Tensorflow Lite - 输入形状必须是 5 维错误

Question

我正在尝试将 tensorflow 模型移植到 tensorflow lite 以在 android 应用程序中使用它。转换成功，除了 Internal error: Failed to run on the given Interpreter: input must be 5-dimensional 之外的所有内容都在运行。原始模型中的输入是 input_shape=(20, 320, 240, 1)，即 20 320 x 240 灰度图像（因此 ...,1）。这是重要的代码：

List<Mat> preprocessedFrames = preprocFrames(buf);
//has length of 20 -> no problem there (shouldn't affect dimensionality either...)

        int[] output = new int[2];
        float[][][] inputMatrices = new float[preprocessedFrames.toArray().length][320][240];

        for(int i = 0; i < preprocessedFrames.toArray().length; i++) {
            Mat inpRaw = preprocessedFrames.get(i);

            Bitmap data = Bitmap.createBitmap(inpRaw.cols(), inpRaw.rows(), Bitmap.Config.ARGB_8888);
            Utils.matToBitmap(inpRaw, data);

            int[][] pixels = pixelsFromBitmap(data);
            float[][] inputMatrix = inputMatrixFromIntPixels(pixels);
            // returns float[][] with floats from 0 to 1

            inputMatrices[i] = inputMatrix;
        }

        try{

            detector.run(inputMatrices, output);
            Debug("results: " + output.toString());
        }

该模型为我提供了 2 个神经元的输出，转换为 2 个标签。型号代码如下：

model = tf.keras.Sequential(name='detector')
    model.add(tf.keras.layers.Conv3D(filters=(56), input_shape=(20, 320, 240, 1), strides=(2,2,2), kernel_size=(3,11,11), padding='same', activation="relu"))
    model.add(tf.keras.layers.AveragePooling3D(pool_size=(1,4,4)))
    model.add(tf.keras.layers.Conv3D(filters=(72), kernel_size=(4,7,7), strides=(1,2,2), padding='same'))
    model.add(tf.keras.layers.Conv3D(filters=(81), kernel_size=(2,4,4), strides=(2,2,2), padding='same'))
    model.add(tf.keras.layers.Conv3D(filters=(100), kernel_size=(1,2,2), strides=(3,2,2), padding='same'))
    model.add(tf.keras.layers.Conv3D(filters=(128), kernel_size=(1,2,2), padding='same'))
    model.add(tf.keras.layers.Flatten())
    model.add(tf.keras.layers.Dense(768, activation='tanh', kernel_regularizer=tf.keras.regularizers.l2(0.011)))
    model.add(tf.keras.layers.Dropout(rate=0.1))
    model.add(tf.keras.layers.Dense(256, activation='sigmoid', kernel_regularizer=tf.keras.regularizers.l2(0.012)))
    model.add(tf.keras.layers.Dense(2, activation='softmax'))

    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.00001), loss=tf.keras.losses.CategoricalCrossentropy(),
        metrics=['accuracy'])

编辑：我打印出第一个输入张量如下：

int[] shape = detector.getInputTensor(0).shape();
            for(int r = 0; r < shape.length; r++){
                Log.d("********" + r, "*******: " + r + " : " + shape[r]);
            }

我首先得到输出 [1,20,320,240,1]，然后我只得到 [20,320,240]。我现在真的很绝望...

Answer 1

所以，我自己弄明白了，看起来我真的只需要通过将内容放入第一维并将每个像素放入第五维来使输入成为 5 维。我不知道为什么，但我会接受 xD。

float[][] output = new float[1][2];
            float[][][][][] inputMatrices = new float[1][preprocessedFrames.toArray().length][320][240][1];

            for(int i = 0; i < preprocessedFrames.toArray().length; i++) {
                Mat inpRaw = preprocessedFrames.get(i);

                Bitmap data = Bitmap.createBitmap(inpRaw.cols(), inpRaw.rows(), Bitmap.Config.ARGB_8888);
                Utils.matToBitmap(inpRaw, data);

                int[][] pixels = pixelsFromBitmap(data);
                float[][] inputMatrix = inputMatrixFromIntPixels(pixels);

                for (int j = 0; j < inputMatrix.length - 1; j++) {
                    for(int k = 0; k < inputMatrix[0].length - 1; k++) {
                        inputMatrices[0][i][k][j][0] = inputMatrix[j][k];
                    }
                }
            }

Tensorflow Lite - 输入形状必须是 5 维错误

Tensorflow Lite - Input shape must be 5 dimensional error

android

tensorflow-lite

tensorflow2.0