// Do one forward pass of convTrans layer and check to see if its output // matches the given result void doOneConvtTest(size_t imgSize, size_t output_x, size_t stride, size_t padding, size_t filter_size, MatrixPtr& result) { TestConfig configt; configt.biasSize = 1; configt.layerConfig.set_type("exconvt"); configt.layerConfig.set_num_filters(1); configt.layerConfig.set_partial_sum(1); configt.layerConfig.set_shared_biases(true); configt.inputDefs.push_back( {INPUT_DATA, "layer_0", output_x * output_x, filter_size * filter_size}); LayerInputConfig* input = configt.layerConfig.add_inputs(); ConvConfig* conv = input->mutable_conv_conf(); conv->set_filter_size(filter_size); conv->set_filter_size_y(filter_size); conv->set_channels(1); conv->set_padding(padding); conv->set_padding_y(padding); conv->set_stride(stride); conv->set_stride_y(stride); conv->set_groups(1); conv->set_filter_channels(1); conv->set_img_size(imgSize); conv->set_output_x(output_x); configt.layerConfig.set_size(conv->img_size() * conv->img_size() * configt.layerConfig.num_filters()); configt.layerConfig.set_name("convTrans"); std::vector<DataLayerPtr> dataLayers; LayerMap layerMap; vector<Argument> datas; initDataLayer( configt, &dataLayers, &datas, &layerMap, "convTrans", 1, false, false); dataLayers[0]->getOutputValue()->zeroMem(); dataLayers[0]->getOutputValue()->add(1.0); // test layer initialize std::vector<ParameterPtr> parameters; LayerPtr convtLayer; initTestLayer(configt, &layerMap, ¶meters, &convtLayer); convtLayer->getBiasParameter()->zeroMem(); convtLayer->getParameters()[0]->zeroMem(); convtLayer->getParameters()[0]->getBuf(PARAMETER_VALUE)->add(1.0); convtLayer->forward(PASS_GC); checkMatrixEqual(convtLayer->getOutputValue(), result); }
// Do one forward pass of priorBox layer and check to see if its output // matches the given result void doOnePriorBoxTest(size_t feature_map_width, size_t feature_map_height, size_t image_width, size_t image_height, vector<int> min_size, vector<int> max_size, vector<real> aspect_ratio, vector<real> variance, bool use_gpu, MatrixPtr& result) { // Setting up the priorbox layer TestConfig configt; configt.layerConfig.set_type("priorbox"); configt.inputDefs.push_back({INPUT_DATA, "featureMap", 1, 0}); LayerInputConfig* input = configt.layerConfig.add_inputs(); configt.inputDefs.push_back({INPUT_DATA, "image", 1, 0}); configt.layerConfig.add_inputs(); PriorBoxConfig* pb = input->mutable_priorbox_conf(); for (size_t i = 0; i < min_size.size(); i++) pb->add_min_size(min_size[i]); for (size_t i = 0; i < max_size.size(); i++) pb->add_max_size(max_size[i]); for (size_t i = 0; i < variance.size(); i++) pb->add_variance(variance[i]); for (size_t i = 0; i < aspect_ratio.size(); i++) pb->add_aspect_ratio(aspect_ratio[i]); // data layer initialize std::vector<DataLayerPtr> dataLayers; LayerMap layerMap; vector<Argument> datas; initDataLayer( configt, &dataLayers, &datas, &layerMap, "priorbox", 1, false, use_gpu); dataLayers[0]->getOutput().setFrameHeight(feature_map_height); dataLayers[0]->getOutput().setFrameWidth(feature_map_width); dataLayers[1]->getOutput().setFrameHeight(image_height); dataLayers[1]->getOutput().setFrameWidth(image_width); // test layer initialize std::vector<ParameterPtr> parameters; LayerPtr priorboxLayer; initTestLayer(configt, &layerMap, ¶meters, &priorboxLayer); priorboxLayer->forward(PASS_GC); checkMatrixEqual(priorboxLayer->getOutputValue(), result); }
LayerPtr createCTCLayer(string name, size_t numClasses, bool useGpu, bool normByTimes, LayerPtr dataLayer, LayerPtr labelLayer) { LayerMap layerMap; layerMap[dataLayer->getName()] = dataLayer; layerMap[labelLayer->getName()] = labelLayer; ParameterMap parameterMap; LayerConfig layerConfig; layerConfig.set_name(name); layerConfig.set_type("ctc"); layerConfig.set_size(numClasses); layerConfig.set_norm_by_times(normByTimes); layerConfig.add_inputs(); LayerInputConfig& input0 = *(layerConfig.mutable_inputs(0)); input0.set_input_layer_name(dataLayer->getName()); layerConfig.add_inputs(); LayerInputConfig& input1 = *(layerConfig.mutable_inputs(1)); input1.set_input_layer_name(labelLayer->getName()); LayerPtr layer = LayerPtr(new CTCLayer(layerConfig)); layerMap[layer->getName()] = layer; layer->init(layerMap, parameterMap); ActivationFunction* softmaxActivation = ActivationFunction::create("softmax"); softmaxActivation->forward(dataLayer->getOutput()).check(); layer->forward(PASS_GC); layer->backward(); softmaxActivation->backward(dataLayer->getOutput()).check(); return layer; }
