用python编写的，基于tensorflow深度学习的框架的手写数字识别的完整代码，有注释，可运行，无bug
2019-12-21 20:53:03
36.61MB
1
构建CNN
LayerBuilder builder = new LayerBuilder();
builder.addLayer(Layer.buildInputLayer(new Size(28, 28)));
builder.addLayer(Layer.buildConvLayer(6, new Size(5, 5)));
builder.addLayer(Layer.buildSampLayer(new Size(2, 2)));
builder.addLayer(Layer.buildConvLayer(12, new Size(5, 5)));
builder.addLayer(Layer.buildSampLayer(new Size(2, 2)));
builder.addLayer(Layer.buildOutputLayer(10));
CNN cnn = new CNN(builder, 50);
运行MNIST数据集
String fileName = "data/train.format";
Dataset dataset = Dataset.load(fileName, ",", 784);
cnn.train(dataset, 100);
Dataset testset = Dataset.load("data/test.format", ",", -1);
cnn.predict(testset, "data/test.predict");
计算精度可以达到97.8%。
2019-12-21 20:51:47
1.87MB
1
包括mnist数据集文件，输入数据的python代码，深度分类mnist代码，softmax函数代码以及整合的内含详细代码解释的mnist_with_summaries代码
2019-12-21 20:49:09
13.1MB
1
深度学习常用数据集之一，fashion-mnist数据集，可看成是mnist数据集的升级版，数据的属性和mnist数据集一样（测试集和训练集的样本数）
2019-12-21 20:49:03
34.62MB
1