deep-person-reid/torchreid/transforms.py

72 lines
2.1 KiB
Python

from __future__ import absolute_import
from __future__ import division
from torchvision.transforms import *
import torch
from PIL import Image
import random
import numpy as np
class Random2DTranslation(object):
"""
With a probability, first increase image size to (1 + 1/8), and then perform random crop.
Args:
- height (int): target image height.
- width (int): target image width.
- p (float): probability of performing this transformation. Default: 0.5.
"""
def __init__(self, height, width, p=0.5, interpolation=Image.BILINEAR):
self.height = height
self.width = width
self.p = p
self.interpolation = interpolation
def __call__(self, img):
"""
Args:
- img (PIL Image): Image to be cropped.
"""
if random.uniform(0, 1) > self.p:
return img.resize((self.width, self.height), self.interpolation)
new_width, new_height = int(round(self.width * 1.125)), int(round(self.height * 1.125))
resized_img = img.resize((new_width, new_height), self.interpolation)
x_maxrange = new_width - self.width
y_maxrange = new_height - self.height
x1 = int(round(random.uniform(0, x_maxrange)))
y1 = int(round(random.uniform(0, y_maxrange)))
croped_img = resized_img.crop((x1, y1, x1 + self.width, y1 + self.height))
return croped_img
def build_transforms(height, width, is_train, **kwargs):
"""Build transforms
Args:
- height (int): target image height.
- width (int): target image width.
- is_train (bool): train or test phase.
"""
# use imagenet mean and std as default
imagenet_mean = [0.485, 0.456, 0.406]
imagenet_std = [0.229, 0.224, 0.225]
normalize = Normalize(mean=imagenet_mean, std=imagenet_std)
transforms = []
if is_train:
transforms += [Random2DTranslation(height, width)]
transforms += [RandomHorizontalFlip()]
else:
transforms += [Resize((height, width))]
transforms += [ToTensor()]
transforms += [normalize]
transforms = Compose(transforms)
return transforms