#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_layers.h"
+
+#define OFFSET(x) offsetof(NativeContext, x)
+#define FLAGS AV_OPT_FLAG_FILTERING_PARAM
+static const AVOption dnn_native_options[] = {
+ { "conv2d_threads", "threads num for conv2d layer", OFFSET(options.conv2d_threads), AV_OPT_TYPE_INT, { .i64 = 0 }, INT_MIN, INT_MAX, FLAGS },
+ { NULL },
+};
+
+const AVClass dnn_native_class = {
+ .class_name = "dnn_native",
+ .item_name = av_default_item_name,
+ .option = dnn_native_options,
+ .version = LIBAVUTIL_VERSION_INT,
+ .category = AV_CLASS_CATEGORY_FILTER,
+};
+
+static DNNReturnType get_input_native(void *model, DNNData *input, const char *input_name)
+{
+ NativeModel *native_model = (NativeModel *)model;
+ NativeContext *ctx = &native_model->ctx;
+
+ for (int i = 0; i < native_model->operands_num; ++i) {
+ DnnOperand *oprd = &native_model->operands[i];
+ if (strcmp(oprd->name, input_name) == 0) {
+ if (oprd->type != DOT_INPUT) {
+ av_log(ctx, AV_LOG_ERROR, "Found \"%s\" in model, but it is not input node\n", input_name);
+ return DNN_ERROR;
+ }
+ input->dt = oprd->data_type;
+ av_assert0(oprd->dims[0] == 1);
+ input->height = oprd->dims[1];
+ input->width = oprd->dims[2];
+ input->channels = oprd->dims[3];
+ return DNN_SUCCESS;
+ }
+ }
-static DNNReturnType set_input_output_native(void *model, DNNInputData *input, const char *input_name, const char **output_names, uint32_t nb_output)
+ // do not find the input operand
+ av_log(ctx, AV_LOG_ERROR, "Could not find \"%s\" in model\n", input_name);
+ return DNN_ERROR;
+}
+
+static DNNReturnType set_input_native(void *model, DNNData *input, const char *input_name)
{
- ConvolutionalNetwork *network = (ConvolutionalNetwork *)model;
+ NativeModel *native_model = (NativeModel *)model;
+ NativeContext *ctx = &native_model->ctx;
+ DnnOperand *oprd = NULL;
- if (network->layers_num <= 0 || network->operands_num <= 0)
+ if (native_model->layers_num <= 0 || native_model->operands_num <= 0) {
+ av_log(ctx, AV_LOG_ERROR, "No operands or layers in model\n");
return DNN_ERROR;
+ }
- av_assert0(input->dt == DNN_FLOAT);
+ /* inputs */
+ for (int i = 0; i < native_model->operands_num; ++i) {
+ oprd = &native_model->operands[i];
+ if (strcmp(oprd->name, input_name) == 0) {
+ if (oprd->type != DOT_INPUT) {
+ av_log(ctx, AV_LOG_ERROR, "Found \"%s\" in model, but it is not input node\n", input_name);
+ return DNN_ERROR;
+ }
+ break;
+ }
+ oprd = NULL;
+ }
+ if (!oprd) {
+ av_log(ctx, AV_LOG_ERROR, "Could not find \"%s\" in model\n", input_name);
+ return DNN_ERROR;
+ }
- /**
- * as the first step, suppose network->operands[0] is the input operand.
- */
- network->operands[0].dims[0] = 1;
- network->operands[0].dims[1] = input->height;
- network->operands[0].dims[2] = input->width;
- network->operands[0].dims[3] = input->channels;
- network->operands[0].type = DOT_INPUT;
- network->operands[0].data_type = DNN_FLOAT;
- network->operands[0].isNHWC = 1;
-
- av_freep(&network->operands[0].data);
- network->operands[0].length = calculate_operand_data_length(&network->operands[0]);
- network->operands[0].data = av_malloc(network->operands[0].length);
- if (!network->operands[0].data)
+ oprd->dims[0] = 1;
+ oprd->dims[1] = input->height;
+ oprd->dims[2] = input->width;
+ oprd->dims[3] = input->channels;
+
+ av_freep(&oprd->data);
+ oprd->length = calculate_operand_data_length(oprd);
+ if (oprd->length <= 0) {
+ av_log(ctx, AV_LOG_ERROR, "The input data length overflow\n");
+ return DNN_ERROR;
+ }
+ oprd->data = av_malloc(oprd->length);
+ if (!oprd->data) {
+ av_log(ctx, AV_LOG_ERROR, "Failed to malloc memory for input data\n");
return DNN_ERROR;
+ }
+
+ input->data = oprd->data;
- input->data = network->operands[0].data;
return DNN_SUCCESS;
}
// layers_num,layer_type,layer_parameterss,layer_type,layer_parameters...