LayerPtr createWarpCTCLayer(string name, size_t numClasses, bool useGpu, bool normByTimes, LayerPtr dataLayer, LayerPtr labelLayer) { LayerMap layerMap; layerMap[dataLayer->getName()] = dataLayer; layerMap[labelLayer->getName()] = labelLayer; ParameterMap parameterMap; LayerConfig layerConfig; layerConfig.set_name(name); layerConfig.set_type("warp_ctc"); layerConfig.set_size(numClasses); layerConfig.set_blank(numClasses - 1); layerConfig.set_norm_by_times(normByTimes); layerConfig.add_inputs(); LayerInputConfig& input0 = *(layerConfig.mutable_inputs(0)); input0.set_input_layer_name(dataLayer->getName()); layerConfig.add_inputs(); LayerInputConfig& input1 = *(layerConfig.mutable_inputs(1)); input1.set_input_layer_name(labelLayer->getName()); LayerPtr layer = LayerPtr(new WarpCTCLayer(layerConfig)); layerMap[layer->getName()] = layer; layer->init(layerMap, parameterMap); layer->forward(PASS_GC); layer->backward(); return layer; }
// Test that the convTrans forward is the same as conv backward TEST(Layer, convTransLayerFwd) { // Setting up conv-trans layer TestConfig configt; configt.biasSize = 3; configt.layerConfig.set_type("exconvt"); configt.layerConfig.set_num_filters(3); configt.layerConfig.set_partial_sum(1); configt.layerConfig.set_shared_biases(true); configt.inputDefs.push_back({INPUT_DATA, "layer_0", 1024, 384}); LayerInputConfig* input = configt.layerConfig.add_inputs(); ConvConfig* conv = input->mutable_conv_conf(); conv->set_filter_size(2); conv->set_filter_size_y(4); conv->set_channels(16); conv->set_padding(0); conv->set_padding_y(1); conv->set_stride(2); conv->set_stride_y(2); conv->set_groups(1); conv->set_filter_channels(3 / conv->groups()); conv->set_img_size(16); conv->set_output_x(outputSize(conv->img_size(), conv->filter_size(), conv->padding(), conv->stride(), /* caffeMode */ true)); configt.layerConfig.set_size(conv->img_size() * conv->img_size() * configt.layerConfig.num_filters()); configt.layerConfig.set_name("convTrans"); // data layer initialize std::vector<DataLayerPtr> dataLayers; LayerMap layerMap; vector<Argument> datas; initDataLayer(configt, &dataLayers, &datas, &layerMap, "convTrans", 100, false, false); // test layer initialize std::vector<ParameterPtr> parameters; LayerPtr convtLayer; initTestLayer(configt, &layerMap, ¶meters, &convtLayer); convtLayer->getBiasParameter()->zeroMem(); convtLayer->forward(PASS_GC); // Setting up conv-layer config TestConfig config; config.biasSize = 16; config.layerConfig.set_type("exconv"); config.layerConfig.set_num_filters(16); config.layerConfig.set_partial_sum(1); config.layerConfig.set_shared_biases(true); config.inputDefs.push_back({INPUT_DATA, "layer_1", 768, 384}); input = config.layerConfig.add_inputs(); conv = input->mutable_conv_conf(); conv->set_filter_size(2); conv->set_filter_size_y(4); conv->set_channels(3); conv->set_padding(0); conv->set_padding_y(1); conv->set_stride(2); conv->set_stride_y(2); conv->set_groups(1); conv->set_filter_channels(conv->channels() / conv->groups()); conv->set_img_size(16); conv->set_output_x(outputSize(conv->img_size(), conv->filter_size(), conv->padding(), conv->stride(), /* caffeMode */ true)); config.layerConfig.set_size(conv->output_x() * conv->output_x() * config.layerConfig.num_filters()); config.layerConfig.set_name("conv"); // data layer initialize std::vector<DataLayerPtr> dataLayers2; LayerMap layerMap2; vector<Argument> datas2; initDataLayer(config, &dataLayers2, &datas2, &layerMap2, "conv", 100, false, false); // test layer initialize std::vector<ParameterPtr> parameters2; LayerPtr convLayer; initTestLayer(config, &layerMap2, ¶meters2, &convLayer); // Sync convLayer and convtLayer parameter convLayer->getBiasParameter()->zeroMem(); convLayer->getParameters()[0]->getBuf(PARAMETER_VALUE)->copyFrom( *(convtLayer->getParameters()[0]->getBuf(PARAMETER_VALUE))); // Set convLayer outputGrad as convTransLayer input value convLayer->forward(PASS_GC); convLayer->getOutput().grad->copyFrom(*(dataLayers[0]->getOutputValue())); vector<int> callbackFlags(parameters2.size(), 0); auto callback = [&](Parameter* para) { ++callbackFlags[para->getID()]; }; convLayer->backward(callback); // Check that the convLayer backward is the same as convTransLayer forward checkMatrixEqual(convtLayer->getOutputValue(), dataLayers2[0]->getOutputGrad()); }