（转）Cifar |
您所在的位置：网站首页 › cifar 10数据集可视化 › （转）Cifar |
（转）Cifar
|
https://blog.csdn.net/hyqwmxsh/article/details/82629961 学习Tensorflow或深度学习，难免用到各种数据集， 最近用到cifar10数据集，简单研究了下，然后把cifar-10数据集保存为jpg图片， 分别利用python和c++做了实现。CIFAR-10下载 关于cifar-10，网上介绍很多，这里主要用了python和binary版本： 每个batch包含一个字典，该字典有data和labels两个key。其中，data是1000*3072（ 3 *32 *32）的图像数据。1000即图片数量，前1024个数据是red通道像素值，然后1024是个green通道像素值，最后啥blue通道。labels是1000个0~9表示数据类别的数据。 代码如下： import numpy as np from PIL import Image import pickle import os CHANNEL = 3 WIDTH = 32 HEIGHT = 32 data = [] labels=[] classification = ['airplane','automobile','bird','cat','deer','dog','frog','horse','ship','truck'] for i in range(5): with open("data/cifar-10-batches-py/data_batch_"+ str(i+1),mode='rb') as file: data_dict = pickle.load(file, encoding='bytes') data+= list(data_dict[b'data']) labels+= list(data_dict[b'labels']) img = np.reshape(data,[-1,CHANNEL, WIDTH, HEIGHT]) data_path = "data/images/" if not os.path.exists(data_path): os.makedirs(data_path) for i in range(img.shape[0]): r = img[i][0] g = img[i][1] b = img[i][2] ir = Image.fromarray(r) ig = Image.fromarray(g) ib = Image.fromarray(b) rgb = Image.merge("RGB", (ir, ig, ib)) name = "img-" + str(i) +"-"+ classification[labels[i]]+ ".png" rgb.save(data_path + name, "PNG")结果截图： 每个batch包括10000*（1 + 3072）大小数据，1代表label大小，3072是图像数据。存储方式同上。 代码如下： #include #include using namespace std; using namespace cv; #define WIDTH 32 #define HEIGHT 32 #define CHANNEL 3 #define PERNUM 1000 #define CLASS 10 char classification[CLASS][256] = { "airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck" }; int main(){ FILE *pBatch = fopen("data_batch_1.bin","rb"); if (!pBatch) return -1; unsigned char buf[CHANNEL * WIDTH * HEIGHT + 1]; memset(buf,0,sizeof(buf)); Mat bgr; bgr.create(WIDTH,HEIGHT,CV_8UC3); int index = 0; while (!feof(pBatch)){ fread(buf, 1, CHANNEL * WIDTH * HEIGHT + 1, pBatch); unsigned char* pBuf = buf + 1; for (int i = 0; i < bgr.rows;i++){ Vec3b *pbgr = bgr.ptr(i); for (int j = 0; j < bgr.cols;j++){ //pBuf += (i * bgr.rows + j * bgr.cols); for (int c = 0; c < 3;c++){ pbgr[j][c] = pBuf[(2 - c)* bgr.rows * bgr.cols + i * bgr.rows + j ]; } } } imwrite("image/img" + to_string(index)+".jpg",bgr); index++; } fclose(pBatch); return 0; }结果截图：
|
【本文地址】
今日新闻 |
推荐新闻 |