jadechoghari's picture
add qa files
5085882 verified
raw
history blame
1.36 kB
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import math
import torch
from torchvision import transforms
from torchvision.transforms import functional as F
class RandomResizedCrop(transforms.RandomResizedCrop):
"""
RandomResizedCrop for matching TF/TPU implementation: no for-loop is used.
This may lead to results different with torchvision's version.
Following BYOL's TF code:
https://github.com/deepmind/deepmind-research/blob/master/byol/utils/dataset.py#L206
"""
@staticmethod
def get_params(img, scale, ratio):
width, height = F._get_image_size(img)
area = height * width
target_area = area * torch.empty(1).uniform_(scale[0], scale[1]).item()
log_ratio = torch.log(torch.tensor(ratio))
aspect_ratio = torch.exp(
torch.empty(1).uniform_(log_ratio[0], log_ratio[1])
).item()
w = int(round(math.sqrt(target_area * aspect_ratio)))
h = int(round(math.sqrt(target_area / aspect_ratio)))
w = min(w, width)
h = min(h, height)
i = torch.randint(0, height - h + 1, size=(1,)).item()
j = torch.randint(0, width - w + 1, size=(1,)).item()
return i, j, h, w