全卷积网络

Question

TensorFlow.js版本

tfjs-节点-gpu 0.2.1

描述问题或特性请求

我试图建立一个有监督的、完全卷积的网络，但无法产生适当的输出。net结构基于几个FCN示例，特别是这个示例：segm.html。

我把掩码放在一个单热的4d布尔向量中，它的顺序是批处理，高度，宽度，类，只有一个类。输入数据被修改为float32张量的批次，高度，宽度，1，范围为0到1。

数据在这里，并来自上面的同一教程：60jvsCt1hZWNfcW4wbHE5N3M/view

        const input = tf.input({ shape: [this._dims[1], this._dims[2], this._dims[3]], name: 'Input', });

        const batchNorm_0 = tf.layers.batchNormalization().apply(input);
        //**Begin A-Scan Net*/
        const fcn_1_0 = tf.layers.conv2d( { name: '', kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64,  } ).apply(input);
        const fcn_2 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_1_0);

        const fcn_3_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_2);
        const fcn_3_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_3_0);
        const fcn_3_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_3_1);
        const fcn_4 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_3_2);

        const fcn_5_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_4);
        const fcn_5_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_5_0);
        const fcn_5_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_5_1);
        const fcn_6 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_5_2);

        const fcn_7_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_6);
        const fcn_7_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_7_0);
        const fcn_7_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_7_1);
        const fcn_8 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_7_2);

        const fcn_9_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_8);
        const fcn_9_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_9_0);
        const fcn_9_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_9_1);
        const fcn_10 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_9_2);

        const fcn_11 = tf.layers.conv2d({ kernelSize: [1, 1], strides: [1, 1], activation: 'relu', padding: 'same', filters: 2048 }).apply(fcn_10);

        const fcn_12 = tf.layers.conv2d({ kernelSize: [1, 1], strides: [1, 1], activation: 'relu', padding: 'same', filters: this._classes }).apply(fcn_11);

        const upsample_5 = tf.layers.conv2dTranspose( { kernelSize: [32, 32], strides: [32, 32], filters: this._classes, activation: 'relu', padding: 'same' } ).apply(fcn_12);
        const upsample_6 = tf.layers.conv2d( { kernelSize: [1, 1], strides: [1, 1], filters: this._classes, activation: 'softmax', padding: 'same' } ).apply(upsample_5);

        var model = tf.model( { name: 'AdvancedCNN', inputs: [input], outputs: [upsample_6] } );

损失/计量/优化器是：

        const LEARNING_RATE = .00001;
        const optimizer = tf.train.adam(LEARNING_RATE)
        model.compile({
            optimizer,
            loss: tf.losses.logLoss,
            metrics: tf.metrics.categoricalCrossentropy,
        });

问题是，网络没有学习，输出类要么是全部0，要么是全部1，即使经过多个时代之后。我试过有和没有批处理规范和改变学习率。数据看起来很好，所以要么我格式化数据错误，要么是丢失函数、标签结构等出现了问题。

其他人是否使用TensorFlow.js构建了一个FCN？

Answer 1

我解决了这个问题。我用upSampling2d和conv2d层交换了upSampling2d。掩码的一次热编码和丢失函数的tf.losses.softmaxCrossEntropy一样是足够的。

最后，将图像调整为256x512有助于加快培训时间。起作用的最后一个网状结构(超级原始网络，所以可以随意使用它)是：

        const fcn_1_0 = tf.layers.conv2d( { name: '', kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64, } ).apply(input);
        const fcn_1_1 = tf.layers.conv2d( { name: '', kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64,  } ).apply(fcn_1_0);
        const fcn_1_2 = tf.layers.conv2d( { name: '', kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64,  } ).apply(fcn_1_1);
        const fcn_2 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_1_2);

        const fcn_3_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_2);
        const fcn_3_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_3_0);
        const fcn_3_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_3_1);
        const fcn_4 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_3_2);

        const fcn_5_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_4);
        const fcn_5_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_5_0);
        const fcn_5_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_5_1);
        const fcn_6 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_5_2);

        const fcn_7_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_6);
        const fcn_7_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_7_0);
        const fcn_7_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_7_1);
        const fcn_8 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_7_2);

        const fcn_9_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_8);
        const fcn_9_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_9_0);
        const fcn_9_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_9_1);
        const fcn_10 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_9_2);