// For CONV layer: activation_function, input_num, output_num, kernel_size, kernel, biases
// For DEPTH_TO_SPACE layer: block_size
-DNNModel *ff_dnn_load_model_native(const char *model_filename)
+DNNModel *ff_dnn_load_model_native(const char *model_filename, const char *options, void *userdata)
{
DNNModel *model = NULL;
- ConvolutionalNetwork *network = NULL;
+ char header_expected[] = "FFMPEGDNNNATIVE";
+ char *buf;
+ size_t size;
+ int version, header_size, major_version_expected = 1;
+ NativeModel *native_model = 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;
-
- model = av_malloc(sizeof(DNNModel));
- if (!model){
- return NULL;
- }
if (avio_open(&model_file_context, model_filename, AVIO_FLAG_READ) < 0){
- av_freep(&model);
return NULL;
}
file_size = avio_size(model_file_context);
- network = av_mallocz(sizeof(ConvolutionalNetwork));
- if (!network){
- avio_closep(&model_file_context);
- av_freep(&model);
- return NULL;
+ model = av_mallocz(sizeof(DNNModel));
+ if (!model){
+ goto fail;
}
- model->model = (void *)network;
+
+ /**
+ * check file header with string and version
+ */
+ size = sizeof(header_expected);
+ buf = av_malloc(size);
+ if (!buf) {
+ goto fail;
+ }
+
+ // size - 1 to skip the ending '\0' which is not saved in file
+ avio_get_str(model_file_context, size - 1, buf, size);
+ dnn_size = size - 1;
+ if (strncmp(buf, header_expected, size) != 0) {
+ av_freep(&buf);
+ goto fail;
+ }
+ av_freep(&buf);
+
+ version = (int32_t)avio_rl32(model_file_context);
+ dnn_size += 4;
+ if (version != major_version_expected) {
+ goto fail;
+ }
+
+ // currently no need to check minor version
+ version = (int32_t)avio_rl32(model_file_context);
+ dnn_size += 4;
+ header_size = dnn_size;
+
+ native_model = av_mallocz(sizeof(NativeModel));
+ if (!native_model){
+ goto fail;
+ }
+
+ native_model->ctx.class = &dnn_native_class;
+ model->options = options;
+ if (av_opt_set_from_string(&native_model->ctx, model->options, NULL, "=", "&") < 0)
+ goto fail;
+ model->model = (void *)native_model;
+
+#if !HAVE_PTHREAD_CANCEL
+ if (native_model->ctx.options.conv2d_threads > 1){
+ av_log(&native_model->ctx, AV_LOG_WARNING, "'conv2d_threads' option was set but it is not supported "
+ "on this build (pthread support is required)\n");
+ }
+#endif
avio_seek(model_file_context, file_size - 8, SEEK_SET);
- network->layers_num = (int32_t)avio_rl32(model_file_context);
- network->operands_num = (int32_t)avio_rl32(model_file_context);
- dnn_size = 8;
- avio_seek(model_file_context, 0, SEEK_SET);
-
- network->layers = av_mallocz(network->layers_num * sizeof(Layer));
- if (!network->layers){
- avio_closep(&model_file_context);
- ff_dnn_free_model_native(&model);
- return NULL;
+ native_model->layers_num = (int32_t)avio_rl32(model_file_context);
+ native_model->operands_num = (int32_t)avio_rl32(model_file_context);
+ dnn_size += 8;
+ avio_seek(model_file_context, header_size, SEEK_SET);
+
+ native_model->layers = av_mallocz(native_model->layers_num * sizeof(Layer));
+ if (!native_model->layers){
+ goto fail;
}
- network->operands = av_mallocz(network->operands_num * sizeof(DnnOperand));
- if (!network->operands){
- avio_closep(&model_file_context);
- ff_dnn_free_model_native(&model);
- return NULL;
+ native_model->operands = av_mallocz(native_model->operands_num * sizeof(DnnOperand));
+ if (!native_model->operands){
+ goto fail;
}
- for (layer = 0; layer < network->layers_num; ++layer){
+ for (layer = 0; layer < native_model->layers_num; ++layer){
layer_type = (int32_t)avio_rl32(model_file_context);
dnn_size += 4;
- switch (layer_type){
- case CONV:
- 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].type = CONV;
- network->layers[layer].params = conv_params;
- break;
- case 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].type = DEPTH_TO_SPACE;
- network->layers[layer].params = depth_to_space_params;
- break;
- case 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].type = MIRROR_PAD;
- network->layers[layer].params = pad_params;
- break;
- default:
