd PaddleClas
pip3 install -r requirements.txt
Sign up and login in ImageNet official website, then choose 'Download' to download the whole ImageNet dataset. Specify /path/to/imagenet
to your ImageNet path in later training process.
The ImageNet dataset path structure should look like:
imagenet
├── train
│ └── n01440764
│ ├── n01440764_10026.JPEG
│ └── ...
├── train_list.txt
├── val
│ └── n01440764
│ ├── ILSVRC2012_val_00000293.JPEG
│ └── ...
└── val_list.txt
# Modify the file: PaddleClas/ppcls/configs/ImageNet/Inception/GoogLeNet.yaml to add the option of AMP
AMP:
scale_loss: 128.0
use_dynamic_loss_scaling: True
# O1: mixed fp16
level: O1
# Make sure your dataset path is the same as above
cd PaddleClas
# Link your dataset to default location
ln -s /path/to/imagenet ./dataset/ILSVRC2012
export FLAGS_cudnn_exhaustive_search=True
export FLAGS_cudnn_batchnorm_spatial_persistent=True
export CUDA_VISIBLE_DEVICES=0,1,2,3
python3 -u -m paddle.distributed.launch --gpus=0,1,2,3 tools/train.py -c ppcls/configs/ImageNet/Inception/GoogLeNet.yaml
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。