        // const fcn_11_0 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_10);
        // const fcn_11_1 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_11_0);
        // const fcn_11_2 = tf.layers.conv2d( { kernelSize: [3, 3], strides: [1, 1], activation: 'relu', padding: 'same', filters: 64 } ).apply(fcn_11_1);
        // const fcn_12 = tf.layers.maxPool2d( { kernelSize: [2, 2], strides: [2, 2] } ).apply(fcn_11_2);

        //const fcn_13 = tf.layers.conv2d({ kernelSize: [7, 7], strides: [1, 1], activation: 'relu', padding: 'same', filters: 4096 }).apply(fcn_12);
        const fcn_13_0 = tf.layers.conv2d({ kernelSize: [1, 1], strides: [1, 1], activation: 'relu', padding: 'same', filters: 4096 }).apply(fcn_10);
        //const drop_0 = tf.layers.dropout( { rate: .5 } ).apply(fcn_13);

        //const fcn_15 = tf.layers.conv2d({ kernelSize: [1, 1], strides: [1, 1], activation: 'relu', padding: 'same', filters: this._classes }).apply(fcn_13_0);

        const upsample_1 = tf.layers.upSampling2d( { size: [2, 2], padding: 'same' } ).apply(fcn_13_0);
        const conv_upsample1 = tf.layers.conv2d( { kernelSize: 3, strides: 1, activation: 'relu', padding: 'same', filters: 64 }).apply(upsample_1);

        const upsample_2 = tf.layers.upSampling2d( { size: [2, 2], padding: 'same' } ).apply(conv_upsample1);
        const conv_upsample2 = tf.layers.conv2d( { kernelSize: 3, strides: 1, activation: 'relu', padding: 'same', filters: 64 }).apply(upsample_2);

        const upsample_3 = tf.layers.upSampling2d( { size: [2, 2], padding: 'same' } ).apply(conv_upsample2);
        const conv_upsample3 = tf.layers.conv2d( { kernelSize: 3, strides: 1, activation: 'relu', padding: 'same', filters: 64 }).apply(upsample_3);

        const upsample_4 = tf.layers.upSampling2d( { size: [2, 2], padding: 'same' } ).apply(conv_upsample3);
        const conv_upsample4 = tf.layers.conv2d( { kernelSize: 3, strides: 1, activation: 'relu', padding: 'same', filters: 64 }).apply(upsample_4);

        const upsample_5 = tf.layers.upSampling2d( { size: [2, 2], padding: 'same' } ).apply(conv_upsample4);
        const conv_upsample5 = tf.layers.conv2d( { kernelSize: 3, strides: 1, activation: 'relu', padding: 'same', filters: 64 }).apply(upsample_5);

        //const upsample_6 = tf.layers.upSampling2d( { size: [2, 2], padding: 'same' } ).apply(fcn_15);
        const conv_upsample = tf.layers.conv2dTranspose( { kernelSize: 1, strides: 1, activation: 'softmax', padding: 'same', filters: this._classes }).apply(conv_upsample5);

Answer 2

在完全CNN卷积神经网络中，最后一层是稠密层或完全连通层。它是从稠密的层，计算软件最大的激活。目前，您的NN神经网络体系结构缺少这样一个层，其中您无法得到正确的分类。

实际上，这是最后一层，使用卷积层学习到的不同特征进行分类的稠密层。

唯一要指出的是，您可能需要在密集层的入口处使用扁平层--仅用于尺寸匹配。

更新:对最后一层使用上采样层的可能会减少损失。我认为问题与转置层有关。这个文章解释了什么是重采样