03 2020 档案

摘要:1 from torch.utils.data import DataLoader 2 from torchvision import datasets 3 from PIL import Image as img 4 5 dataPath = './data/imgs/' 6 7 dataset 阅读全文
posted @ 2020-03-17 20:44 Junzhao 阅读(432) 评论(0) 推荐(0)
摘要:转置卷积实际是根据输入卷积核和输入特征图生成中间卷积核和特征图,再进行卷积操作 输入的卷积核kernel 大小 Size = size 步长 Stride = stride 填充 Padding = padding 输入特征图 H W 中间卷积核kernel' 大小 Size' = size 步长 阅读全文
posted @ 2020-03-16 10:54 Junzhao 阅读(790) 评论(0) 推荐(0)
摘要:PIL.Image.size与numpy.array.shape不同 1 >>> i=Image.open('11.png') 2 >>> i.size 3 (170, 256) #(W,H) 4 >>> j=np.array(i) 5 >>> j.shape 6 (256, 170) #(H,W) 阅读全文
posted @ 2020-03-14 17:44 Junzhao 阅读(2334) 评论(0) 推荐(0)
摘要:Histogram equalization and specialization from PIL import Image import os class Img: def __init__(self, image): self.img = image def getPr(self): # 获取 阅读全文
posted @ 2020-03-02 11:58 Junzhao 阅读(432) 评论(0) 推荐(0)