- avio_closep(&model_file_context);
- ff_dnn_free_model_native(&model);
- return NULL;
+
+ if (layer_type >= DLT_COUNT) {
+ goto fail;
+ }
+
+ native_model->layers[layer].type = layer_type;
+ parsed_size = layer_funcs[layer_type].pf_load(&native_model->layers[layer], model_file_context, file_size, native_model->operands_num);
+ if (!parsed_size) {
+ goto fail;
}
+ dnn_size += parsed_size;
}
- for (int32_t i = 0; i < network->operands_num; ++i){
+ for (int32_t i = 0; i < native_model->operands_num; ++i){
DnnOperand *oprd;
int32_t name_len;
int32_t operand_index = (int32_t)avio_rl32(model_file_context);
dnn_size += 4;
- oprd = &network->operands[operand_index];
+ if (operand_index >= native_model->operands_num) {
+ goto fail;
+ }
+
+ oprd = &native_model->operands[operand_index];
name_len = (int32_t)avio_rl32(model_file_context);
dnn_size += 4;
return NULL;
}
- model->set_input_output = &set_input_output_native;
+ model->set_input = &set_input_native;
+ model->get_input = &get_input_native;
+ model->userdata = userdata;
return model;
-}
-#define CLAMP_TO_EDGE(x, w) ((x) < 0 ? 0 : ((x) >= (w) ? (w - 1) : (x)))
-
-static int convolve(DnnOperand *operands, const int32_t *input_operand_indexes, int32_t output_operand_index, const ConvolutionalParams *conv_params)
-{
- float *output;
- int32_t input_operand_index = input_operand_indexes[0];
- int number = operands[input_operand_index].dims[0];
- int height = operands[input_operand_index].dims[1];
- int width = operands[input_operand_index].dims[2];
- int channel = operands[input_operand_index].dims[3];
- const float *input = operands[input_operand_index].data;
-
- int radius = conv_params->kernel_size >> 1;
- int src_linesize = width * conv_params->input_num;
- int filter_linesize = conv_params->kernel_size * conv_params->input_num;
- int filter_size = conv_params->kernel_size * filter_linesize;
- int pad_size = (conv_params->padding_method == VALID) ? (conv_params->kernel_size - 1) / 2 * conv_params->dilation : 0;
-
- DnnOperand *output_operand = &operands[output_operand_index];
- output_operand->dims[0] = number;
- output_operand->dims[1] = height - pad_size * 2;
- output_operand->dims[2] = width - pad_size * 2;
- output_operand->dims[3] = conv_params->output_num;
- output_operand->length = calculate_operand_data_length(output_operand);
- output_operand->data = av_realloc(output_operand->data, output_operand->length);
- if (!output_operand->data)
- return -1;
- output = output_operand->data;
-
- av_assert0(channel == conv_params->input_num);
-
- for (int y = pad_size; y < height - pad_size; ++y) {
- for (int x = pad_size; x < width - pad_size; ++x) {
- for (int n_filter = 0; n_filter < conv_params->output_num; ++n_filter) {
- output[n_filter] = conv_params->biases[n_filter];
-
- for (int ch = 0; ch < conv_params->input_num; ++ch) {
- for (int kernel_y = 0; kernel_y < conv_params->kernel_size; ++kernel_y) {
- for (int kernel_x = 0; kernel_x < conv_params->kernel_size; ++kernel_x) {
- float input_pel;
- if (conv_params->padding_method == SAME_CLAMP_TO_EDGE) {
- int y_pos = CLAMP_TO_EDGE(y + (kernel_y - radius) * conv_params->dilation, height);
- int x_pos = CLAMP_TO_EDGE(x + (kernel_x - radius) * conv_params->dilation, width);
- input_pel = input[y_pos * src_linesize + x_pos * conv_params->input_num + ch];
- } else {
- int y_pos = y + (kernel_y - radius) * conv_params->dilation;
- int x_pos = x + (kernel_x - radius) * conv_params->dilation;
- input_pel = (x_pos < 0 || x_pos >= width || y_pos < 0 || y_pos >= height) ? 0.0 :
- input[y_pos * src_linesize + x_pos * conv_params->input_num + ch];
- }
-
-
- output[n_filter] += input_pel * conv_params->kernel[n_filter * filter_size + kernel_y * filter_linesize +
- kernel_x * conv_params->input_num + ch];
- }
- }
- }
- switch (conv_params->activation){
- case RELU:
- output[n_filter] = FFMAX(output[n_filter], 0.0);
- break;
- case TANH:
- output[n_filter] = 2.0f / (1.0f + exp(-2.0f * output[n_filter])) - 1.0f;
- break;
- case SIGMOID:
