avfilter/dnn: unify the layer load function in native mode

Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>

libavfilter/dnn/dnn_backend_native.c

@@ -25,10 +25,7 @@
 
 #include "dnn_backend_native.h"
 #include "libavutil/avassert.h"
-#include "dnn_backend_native_layer_pad.h"
 #include "dnn_backend_native_layer_conv2d.h"
-#include "dnn_backend_native_layer_depth2space.h"
-#include "dnn_backend_native_layer_maximum.h"
 #include "dnn_backend_native_layers.h"
 
 static DNNReturnType set_input_output_native(void *model, DNNInputData *input, const char *input_name, const char **output_names, uint32_t nb_output)
@@ -104,13 +101,9 @@ DNNModel *ff_dnn_load_model_native(const char *model_filename)
     int version, header_size, major_version_expected = 0;
     ConvolutionalNetwork *network = NULL;
     AVIOContext *model_file_context;
-    int file_size, dnn_size, kernel_size, i;
+    int file_size, dnn_size, parsed_size;
     int32_t layer;
     DNNLayerType layer_type;
-    ConvolutionalParams *conv_params;
-    DepthToSpaceParams *depth_to_space_params;
-    LayerPadParams *pad_params;
-    DnnLayerMaximumParams *maximum_params;
 
     model = av_malloc(sizeof(DNNModel));
     if (!model){
@@ -189,104 +182,21 @@ 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;
+
+        if (layer_type >= DLT_COUNT) {
+            avio_closep(&model_file_context);
+            ff_dnn_free_model_native(&model);
+            return NULL;
+        }
+
         network->layers[layer].type = layer_type;
-        switch (layer_type){
-        case DLT_CONV2D:
-            conv_params = av_malloc(sizeof(ConvolutionalParams));
-            if (!conv_params){
-                avio_closep(&model_file_context);
-                ff_dnn_free_model_native(&model);
-                return NULL;
-            }
-            conv_params->dilation = (int32_t)avio_rl32(model_file_context);
-            conv_params->padding_method = (int32_t)avio_rl32(model_file_context);
-            conv_params->activation = (int32_t)avio_rl32(model_file_context);
-            conv_params->input_num = (int32_t)avio_rl32(model_file_context);
-            conv_params->output_num = (int32_t)avio_rl32(model_file_context);
-            conv_params->kernel_size = (int32_t)avio_rl32(model_file_context);
-            kernel_size = conv_params->input_num * conv_params->output_num *
-                          conv_params->kernel_size * conv_params->kernel_size;
-            dnn_size += 24 + (kernel_size + conv_params->output_num << 2);
-            if (dnn_size > file_size || conv_params->input_num <= 0 ||
-                conv_params->output_num <= 0 || conv_params->kernel_size <= 0){
-                avio_closep(&model_file_context);
-                av_freep(&conv_params);
-                ff_dnn_free_model_native(&model);
-                return NULL;
-            }
-            conv_params->kernel = av_malloc(kernel_size * sizeof(float));
-            conv_params->biases = av_malloc(conv_params->output_num * sizeof(float));
-            if (!conv_params->kernel || !conv_params->biases){
-                avio_closep(&model_file_context);
-                av_freep(&conv_params->kernel);
-                av_freep(&conv_params->biases);
-                av_freep(&conv_params);
-                ff_dnn_free_model_native(&model);
-                return NULL;
-            }
-            for (i = 0; i < kernel_size; ++i){
-                conv_params->kernel[i] = av_int2float(avio_rl32(model_file_context));
-            }
-            for (i = 0; i < conv_params->output_num; ++i){
-                conv_params->biases[i] = av_int2float(avio_rl32(model_file_context));
-            }
-            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].params = conv_params;
-            break;
-        case DLT_DEPTH_TO_SPACE:
-            depth_to_space_params = av_malloc(sizeof(DepthToSpaceParams));
-            if (!depth_to_space_params){
-                avio_closep(&model_file_context);
-                ff_dnn_free_model_native(&model);
-                return NULL;
-            }
-            depth_to_space_params->block_size = (int32_t)avio_rl32(model_file_context);
-            dnn_size += 4;
-            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].params = depth_to_space_params;
-            break;
-        case DLT_MIRROR_PAD:
-            pad_params = av_malloc(sizeof(LayerPadParams));
-            if (!pad_params){
-                avio_closep(&model_file_context);
-                ff_dnn_free_model_native(&model);
-                return NULL;
-            }
-            pad_params->mode = (int32_t)avio_rl32(model_file_context);
-            dnn_size += 4;
-            for (i = 0; i < 4; ++i) {
-                pad_params->paddings[i][0] = avio_rl32(model_file_context);
-                pad_params->paddings[i][1] = avio_rl32(model_file_context);
-                dnn_size += 8;
-            }
-            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].params = pad_params;
-            break;
-        case DLT_MAXIMUM:
-            maximum_params = av_malloc(sizeof(*maximum_params));
-            if (!maximum_params){
-                avio_closep(&model_file_context);
-                ff_dnn_free_model_native(&model);
-                return NULL;
-            }
-            maximum_params->val.u32 = avio_rl32(model_file_context);
-            dnn_size += 4;
-            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);
-            dnn_size += 8;
-            break;
-        default:
+        parsed_size = layer_funcs[layer_type].pf_load(&network->layers[layer], model_file_context, file_size);
+        if (!parsed_size) {
             avio_closep(&model_file_context);
             ff_dnn_free_model_native(&model);
             return NULL;
         }
+        dnn_size += parsed_size;
     }
 
