plt原图像素+去四周白边和坐标轴保存图片

在复现一个floor_plan的语义分割的任务的时候想提取其中的一个子任务,也就是平面图识别中的房间识别,于是我需要把标记好的图片通过plt保存,并且维持原分辨率(像素)并且去除坐标轴和白边,看了很多教程,探索出了一段可以批量处理Cubicasa数据集房间识别的代码:

import cv2
import shutil
import numpy as np
import matplotlib.pyplot as plt
from tqdm import tqdm
from floortrans.loaders import FloorplanSVG
from torch.utils.data import DataLoader
from floortrans.plotting import discrete_cmap

discrete_cmap()

room_classes = ["Background", "Outdoor", "Wall", "Kitchen", "Living Room" ,"Bed Room", "Bath", "Entry", "Railing", "Storage", "Garage", "Undefined"] #不同的房间类型
data_folder = 'data/cubicasa140/' # 数据集文件夹
data_file = 'train.txt' # 数据集类型
savedata_folder = 'data_/pic/'
savelabel_folder = 'data_/label/' 

normal_set = FloorplanSVG(data_f
def img_cut_roi_resize_to_target_black(img_txt_path,result_path): img_total = [] txt_total = [] file = os.listdir(img_txt_path) for filename in file: first, last = os.path.splitext(filename) if last == ".bmp": # 图片的后缀名 img_total.append(first) # print(img_total) else: txt_total.append(first) for img_ in img_total: if img_ in txt_total: filename_img = img_ + ".bmp" # 图片的后缀名 # print('filename_img:', filename_img) path1 = os.path.join(img_txt_path, filename_img) img = cv2.imread(path1) h, w = img.shape[0], img.shape[1] # 直接读取原图的长宽不会失真 img = cv2.resize(img, (w, h), interpolation=cv2.INTER_CUBIC) # resize 像大小,否则roi区域可能会报错 # plt.imshow('resized_img',img) # 会报错,之后再次查看resize后的图片(已解决) # plt.show() filename_txt = img_ + ".txt" # print('filename_txt:', filename_txt) n = 1 with open(os.path.join(img_txt_path, filename_txt), "r+", encoding="utf-8", errors="ignore") as f: for line in f: aa = line.split(" ") x_center = w * float(aa[1]) # aa[1]左上点的x坐标 y_center = h * float(aa[2]) # aa[2]左上点的y坐标 width = int(w * float(aa[3])) # aa[3]图片width height = int(h * float(aa[4])) # aa[4]图片height lefttopx = int(x_center - width / 2.0) lefttopy = int(y_center - height / 2.0) # roi = img[lefttopy+1:lefttopy+height+3,lefttopx+1:lefttopx+width+1] # [左上y:右下y,左上x:右下x] (y1:y2,x1:x2)需要调参,否则裁剪出来的小可能不太好 roi = img[lefttopy:lefttopy + height, lefttopx:lefttopx + width] # 目前没有看出差距 roi = img_resize_to_target_black(roi) # roi = cv2.copyMakeBorder(roi, 50, 50, 50, 50, cv2.BORDER_CONSTANT, value=[255, 255, 255]) # 是将原图长宽各个
05-26
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值