- output[n_filter] = 1.0f / (1.0f + exp(-output[n_filter]));
- break;
- case NONE:
- break;
- case LEAKY_RELU:
- output[n_filter] = FFMAX(output[n_filter], 0.0) + 0.2 * FFMIN(output[n_filter], 0.0);
- }
- }
- output += conv_params->output_num;
- }
- }
- return 0;
-}
-
-static int depth_to_space(DnnOperand *operands, const int32_t *input_operand_indexes, int32_t output_operand_index, int block_size)
-{
- float *output;
- int32_t input_operand_index = input_operand_indexes[0];
- int number = operands[input_operand_index].dims[0];
- int height = operands[input_operand_index].dims[1];
- int width = operands[input_operand_index].dims[2];
- int channels = operands[input_operand_index].dims[3];
- const float *input = operands[input_operand_index].data;
-
- int y, x, by, bx, ch;
- int new_channels = channels / (block_size * block_size);
- int output_linesize = width * channels;
- int by_linesize = output_linesize / block_size;
- int x_linesize = new_channels * block_size;
-
- DnnOperand *output_operand = &operands[output_operand_index];
- output_operand->dims[0] = number;
- output_operand->dims[1] = height * block_size;
- output_operand->dims[2] = width * block_size;
- output_operand->dims[3] = new_channels;
- output_operand->length = calculate_operand_data_length(output_operand);
- output_operand->data = av_realloc(output_operand->data, output_operand->length);
- if (!output_operand->data)
- return -1;
- output = output_operand->data;
-
- for (y = 0; y < height; ++y){
- for (x = 0; x < width; ++x){
- for (by = 0; by < block_size; ++by){
- for (bx = 0; bx < block_size; ++bx){
- for (ch = 0; ch < new_channels; ++ch){
- output[by * by_linesize + x * x_linesize + bx * new_channels + ch] = input[ch];
- }
- input += new_channels;
- }
- }
- }
- output += output_linesize;
- }
- return 0;
+fail:
+ ff_dnn_free_model_native(&model);
+ avio_closep(&model_file_context);
+ return NULL;
}
-DNNReturnType ff_dnn_execute_model_native(const DNNModel *model, DNNData *outputs, uint32_t nb_output)
+DNNReturnType ff_dnn_execute_model_native(const DNNModel *model, DNNData *outputs, const char **output_names, uint32_t nb_output)
{
- ConvolutionalNetwork *network = (ConvolutionalNetwork *)model->model;
+ NativeModel *native_model = (NativeModel *)model->model;
+ NativeContext *ctx = &native_model->ctx;
int32_t layer;
- ConvolutionalParams *conv_params;
- DepthToSpaceParams *depth_to_space_params;
- LayerPadParams *pad_params;
- if (network->layers_num <= 0 || network->operands_num <= 0)
+ if (native_model->layers_num <= 0 || native_model->operands_num <= 0) {
+ av_log(ctx, AV_LOG_ERROR, "No operands or layers in model\n");
return DNN_ERROR;
- if (!network->operands[0].data)
+ }
+ if (!native_model->operands[0].data) {
+ av_log(ctx, AV_LOG_ERROR, "Empty model input data\n");
return DNN_ERROR;
+ }
- for (layer = 0; layer < network->layers_num; ++layer){
- switch (network->layers[layer].type){
- case CONV:
- 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:
- 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:
- 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 INPUT:
+ for (layer = 0; layer < native_model->layers_num; ++layer){
+ DNNLayerType layer_type = native_model->layers[layer].type;
+ if (layer_funcs[layer_type].pf_exec(native_model->operands,
+ native_model->layers[layer].input_operand_indexes,
+ native_model->layers[layer].output_operand_index,
+ native_model->layers[layer].params,
+ &native_model->ctx) == DNN_ERROR) {
+ av_log(ctx, AV_LOG_ERROR, "Failed to execuet model\n");
return DNN_ERROR;
}
}
- // native mode does not support multiple outputs yet
- if (nb_output > 1)
- return DNN_ERROR;
+ for (uint32_t i = 0; i < nb_output; ++i) {
+ DnnOperand *oprd = NULL;
+ const char *output_name = output_names[i];
+ for (int j = 0; j < native_model->operands_num; ++j) {
+ if (strcmp(native_model->operands[j].name, output_name) == 0) {
+ oprd = &native_model->operands[j];
+ break;
+ }
+ }
- /**
- * as the first step, suppose network->operands[network->operands_num - 1] is the output operand.
