本文主要介绍了pytorch cnn 识别手写的字实现自建图片数据,分享给大家,具体如下:
# library # standard library import os # third-party library import torch import torch.nn as nn from torch.autograd import Variable from torch.utils.data import Dataset, DataLoader import torchvision import matplotlib.pyplot as plt from PIL import Image import numpy as np # torch.manual_seed(1) # reproducible # Hyper Parameters EPOCH = 1 # train the training data n times, to save time, we just train 1 epoch BATCH_SIZE = 50 LR = 0.001 # learning rate root = "./mnist/raw/" def default_loader(path): # return Image.open(path).convert('RGB') return Image.open(path) class MyDataset(Dataset): def __init__(self, txt, transform=None, target_transform=None, loader=default_loader): fh = open(txt, 'r') imgs = [] for line in fh: line = line.strip('\n') line = line.rstrip() words = line.split() imgs.append((words[0], int(words[1]))) self.imgs = imgs self.transform = transform self.target_transform = target_transform self.loader = loader fh.close() def __getitem__(self, index): fn, label = self.imgs[index] img = self.loader(fn) img = Image.fromarray(np.array(img), mode='L') if self.transform is not None: img = self.transform(img) return img,label def __len__(self): return len(self.imgs) train_data = MyDataset(txt= root + 'train.txt', transform = torchvision.transforms.ToTensor()) train_loader = DataLoader(dataset = train_data, batch_size=BATCH_SIZE, shuffle=True) test_data = MyDataset(txt= root + 'test.txt', transform = torchvision.transforms.ToTensor()) test_loader = DataLoader(dataset = test_data, batch_size=BATCH_SIZE) class CNN(nn.Module): def __init__(self): super(CNN, self).__init__() self.conv1 = nn.Sequential( # input shape (1, 28, 28) nn.Conv2d( in_channels=1, # input height out_channels=16, # n_filters kernel_size=5, # filter size stride=1, # filter movement/step padding=2, # if want same width and length of this image after con2d, padding=(kernel_size-1)/2 if stride=1 ), # output shape (16, 28, 28) nn.ReLU(), # activation nn.MaxPool2d(kernel_size=2), # choose max value in 2x2 area, output shape (16, 14, 14) ) self.conv2 = nn.Sequential( # input shape (16, 14, 14) nn.Conv2d(16, 32, 5, 1, 2), # output shape (32, 14, 14) nn.ReLU(), # activation nn.MaxPool2d(2), # output shape (32, 7, 7) ) self.out = nn.Linear(32 * 7 * 7, 10) # fully connected layer, output 10 classes def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = x.view(x.size(0), -1) # flatten the output of conv2 to (batch_size, 32 * 7 * 7) output = self.out(x) return output, x # return x for visualization cnn = CNN() print(cnn) # net architecture optimizer = torch.optim.Adam(cnn.parameters(), lr=LR) # optimize all cnn parameters loss_func = nn.CrossEntropyLoss() # the target label is not one-hotted # training and testing for epoch in range(EPOCH): for step, (x, y) in enumerate(train_loader): # gives batch data, normalize x when iterate train_loader b_x = Variable(x) # batch x b_y = Variable(y) # batch y output = cnn(b_x)[0] # cnn output loss = loss_func(output, b_y) # cross entropy loss optimizer.zero_grad() # clear gradients for this training step loss.backward() # backpropagation, compute gradients optimizer.step() # apply gradients if step % 50 == 0: cnn.eval() eval_loss = 0. eval_acc = 0. for i, (tx, ty) in enumerate(test_loader): t_x = Variable(tx) t_y = Variable(ty) output = cnn(t_x)[0] loss = loss_func(output, t_y) eval_loss += loss.data[0] pred = torch.max(output, 1)[1] num_correct = (pred == t_y).sum() eval_acc += float(num_correct.data[0]) acc_rate = eval_acc / float(len(test_data)) print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss / (len(test_data)), acc_rate))
图片和label 见上一篇文章《pytorch 把MNIST数据集转换成图片和txt》
结果如下:
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。
华山资源网 Design By www.eoogi.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
华山资源网 Design By www.eoogi.com
暂无评论...
RTX 5090要首发 性能要翻倍!三星展示GDDR7显存
三星在GTC上展示了专为下一代游戏GPU设计的GDDR7内存。
首次推出的GDDR7内存模块密度为16GB,每个模块容量为2GB。其速度预设为32 Gbps(PAM3),但也可以降至28 Gbps,以提高产量和初始阶段的整体性能和成本效益。
据三星表示,GDDR7内存的能效将提高20%,同时工作电压仅为1.1V,低于标准的1.2V。通过采用更新的封装材料和优化的电路设计,使得在高速运行时的发热量降低,GDDR7的热阻比GDDR6降低了70%。
更新日志
2024年09月21日
2024年09月21日
- 【雨果唱片】陈百强《梦里人LPCD45》2012[WAV+CUE]
- 《黑神话》纪录片9月20日上线!揭秘关卡为何删减
- 游戏科学估值已和育碧市值相当:后者有两万多名员工
- 黑神话第81周目Boss伤害有多恐怖?起手伤害直接秒
- 群星.2009-原班情歌2CD【SONY】【WAV+CUE】
- 群星.2024-长乐曲电视剧原声带【TME影音】【FLAC分轨】
- 群星.1993-烧得厉害VOL.1好戏好歌唱不停【滚石】【WAV+CUE】
- 那英《幸福的泪 磁性和爆发力完美展现 2CD》[WAV/分轨][600MB]
- 《宝丽金辉煌60年 女人篇3CD》[WAV+CUE][1.5G]
- 《年度十大发烧唱片精选 唱片榜获奖作品 2CD》[WAV/分轨][1GB]
- 归龙潮三枚天灯碎片位置在哪 笼律鸟任务天灯图文位置
- 归龙潮新手开荒阵容怎么搭配 新手前期阵容养成攻略
- 归龙潮中浦城区福鼠位置在哪 中浦城区福鼠收集位置大全
- MatteoPasqualini-JohannSebastianBachItalienischesKonzertFranzsischeOuvertureVierDue
- 【雨果唱片】陈百强《梦里人LPCD45》2012[WAV+CUE]