Skip to content
/ imagenet Public template

ImageNet training code that implements academic defaults

License

Notifications You must be signed in to change notification settings

landskape-ai/imagenet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ImageNet

ImageNet training repository for Landskape experiments

Datasets

Downloading

The ImageNet dataset URLs are no longer public. You must obtain a non-public copy from https://image-net.org/ and download the relavent tar files. extract.sh automates this, as long as you pass your URL into the TRAIN_URL and VALID_URL environment variables, like this:

$ TRAIN_URL="https://example.com/" VALID_URL="https://example.com/" extract.sh

Extracting

Download ILSVRC2012_img_train.tar and run the bash script extract_data.sh present in the utils directory. This creates two directories, train and val, each with 1000 subdirectories which consist of the images from the dataset.

Training

This implements training of popular model architectures, such as ResNet, AlexNet, and VGG on the ImageNet dataset.

Requirements

  • Install PyTorch (pytorch.org)
  • pip install -r requirements.txt
  • Download and extract the ImageNet dataset as shown above

Training

To train a model, run main.py with the desired model architecture and the path to the ImageNet dataset:

python main.py -a resnet18 [imagenet-folder with train and val folders]

The default learning rate schedule starts at 0.1 and decays by a factor of 10 every 30 epochs. This is appropriate for ResNet and models with batch normalization, but too high for AlexNet and VGG. Use 0.01 as the initial learning rate for AlexNet or VGG:

python main.py -a alexnet --lr 0.01 [imagenet-folder with train and val folders]

Multi-processing Distributed Data Parallel Training

You should always use the NCCL backend for multi-processing distributed training since it currently provides the best distributed training performance.

Single node, multiple GPUs:

python main.py -a resnet50 --dist-url 'tcp://127.0.0.1:FREEPORT' --dist-backend 'nccl' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders]

Multiple nodes:

Node 0:

python main.py -a resnet50 --dist-url 'tcp://IP_OF_NODE0:FREEPORT' --dist-backend 'nccl' --multiprocessing-distributed --world-size 2 --rank 0 [imagenet-folder with train and val folders]

Node 1:

python main.py -a resnet50 --dist-url 'tcp://IP_OF_NODE0:FREEPORT' --dist-backend 'nccl' --multiprocessing-distributed --world-size 2 --rank 1 [imagenet-folder with train and val folders]

Usage

usage: main.py [-h] [--arch ARCH] [-j N] [--epochs N] [--start-epoch N] [-b N]
               [--lr LR] [--momentum M] [--weight-decay W] [--print-freq N]
               [--resume PATH] [-e] [--pretrained] [--world-size WORLD_SIZE]
               [--rank RANK] [--dist-url DIST_URL]
               [--dist-backend DIST_BACKEND] [--seed SEED] [--gpu GPU]
               [--multiprocessing-distributed]  [--name]
               DIR

PyTorch ImageNet Training

positional arguments:
  DIR                   path to dataset

optional arguments:
  -h, --help            show this help message and exit
  --arch ARCH, -a ARCH  model architecture: alexnet | densenet121 |
                        densenet161 | densenet169 | densenet201 |
                        resnet101 | resnet152 | resnet18 | resnet34 |
                        resnet50 | squeezenet1_0 | squeezenet1_1 | vgg11 |
                        vgg11_bn | vgg13 | vgg13_bn | vgg16 | vgg16_bn | vgg19
                        | vgg19_bn (default: resnet18)
  -j N, --workers N     number of data loading workers (default: 4)
  --epochs N            number of total epochs to run
  --start-epoch N       manual epoch number (useful on restarts)
  -b N, --batch-size N  mini-batch size (default: 256), this is the total
                        batch size of all GPUs on the current node when using
                        Data Parallel or Distributed Data Parallel
  --lr LR, --learning-rate LR
                        initial learning rate
  --momentum M          momentum
  --weight-decay W, --wd W
                        weight decay (default: 1e-4)
  --print-freq N, -p N  print frequency (default: 10)
  --resume PATH         path to latest checkpoint (default: none)
  -e, --evaluate        evaluate model on validation set
  --pretrained          use pre-trained model
  --world-size WORLD_SIZE
                        number of nodes for distributed training
  --rank RANK           node rank for distributed training
  --dist-url DIST_URL   url used to set up distributed training
  --dist-backend DIST_BACKEND
                        distributed backend
  --seed SEED           seed for initializing training.
  --gpu GPU             GPU id to use.
  --multiprocessing-distributed
                        Use multi-processing distributed training to launch N
                        processes per node, which has N GPUs. This is the
                        fastest way to use PyTorch for either single node or
                        multi node data parallel training                    
  --name                Name for the W&B run