utils.py

import torch
import torchvision.transforms as transforms

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                 std=[0.229, 0.224, 0.225])

class PCALighting(object):
    """Lighting noise(AlexNet - style PCA - based noise)"""
    def __init__(self, alphastd, eigval, eigvec):
        self.alphastd = alphastd
        self.eigval = eigval
        self.eigvec = eigvec

    def __call__(self, img):
        if self.alphastd == 0:
            return img
        alpha = img.new().resize_(3).normal_(0, self.alphastd)
        rgb = self.eigvec.type_as(img).clone()\
            .mul(alpha.view(1, 3).expand(3, 3))\
            .mul(self.eigval.view(1, 3).expand(3, 3))\
            .sum(1).squeeze()
        return img.add(rgb.view(3, 1, 1).expand_as(img))


imagenet_pca = {
    'eigval': torch.Tensor([0.2175, 0.0188, 0.0045]),
    'eigvec': torch.Tensor([
        [-0.5675,  0.7192,  0.4009],
        [-0.5808, -0.0045, -0.8140],
        [-0.5836, -0.6948,  0.4203],
    ])
}

def strong_train_preprocess(img_size):
    trans = transforms.Compose([
        transforms.RandomResizedCrop(img_size),
        transforms.RandomHorizontalFlip(),
        transforms.ColorJitter(brightness=0.4, saturation=0.4, hue=0.4),
        transforms.ToTensor(),
        PCALighting(0.1, imagenet_pca['eigval'], imagenet_pca['eigvec']),
        normalize,
    ])
    print('---------------------- strong dataaug!')
    return trans

def standard_train_preprocess(img_size):
    trans = transforms.Compose([
        transforms.RandomResizedCrop(img_size),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        normalize,
    ])
    print('---------------------- weak dataaug!')
    return trans

def val_preprocess(img_size):
    trans = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(img_size),
        transforms.ToTensor(),
        normalize,
    ])
    return trans

class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self, name, fmt=':f'):
        self.name = name
        self.fmt = fmt
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count

    def __str__(self):
        fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
        return fmtstr.format(**self.__dict__)


class ProgressMeter(object):
    def __init__(self, num_batches, meters, prefix=""):
        self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
        self.meters = meters
        self.prefix = prefix

    def display(self, batch):
        entries = [self.prefix + self.batch_fmtstr.format(batch)]
        entries += [str(meter) for meter in self.meters]
        print('\t'.join(entries))

    def _get_batch_fmtstr(self, num_batches):
        num_digits = len(str(num_batches // 1))
        fmt = '{:' + str(num_digits) + 'd}'
        return '[' + fmt + '/' + fmt.format(num_batches) + ']'


def accuracy(output, target, topk=(1,)):
    """Computes the accuracy over the k top predictions for the specified values of k"""
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].reshape(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res


def read_hdf5(file_path):
    import h5py
    import numpy as np
    result = {}
    with h5py.File(file_path, 'r') as f:
        for k in f.keys():
            value = np.asarray(f[k])
            result[str(k).replace('+', '/')] = value
    print('read {} arrays from {}'.format(len(result), file_path))
    f.close()
    return result

def model_load_hdf5(model:torch.nn.Module, hdf5_path, ignore_keys='stage0.'):
    weights_dict = read_hdf5(hdf5_path)
    for name, param in model.named_parameters():
        print('load param: ', name, param.size())
        if name in weights_dict:
            np_value = weights_dict[name]
        else:
            np_value = weights_dict[name.replace(ignore_keys, '')]
        value = torch.from_numpy(np_value).float()
        assert tuple(value.size()) == tuple(param.size())
        param.data = value
    for name, param in model.named_buffers():
        print('load buffer: ', name, param.size())
        if name in weights_dict:
            np_value = weights_dict[name]
        else:
            np_value = weights_dict[name.replace(ignore_keys, '')]
        value = torch.from_numpy(np_value).float()
        assert tuple(value.size()) == tuple(param.size())
        param.data = value