Kernel size issue with "inceptionresnetv2"

[roy-shudipto]

When I am trying to run examples/cifar10.py with Inception-Resnet-v2, i am getting the following error:

RuntimeError: Calculated padded input size per channel: (1 x 1). Kernel size: (3 x 3). Kernel size can't be greater than actual input size

Tried to run this:

import argparse
import torch
import torchvision
import torchvision.transforms as transforms
from torch.autograd import Variable
import torch.nn as nn
import torch.optim as optim
from cnn_finetune import make_model

parser = argparse.ArgumentParser(description='Inception-Resnet-v2-TRAIN')
parser.add_argument('--batch-size', type=int, default=32, metavar='N',
                    help='input batch size for training (default: 32)')
parser.add_argument('--test-batch-size', type=int, default=64, metavar='N',
                    help='input batch size for testing (default: 64)')
parser.add_argument('--epochs', type=int, default=100, metavar='N',
                    help='number of epochs to train (default: 100)')
parser.add_argument('--save-model', type=int, default=10, metavar='N',
                    help='number of epochs after which the model will be saved (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
                    help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.9, metavar='M',
                    help='SGD momentum (default: 0.9)')
parser.add_argument('--no-cuda', action='store_true', default=False,
                    help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
                    help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=100, metavar='N',
                    help='how many batches to wait before logging training status')
parser.add_argument('--model-name', type=str, default='resnet50', metavar='M',
                    help='model name (default: resnet50)')
parser.add_argument('--dropout-p', type=float, default=0.2, metavar='D',
                    help='Dropout probability (default: 0.2)')

args = parser.parse_args()
use_cuda = not args.no_cuda and torch.cuda.is_available()
device = torch.device('cuda' if use_cuda else 'cpu')


def train(model, epoch, optimizer, train_loader, criterion=nn.CrossEntropyLoss()):
    total_loss = 0
    total_size = 0
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        total_loss += loss.item()
        total_size += data.size(0)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tAverage loss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), total_loss / total_size))


def main():
    model_name = args.model_name

    classes = (
        'plane', 'car', 'bird', 'cat', 'deer',
        'dog', 'frog', 'horse', 'ship', 'truck'
    )

    model = make_model(
        model_name,
        pretrained=True,
        num_classes=len(classes),
        pool=nn.AdaptiveMaxPool2d(1),
        dropout_p=args.dropout_p
    )
    model = model.to(device)

    transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(
            mean=model.original_model_info.mean,
            std=model.original_model_info.std),
    ])

    train_set = torchvision.datasets.CIFAR10(
        root='./data', train=True, download=True, transform=transform
    )
    train_loader = torch.utils.data.DataLoader(
        train_set, batch_size=args.batch_size, shuffle=True, num_workers=2
    )

    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)

    # Use exponential decay for fine-tuning optimizer
    scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=1, gamma=0.975)

    # Train
    for epoch in range(1, args.epochs + 1):
        train(model, epoch, optimizer, train_loader)
        scheduler.step(epoch)
        if epoch % args.save_model == 0:
            torch.save(model.state_dict(), './checkpoint/' + 'ckpt_' + str(epoch) + '.pth')


if __name__ == '__main__':
    main()