From b78dc27bba2cc612643df7e9c84addc142273e71 Mon Sep 17 00:00:00 2001 From: "Guo, Yejun" Date: Wed, 9 Oct 2019 22:08:04 +0800 Subject: [PATCH] avfilter/dnn: add DLT prefix for enum DNNLayerType to avoid potential conflicts and also change CONV to DLT_CONV2D for better description Signed-off-by: Guo, Yejun Signed-off-by: Pedro Arthur --- libavfilter/dnn/dnn_backend_native.c | 25 +++++++++++-------------- libavfilter/dnn/dnn_backend_native.h | 12 +++++++++++- libavfilter/dnn/dnn_backend_tf.c | 10 +++++----- 3 files changed, 27 insertions(+), 20 deletions(-) diff --git a/libavfilter/dnn/dnn_backend_native.c b/libavfilter/dnn/dnn_backend_native.c index 68fca50e76..97549d3077 100644 --- a/libavfilter/dnn/dnn_backend_native.c +++ b/libavfilter/dnn/dnn_backend_native.c @@ -188,8 +188,9 @@ DNNModel *ff_dnn_load_model_native(const char *model_filename) for (layer = 0; layer < network->layers_num; ++layer){ layer_type = (int32_t)avio_rl32(model_file_context); dnn_size += 4; + network->layers[layer].type = layer_type; switch (layer_type){ - case CONV: + case DLT_CONV2D: conv_params = av_malloc(sizeof(ConvolutionalParams)); if (!conv_params){ avio_closep(&model_file_context); @@ -231,10 +232,9 @@ DNNModel *ff_dnn_load_model_native(const char *model_filename) network->layers[layer].input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context); network->layers[layer].output_operand_index = (int32_t)avio_rl32(model_file_context); dnn_size += 8; - network->layers[layer].type = CONV; network->layers[layer].params = conv_params; break; - case DEPTH_TO_SPACE: + case DLT_DEPTH_TO_SPACE: depth_to_space_params = av_malloc(sizeof(DepthToSpaceParams)); if (!depth_to_space_params){ avio_closep(&model_file_context); @@ -246,10 +246,9 @@ DNNModel *ff_dnn_load_model_native(const char *model_filename) network->layers[layer].input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context); network->layers[layer].output_operand_index = (int32_t)avio_rl32(model_file_context); dnn_size += 8; - network->layers[layer].type = DEPTH_TO_SPACE; network->layers[layer].params = depth_to_space_params; break; - case MIRROR_PAD: + case DLT_MIRROR_PAD: pad_params = av_malloc(sizeof(LayerPadParams)); if (!pad_params){ avio_closep(&model_file_context); @@ -266,10 +265,9 @@ DNNModel *ff_dnn_load_model_native(const char *model_filename) network->layers[layer].input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context); network->layers[layer].output_operand_index = (int32_t)avio_rl32(model_file_context); dnn_size += 8; - network->layers[layer].type = MIRROR_PAD; network->layers[layer].params = pad_params; break; - case MAXIMUM: + case DLT_MAXIMUM: maximum_params = av_malloc(sizeof(*maximum_params)); if (!maximum_params){ avio_closep(&model_file_context); @@ -278,7 +276,6 @@ DNNModel *ff_dnn_load_model_native(const char *model_filename) } maximum_params->val.u32 = avio_rl32(model_file_context); dnn_size += 4; - network->layers[layer].type = MAXIMUM; network->layers[layer].params = maximum_params; network->layers[layer].input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context); network->layers[layer].output_operand_index = (int32_t)avio_rl32(model_file_context); @@ -347,27 +344,27 @@ DNNReturnType ff_dnn_execute_model_native(const DNNModel *model, DNNData *output for (layer = 0; layer < network->layers_num; ++layer){ switch (network->layers[layer].type){ - case