本文共 1716 字,大约阅读时间需要 5 分钟。
在深度学习的训练中,大多需要使用正方形的图片,但是我们平常拍摄的图像大多都是长方形的,所以在缩放图片时,要给图片加灰条,代码很简单:
def letterbox_image(image, size): iw, ih = image.size w, h = size scale = min(w/iw, h/ih) nw = int(iwscale) nh = int(ihscale)image = image.resize((nw,nh), Image.BICUBIC)new_image = Image.new('RGB', size, (128,128,128))new_image.paste(image, ((w-nw)//2, (h-nh)//2))return new_image
这部分代码是用来加灰条的,iw和ih是原图的行列数,w和h是需要生成的图像的行列数,scale得到的是新图与原图的宽高比,简单想一下,宽高比越小的,变化的范围就越大,那么反之,就要给另外一边补灰条。所以先得到scale这个较小的宽高比,然后对图片进行缩放,new_image是一张灰色的新图,然后将缩放好的图像粘贴到灰色图像上,覆盖掉一部分,那么剩下的部分就是灰条了。
下面附完整的批量加灰条代码:import osimport numpy as npimport cv2from PIL import Imagedef letterbox_image(image, size): iw, ih = image.size w, h = size scale = min(w/iw, h/ih) nw = int(iw*scale) nh = int(ih*scale) image = image.resize((nw,nh), Image.BICUBIC) new_image = Image.new('RGB', size, (128,128,128)) new_image.paste(image, ((w-nw)//2, (h-nh)//2)) return new_imagedef search_files(directory): directory = os.path.normpath(directory) objects = {} for curdir, subdirs, files in os.walk(directory): for file in files: if file.endswith('.jpg'): label = curdir.split(os.path.sep)[-1] if label not in objects: objects[label] = [] path = os.path.join(curdir, file) objects[label].append(path) return objectsif __name__ == "__main__": train_samples = search_files('E:\\python\\learning\\tree_learn\\crossFork') print(train_samples) for label, filenames in train_samples.items(): for filename in filenames: img = Image.open(filename) new_img = letterbox_image(img, (224, 224)) new_img.save(filename)
转载地址:http://hlhtz.baihongyu.com/