小编Mur*_*nat的帖子

Keras准确度不会改变

我有几千个音频文件,我想用Keras和Theano对它们进行分类.到目前为止,我生成了每个音频文件的28x28频谱图(更大可能更好,但我只是想让算法工作),并将图像读入矩阵.所以最后我将这个大图像矩阵输入网络进行图像分类.

在教程中,我发现了这个mnist分类代码:

import numpy as np

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epochs = 2

(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255

print(X_train.shape[0], "train samples")
print(X_test.shape[0], "test samples")

y_train = np_utils.to_categorical(y_train, nb_classes)
y_test =  np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Dense(output_dim = 100, input_dim = 784, …

Run Code Online (Sandbox Code Playgroud)

python audio machine-learning theano keras

Mur*_*nat

2016 05-15

31
推荐指数

6
解决办法

5万
查看次数

Three.js - TypeError: THREE.Scene 不是构造函数

我只是在尝试 Three.js，所以我可以将它实现到我的项目中，但是当我运行文档中的第一个示例时：

<html>
    <head>
        <title>My first Three.js app</title>
        <style>
            body { margin: 0; }
            canvas { width: 100%; height: 100% }
        </style>
    </head>
    <body>
        <script src="three.js"></script>        
        <script>
            var scene = new THREE.Scene();
            var camera = new THREE.PerspectiveCamera( 75, window.innerWidth/window.innerHeight, 0.1, 1000 );

            var renderer = new THREE.WebGLRenderer();
            renderer.setSize( window.innerWidth, window.innerHeight );
            document.body.appendChild( renderer.domElement );

            var geometry = new THREE.BoxGeometry( 1, 1, 1 );
            var material = new THREE.MeshBasicMaterial( { color: 0x00ff00 } );
            var cube = new THREE.Mesh( geometry, material …

Run Code Online (Sandbox Code Playgroud)

html javascript three.js

Mur*_*nat

2016 08-23

5
推荐指数

2
解决办法

2万
查看次数