CUB

2024-07-14 20:06:17| 来源: 网络整理| 查看: 265

2021/2/5 更新

极力推荐的方式 https://github.com/wvinzh/WS_DAN_PyTorch

2020/7/19 更新 CUB-200-2011的下载：

https://www.vision.caltech.edu/datasets/cub_200_2011/ 网站有时进不去，可以通过百度云下载。百度云链接：链接: https://pan.baidu.com/s/1o60hA0qrupDjtMGPVCke3A 密码: u0sr 如果只跑分类，下载第一个就行了。里面除了类别标签也有标注框。如果还想用到分割的话，可以下载Segmentations。我只下了红框内的压缩包在这里插入图片描述下载完，解压后： images文件夹：一共200类，每类60张左右的图片：

读取图片与类别标签：

方法一：使用scipy.misc、PIL和numpy结合处理方法一代码是参考NTS-Net的，哈哈哈哈！！！原作者写的非常瓦利鼓的！！！

import numpy as np # 读取数据 import scipy.misc import os from PIL import Image from torchvision import transforms import torch class CUB(): def __init__(self, root, is_train=True, data_len=None,transform=None, target_transform=None): self.root = root self.is_train = is_train self.transform = transform self.target_transform = target_transform img_txt_file = open(os.path.join(self.root, 'images.txt')) label_txt_file = open(os.path.join(self.root, 'image_class_labels.txt')) train_val_file = open(os.path.join(self.root, 'train_test_split.txt')) # 图片索引 img_name_list = [] for line in img_txt_file: # 最后一个字符为换行符 img_name_list.append(line[:-1].split(' ')[-1]) # 标签索引，每个对应的标签减１，标签值从0开始 label_list = [] for line in label_txt_file: label_list.append(int(line[:-1].split(' ')[-1]) - 1) # 设置训练集和测试集 train_test_list = [] for line in train_val_file: train_test_list.append(int(line[:-1].split(' ')[-1])) # zip压缩合并，将数据与标签(训练集还是测试集)对应压缩 # zip() 函数用于将可迭代的对象作为参数，将对象中对应的元素打包成一个个元组， # 然后返回由这些元组组成的对象，这样做的好处是节约了不少的内存。 # 我们可以使用 list() 转换来输出列表 # 如果 i 为 1，那么设为训练集 # １为训练集，０为测试集 # zip压缩合并，将数据与标签(训练集还是测试集)对应压缩 # 如果 i 为 1，那么设为训练集 train_file_list = [x for i, x in zip(train_test_list, img_name_list) if i] test_file_list = [x for i, x in zip(train_test_list, img_name_list) if not i] train_label_list = [x for i, x in zip(train_test_list, label_list) if i][:data_len] test_label_list = [x for i, x in zip(train_test_list, label_list) if not i][:data_len] if self.is_train: # scipy.misc.imread 图片读取出来为array类型，即numpy类型 self.train_img = [scipy.misc.imread(os.path.join(self.root, 'images', train_file)) for train_file in train_file_list[:data_len]] # 读取训练集标签 self.train_label = train_label_list if not self.is_train: self.test_img = [scipy.misc.imread(os.path.join(self.root, 'images', test_file)) for test_file in test_file_list[:data_len]] self.test_label = test_label_list # 数据增强 def __getitem__(self,index): # 训练集 if self.is_train: img, target = self.train_img[index], self.train_label[index] # 测试集 else: img, target = self.test_img[index], self.test_label[index] if len(img.shape) == 2: # 灰度图像转为三通道 img = np.stack([img]*3,2) # 转为 RGB 类型 img = Image.fromarray(img,mode='RGB') if self.transform is not None: img = self.transform(img) if self.target_transform is not None: target = self.target_transform(target) return img, target def __len__(self): if self.is_train: return len(self.train_label) else: return len(self.test_label) if __name__ == '__main__': ''' dataset = CUB(root='./CUB_200_2011') for data in dataset: print(data[0].size(),data[1]) ''' # 以pytorch中DataLoader的方式读取数据集 transform_train = transforms.Compose([ transforms.Resize((224, 224)), transforms.RandomCrop(224, padding=4), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.485,0.456,0.406], [0.229,0.224,0.225]), ]) dataset = CUB(root='./CUB_200_2011', is_train=False, transform=transform_train,) print(len(dataset)) trainloader = torch.utils.data.DataLoader(dataset, batch_size=2, shuffle=True, num_workers=0, drop_last=True) print(len(trainloader)) ''' trainset: 5994 trainloader 374 testset: 5794 testloader 363 '''

但是有一个致命缺陷：耗时太长：145.11554789543152 s 读数据耗时两分半，这谁顶的住？在这里插入图片描述方法二：使用cv2和numpy结合处理方法二代码参考github上大佬weiaicunzai的调参仓库

