关于Future的未捕获异常：通用conv实现暂时不支持分组卷积

Question

E/TensorFlowInferenceInterface: Failed to run TensorFlow inference with inputs:[conv2d_1_input], outputs:[dense_2/Softmax]
Uncaught exception on Future: Generic conv implementation does not support grouped convolutions for now.      

我试图更改节点名称并运行模型，甚至尝试重新训练模型。我用于我的应用的基本分类器功能。

我正在Android Studio中使用Keras 2.2.4和Tensorflow 1.13.1，并生成.pb文件。

问题：在“运行推理调用”处。

public List<Classifier.Recognize> recognizeImage(Bitmap bitmap) {
        // Log this method so that it can be analyzed with systrace.
        Trace.beginSection("recognizeImage");

        Trace.beginSection("preprocessBitmap");
        // Preprocess the image data from 0-255 int to normalized float based
        // on the provided parameters.
        bitmap.getPixels(intValues, 0, bitmap.getWidth(), 0, 0, bitmap.getWidth(), bitmap.getHeight());
        for (int i = 0; i < intValues.length; ++i) {
            final int val = intValues[i];
            floatValues[i * 3 + 0] = (((val >> 16) & 0xFF) - imageMean) / imageStd;
            floatValues[i * 3 + 1] = (((val >> 8) & 0xFF) - imageMean) / imageStd;
            floatValues[i * 3 + 2] = ((val & 0xFF) - imageMean) / imageStd;
        }
        Trace.endSection();

        // Copy the input data into TensorFlow.
        Trace.beginSection("feed");
        tensorFlowInferenceInterface.feed(inputName, floatValues, 1, inputsize, inputsize, 3);
        Trace.endSection();

        // Run the inference call.
        Trace.beginSection("run");
        tensorFlowInferenceInterface.run(outputNames, logstats);
        Trace.endSection();

        // Copy the output Tensor back into the output array.
        Trace.beginSection("fetch");
        tensorFlowInferenceInterface.fetch(outputName, outputs);
        Trace.endSection();

        // Find the best classifications.
        PriorityQueue<Recognize> pq =
                new PriorityQueue<Recognize>(
                        3,
                        new Comparator<Recognize>() {
                            @Override
                            public int compare(Recognize lhs, Recognize rhs) {
                                // Intentionally reversed to put high confidence at the head of the queue.
                                return Float.compare(rhs.getGestureConfidence(), lhs.getGestureConfidence());
                            }
                        });
        for (int i = 0; i < outputs.length; ++i) {
            if (outputs[i] > THRESHOLD) {
                pq.add(new Recognize("" + i, labels.size() > i ? labels.get(i) : "unknown", outputs[i]));
            }
        }
        final ArrayList<Recognize> recognitions = new ArrayList<Recognize>();
        int recognitionsSize = Math.min(pq.size(), MAX_RESULTS);
        for (int i = 0; i < recognitionsSize; ++i) {
            recognitions.add(pq.poll());
        }
        Trace.endSection(); // "recognizeImage"
        return recognitions;
    }

我希望将位图图像发送到网络，分类器应该开始进行比较的过程。