CONV: + case DLT_CONV2D: conv_params = (ConvolutionalParams *)network->layers[layer].params; convolve(network->operands, network->layers[layer].input_operand_indexes, network->layers[layer].output_operand_index, conv_params); break; - case DEPTH_TO_SPACE: + case DLT_DEPTH_TO_SPACE: depth_to_space_params = (DepthToSpaceParams *)network->layers[layer].params; depth_to_space(network->operands, network->layers[layer].input_operand_indexes, network->layers[layer].output_operand_index, depth_to_space_params->block_size); break; - case MIRROR_PAD: + case DLT_MIRROR_PAD: pad_params = (LayerPadParams *)network->layers[layer].params; dnn_execute_layer_pad(network->operands, network->layers[layer].input_operand_indexes, network->layers[layer].output_operand_index, pad_params); break; - case MAXIMUM: + case DLT_MAXIMUM: maximum_params = (DnnLayerMaximumParams *)network->layers[layer].params; dnn_execute_layer_maximum(network->operands, network->layers[layer].input_operand_indexes, network->layers[layer].output_operand_index, maximum_params); break; - case INPUT: + case DLT_INPUT: return DNN_ERROR; } } @@ -408,7 +405,7 @@ void ff_dnn_free_model_native(DNNModel **model) { network = (ConvolutionalNetwork *)(*model)->model; for (layer = 0; layer < network->layers_num; ++layer){ - if (network->layers[layer].type == CONV){ + if (network->layers[layer].type == DLT_CONV2D){ conv_params = (ConvolutionalParams *)network->layers[layer].params; av_freep(&conv_params->kernel); av_freep(&conv_params->biases); diff --git a/libavfilter/dnn/dnn_backend_native.h b/libavfilter/dnn/dnn_backend_native.h index 3f2840c8fd..761e5ed02c 100644 --- a/libavfilter/dnn/dnn_backend_native.h +++ b/libavfilter/dnn/dnn_backend_native.h @@ -30,7 +30,17 @@ #include "../dnn_interface.h" #include "libavformat/avio.h" -typedef enum {INPUT = 0, CONV = 1, DEPTH_TO_SPACE = 2, MIRROR_PAD = 3, MAXIMUM = 4} DNNLayerType; +/** + * the enum value of DNNLayerType should not be changed, + * the same values are used in convert_from_tensorflow.py + */ +typedef enum { + DLT_INPUT = 0, + DLT_CONV2D = 1, + DLT_DEPTH_TO_SPACE = 2, + DLT_MIRROR_PAD = 3, + DLT_MAXIMUM = 4 +} DNNLayerType; typedef enum {DOT_INPUT = 1, DOT_OUTPUT = 2, DOT_INTERMEDIATE = DOT_INPUT | DOT_INPUT} DNNOperandType; diff --git a/libavfilter/dnn/dnn_backend_tf.c b/libavfilter/dnn/dnn_backend_tf.c index 612d2e0982..c8dff51744 100644 --- a/libavfilter/dnn/dnn_backend_tf.c +++ b/libavfilter/dnn/dnn_backend_tf.c @@ -499,22 +499,22 @@ static DNNReturnType load_native_model(TFModel *tf_model, const char *model_file for (layer = 0; layer < conv_network->layers_num; ++layer){ switch (conv_network->layers[layer].type){ - case INPUT: + case DLT_INPUT: layer_add_res = DNN_SUCCESS; break; - case CONV: + case DLT_CONV2D: layer_add_res = add_conv_layer(tf_model, transpose_op, &op, (ConvolutionalParams *)conv_network->layers[layer].params, layer); break; - case DEPTH_TO_SPACE: + case DLT_DEPTH_TO_SPACE: layer_add_res = add_depth_to_space_layer(tf_model, &op, (DepthToSpaceParams *)conv_network->layers[layer].params, layer); break; - case MIRROR_PAD: + case DLT_MIRROR_PAD: layer_add_res = add_pad_layer(tf_model, &op, (LayerPadParams *)conv_network->layers[layer].params, layer); break; - case MAXIMUM: + case DLT_MAXIMUM: layer_add_res = add_maximum_layer(tf_model, &op, (DnnLayerMaximumParams *)conv_network->layers[layer].params, layer); break;