建立dataset.py文件 import os import cv2 import numpy as np from torch.utils.data import Dataset class CUB(Dataset): def __init__(self, path, train=True, transform=None, target_transform=None): self.root = path self.is_train = train self.transform = transform self.target_transform = target_transform self.images_path = {} with open(os.path.join(self.root, 'images.txt')) as f: for line in f: image_id, path = line.split() self.images_path[image_id] = path self.class_ids = {} with open(os.path.join(self.root, 'image_class_labels.txt')) as f: for line in f: image_id, class_id = line.split() self.class_ids[image_id] = class_id self.data_id = [] if self.is_train: with open(os.path.join(self.root, 'train_test_split.txt')) as f: for line in f: image_id, is_train = line.split() if int(is_train): self.data_id.append(image_id) if not self.is_train: with open(os.path.join(self.root, 'train_test_split.txt')) as f: for line in f: image_id, is_train = line.split() if not int(is_train): self.data_id.append(image_id) def __len__(self): return len(self.data_id) def __getitem__(self, index): """ Args: index: index of training dataset Returns: image and its corresponding label """ image_id = self.data_id[index] class_id = int(self._get_class_by_id(image_id)) - 1 path = self._get_path_by_id(image_id) image = cv2.imread(os.path.join(self.root, 'images', path)) if self.transform: image = self.transform(image) if self.target_transform: class_id = self.target_transform(class_id) return image, class_id def _get_path_by_id(self, image_id): return self.images_path[image_id] def _get_class_by_id(self, image_id): return self.class_ids[image_id] 建立transforms.py文件 import random import math import numbers import cv2 import numpy as np import torch class Compose: """Composes several transforms together. Args: transforms(list of 'Transform' object): list of transforms to compose """ def __init__(self, transforms): self.transforms = transforms def __call__(self, img): for trans in self.transforms: img = trans(img) return img def __repr__(self): format_string = self.__class__.__name__ + '(' for t in self.transforms: format_string += '\n' format_string += ' {0}'.format(t) format_string += '\n)' return format_string class ToCVImage: """Convert an Opencv image to a 3 channel uint8 image """ def __call__(self, image): """ Args: image (numpy array): Image to be converted to 32-bit floating point Returns: image (numpy array): Converted Image """ if len(image.shape) == 2: image = cv2.cvtColor(image, cv2.COLOR_GRAY2BGR) image = image.astype('uint8') return image class RandomResizedCrop: """Randomly crop a rectangle region whose aspect ratio is randomly sampled in [3/4, 4/3] and area randomly sampled in [8%, 100%], then resize the cropped region into a 224-by-224 square image. Args: size: expected output size of each edge scale: range of size of the origin size cropped ratio: range of aspect ratio of the origin aspect ratio cropped (w / h) interpolation: Default: cv2.INTER_LINEAR: """ def __init__(self, size, scale=(0.08, 1.0), ratio=(3.0 / 4.0, 4.0 / 3.0), interpolation='linear'): self.methods={ "area":cv2.INTER_AREA, "nearest":cv2.INTER_NEAREST, "linear" : cv2.INTER_LINEAR, "cubic" : cv2.INTER_CUBIC, "lanczos4" : cv2.INTER_LANCZOS4 } self.size = (size, size) self.interpolation = self.methods[interpolation] self.scale = scale self.ratio = ratio def __call__(self, img): h, w, _ = img.shape area = w * h for attempt in range(10): target_area = random.uniform(*self.scale) * area target_ratio = random.uniform(*self.ratio) output_h = int(round(math.sqrt(target_area * target_ratio))) output_w = int(round(math.sqrt(target_area / target_ratio))) if random.random()

【本文地址】

公司简介

联系我们

今日新闻

点击排行

实验室常用的仪器、试剂和: 说到实验室常用到的东西，主要就分为仪器、试剂和耗

不用再找了，全球10大实验: 01、赛默飞世尔科技（热电）Thermo Fisher Scientif

三代水柜的量产巅峰T-72坦: 作者：寞寒最近，西边闹腾挺大，本来小寞以为忙完这

通风柜跟实验室通风系统有: 说到通风柜跟实验室通风，不少人都纠结二者到底是不

集消毒杀菌、烘干收纳为一: 厨房是家里细菌较多的地方，潮湿的环境、没有完全密

实验室设备之全钢实验台如: 全钢实验台是实验室家具中较为重要的家具之一，很多

图片新闻

实验室药品柜的特性有哪些: 实验室药品柜是实验室家具的重要组成部分之一，主要

小学科学实验中有哪些教学: 计算机计算器一般打孔器打气筒仪器车显微镜

实验室各种仪器原理动图讲: 1.紫外分光光谱UV分析原理：吸收紫外光能量，引起分

高中化学常见仪器及实验装: 1、可加热仪器：2、计量仪器：（1）仪器A的名称：量

微生物操作主要设备和器具: 今天盘点一下微生物操作主要设备和器具，别嫌我啰嗦

浅谈通风柜使用基本常识: 　众所周知，通风柜功能中最主要的就是排气功能。在

CUB

CUB

今日新闻

点击排行

推荐新闻

图片新闻

专题文章