     for (int32_t i = 0; i < network->operands_num; ++i){
@@ -341,7 +251,7 @@ DNNReturnType ff_dnn_execute_model_native(const DNNModel *model, DNNData *output
 
     for (layer = 0; layer < network->layers_num; ++layer){
         DNNLayerType layer_type = network->layers[layer].type;
-        layer_funcs[layer_type](network->operands,
+        layer_funcs[layer_type].pf_exec(network->operands,
                                   network->layers[layer].input_operand_indexes,
                                   network->layers[layer].output_operand_index,
                                   network->layers[layer].params);

libavfilter/dnn/dnn_backend_native.h

@@ -33,7 +33,7 @@
 /**
  * the enum value of DNNLayerType should not be changed,
  * the same values are used in convert_from_tensorflow.py
- * and, it is used to index the layer execution function pointer.
+ * and, it is used to index the layer execution/load function pointer.
  */
 typedef enum {
     DLT_INPUT = 0,

libavfilter/dnn/dnn_backend_native_layer_conv2d.c

@@ -23,6 +23,52 @@
 
 #define CLAMP_TO_EDGE(x, w) ((x) < 0 ? 0 : ((x) >= (w) ? (w - 1) : (x)))
 
+int dnn_load_layer_conv2d(Layer *layer, AVIOContext *model_file_context, int file_size)
+{
+    ConvolutionalParams *conv_params;
+    int kernel_size;
+    int dnn_size = 0;
+    conv_params = av_malloc(sizeof(*conv_params));
+    if (!conv_params)
+        return 0;
+
+    conv_params->dilation = (int32_t)avio_rl32(model_file_context);
+    conv_params->padding_method = (int32_t)avio_rl32(model_file_context);
+    conv_params->activation = (int32_t)avio_rl32(model_file_context);
+    conv_params->input_num = (int32_t)avio_rl32(model_file_context);
+    conv_params->output_num = (int32_t)avio_rl32(model_file_context);
+    conv_params->kernel_size = (int32_t)avio_rl32(model_file_context);
+    kernel_size = conv_params->input_num * conv_params->output_num *
+                  conv_params->kernel_size * conv_params->kernel_size;
+    dnn_size += 24 + (kernel_size + conv_params->output_num << 2);
+    if (dnn_size > file_size || conv_params->input_num <= 0 ||
+        conv_params->output_num <= 0 || conv_params->kernel_size <= 0){
+        av_freep(&conv_params);
+        return 0;
+    }
+    conv_params->kernel = av_malloc(kernel_size * sizeof(float));
+    conv_params->biases = av_malloc(conv_params->output_num * sizeof(float));
+    if (!conv_params->kernel || !conv_params->biases){
+        av_freep(&conv_params->kernel);
+        av_freep(&conv_params->biases);
+        av_freep(&conv_params);
+        return 0;
+    }
+    for (int i = 0; i < kernel_size; ++i){
+        conv_params->kernel[i] = av_int2float(avio_rl32(model_file_context));
+    }
+    for (int i = 0; i < conv_params->output_num; ++i){
+        conv_params->biases[i] = av_int2float(avio_rl32(model_file_context));
+    }
+
+    layer->params = conv_params;
+
+    layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
+    layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
+    dnn_size += 8;
+    return dnn_size;
+}
+
 int dnn_execute_layer_conv2d(DnnOperand *operands, const int32_t *input_operand_indexes,
                              int32_t output_operand_index, const void *parameters)
 {

libavfilter/dnn/dnn_backend_native_layer_conv2d.h

@@ -35,6 +35,7 @@ typedef struct ConvolutionalParams{
     float *biases;
 } ConvolutionalParams;
 
+int dnn_load_layer_conv2d(Layer *layer, AVIOContext *model_file_context, int file_size);
 int dnn_execute_layer_conv2d(DnnOperand *operands, const int32_t *input_operand_indexes,
                              int32_t output_operand_index, const void *parameters);
 #endif

libavfilter/dnn/dnn_backend_native_layer_depth2space.c

@@ -27,6 +27,24 @@
 #include "libavutil/avassert.h"
 #include "dnn_backend_native_layer_depth2space.h"
 
+int dnn_load_layer_depth2space(Layer *layer, AVIOContext *model_file_context, int file_size)
+{
+    DepthToSpaceParams *params;
+    int dnn_size = 0;
+    params = av_malloc(sizeof(*params));
+    if (!params)
+        return 0;
+
+    params->block_size = (int32_t)avio_rl32(model_file_context);
+    dnn_size += 4;
+    layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
+    layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
+    dnn_size += 8;
+    layer->params = params;
+
+    return dnn_size;
+}
+
 int dnn_execute_layer_depth2space(DnnOperand *operands, const int32_t *input_operand_indexes,
                                   int32_t output_operand_index, const void *parameters)
 {

libavfilter/dnn/dnn_backend_native_layer_depth2space.h

@@ -34,6 +34,7 @@ typedef struct DepthToSpaceParams{
     int block_size;
 } DepthToSpaceParams;
 
+int dnn_load_layer_depth2space(Layer *layer, AVIOContext *model_file_context, int file_size);
 int dnn_execute_layer_depth2space(DnnOperand *operands, const int32_t *input_operand_indexes,
                                   int32_t output_operand_index, const void *parameters);
 

libavfilter/dnn/dnn_backend_native_layer_maximum.c

@@ -27,6 +27,24 @@
 #include "libavutil/avassert.h"
 #include "dnn_backend_native_layer_maximum.h"
 
+int dnn_load_layer_maximum(Layer *layer, AVIOContext *model_file_context, int file_size)
+{
+    DnnLayerMaximumParams *params;
+    int dnn_size = 0;
+    params = av_malloc(sizeof(*params));
+    if (!params)
+        return 0;
+
+    params->val.u32 = avio_rl32(model_file_context);
+    dnn_size += 4;
+    layer->params = params;
+    layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
+    layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
+    dnn_size += 8;
+
+    return dnn_size;
+}
+
 int dnn_execute_layer_maximum(DnnOperand *operands, const int32_t *input_operand_indexes,
                               int32_t output_operand_index, const void *parameters)
 {

libavfilter/dnn/dnn_backend_native_layer_maximum.h

@@ -37,6 +37,7 @@ typedef struct DnnLayerMaximumParams{
     }val;
 } DnnLayerMaximumParams;
 
+int dnn_load_layer_maximum(Layer *layer, AVIOContext *model_file_context, int file_size);
 int dnn_execute_layer_maximum(DnnOperand *operands, const int32_t *input_operand_indexes,
                               int32_t output_operand_index, const void *parameters);
 

libavfilter/dnn/dnn_backend_native_layer_pad.c

@@ -22,6 +22,29 @@
 #include "libavutil/avassert.h"
 #include "dnn_backend_native_layer_pad.h"
 
+int dnn_load_layer_pad(Layer *layer, AVIOContext *model_file_context, int file_size)
+{
+    LayerPadParams *params;
+    int dnn_size = 0;
+    params = av_malloc(sizeof(*params));
+    if (!params)
+        return 0;
+
+    params->mode = (int32_t)avio_rl32(model_file_context);
+    dnn_size += 4;
+    for (int i = 0; i < 4; ++i) {
+        params->paddings[i][0] = avio_rl32(model_file_context);
+        params->paddings[i][1] = avio_rl32(model_file_context);
+        dnn_size += 8;
+    }
+    layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
+    layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
+    dnn_size += 8;
+    layer->params = params;
+
+    return dnn_size;
+}
+
 static int before_get_buddy(int given, int paddings, LayerPadModeParam mode)
 {
     if (mode == LPMP_SYMMETRIC) {

libavfilter/dnn/dnn_backend_native_layer_pad.h

@@ -36,6 +36,7 @@ typedef struct LayerPadParams{
     float constant_values;
 } LayerPadParams;
 
+int dnn_load_layer_pad(Layer *layer, AVIOContext *model_file_context, int file_size);
 int dnn_execute_layer_pad(DnnOperand *operands, const int32_t *input_operand_indexes,
                           int32_t output_operand_index, const void *parameters);
 

libavfilter/dnn/dnn_backend_native_layers.c

@@ -25,10 +25,10 @@
 #include "dnn_backend_native_layer_depth2space.h"
 #include "dnn_backend_native_layer_maximum.h"
 
-LAYER_EXEC_FUNC layer_funcs[DLT_COUNT] = {
-    NULL,
-    dnn_execute_layer_conv2d,
-    dnn_execute_layer_depth2space,
-    dnn_execute_layer_pad,
-    dnn_execute_layer_maximum,
+LayerFunc layer_funcs[DLT_COUNT] = {
+    {NULL, NULL},
+    {dnn_execute_layer_conv2d,      dnn_load_layer_conv2d},
+    {dnn_execute_layer_depth2space, dnn_load_layer_depth2space},
+    {dnn_execute_layer_pad,         dnn_load_layer_pad},
+    {dnn_execute_layer_maximum,     dnn_load_layer_maximum},
 };

libavfilter/dnn/dnn_backend_native_layers.h

@@ -26,7 +26,13 @@
 
 typedef int (*LAYER_EXEC_FUNC)(DnnOperand *operands, const int32_t *input_operand_indexes,
                                int32_t output_operand_index, const void *parameters);
+typedef int (*LAYER_LOAD_FUNC)(Layer *layer, AVIOContext *model_file_context, int file_size);
 
-extern LAYER_EXEC_FUNC layer_funcs[DLT_COUNT];
+typedef struct LayerFunc {
+    LAYER_EXEC_FUNC pf_exec;
+    LAYER_LOAD_FUNC pf_load;
+}LayerFunc;
+
+extern LayerFunc layer_funcs[DLT_COUNT];
 
 #endif