- */
- outputs[0].data = network->operands[network->operands_num - 1].data;
- outputs[0].height = network->operands[network->operands_num - 1].dims[1];
- outputs[0].width = network->operands[network->operands_num - 1].dims[2];
- outputs[0].channels = network->operands[network->operands_num - 1].dims[3];
+ if (oprd == NULL) {
+ av_log(ctx, AV_LOG_ERROR, "Could not find output in model\n");
+ return DNN_ERROR;
+ }
+
+ outputs[i].data = oprd->data;
+ outputs[i].height = oprd->dims[1];
+ outputs[i].width = oprd->dims[2];
+ outputs[i].channels = oprd->dims[3];
+ outputs[i].dt = oprd->data_type;
+ }
return DNN_SUCCESS;
}
-int32_t calculate_operand_data_length(DnnOperand* operand)
+int32_t calculate_operand_dims_count(const DnnOperand *oprd)
+{
+ int32_t result = 1;
+ for (int i = 0; i < 4; ++i)
+ result *= oprd->dims[i];
+
+ return result;
+}
+
+int32_t calculate_operand_data_length(const DnnOperand* oprd)
{
// currently, we just support DNN_FLOAT
- return operand->dims[0] * operand->dims[1] * operand->dims[2] * operand->dims[3] * sizeof(float);
+ uint64_t len = sizeof(float);
+ for (int i = 0; i < 4; i++) {
+ len *= oprd->dims[i];
+ if (len > INT32_MAX)
+ return 0;
+ }
+ return len;
}
void ff_dnn_free_model_native(DNNModel **model)
{
- ConvolutionalNetwork *network;
+ NativeModel *native_model;
ConvolutionalParams *conv_params;
int32_t layer;
if (*model)
{
- network = (ConvolutionalNetwork *)(*model)->model;
- for (layer = 0; layer < network->layers_num; ++layer){
- if (network->layers[layer].type == CONV){
- conv_params = (ConvolutionalParams *)network->layers[layer].params;
- av_freep(&conv_params->kernel);
- av_freep(&conv_params->biases);
+ if ((*model)->model) {
+ native_model = (NativeModel *)(*model)->model;
+ if (native_model->layers) {
+ for (layer = 0; layer < native_model->layers_num; ++layer){
+ if (native_model->layers[layer].type == DLT_CONV2D){
+ conv_params = (ConvolutionalParams *)native_model->layers[layer].params;
+ av_freep(&conv_params->kernel);
+ av_freep(&conv_params->biases);
+ }
+ av_freep(&native_model->layers[layer].params);
+ }
+ av_freep(&native_model->layers);
}
- av_freep(&network->layers[layer].params);
- }
- av_freep(&network->layers);
- for (uint32_t operand = 0; operand < network->operands_num; ++operand)
- av_freep(&network->operands[operand].data);
- av_freep(&network->operands);
+ if (native_model->operands) {
+ for (uint32_t operand = 0; operand < native_model->operands_num; ++operand)
+ av_freep(&native_model->operands[operand].data);
+ av_freep(&native_model->operands);
+ }
- av_freep(&network);
+ av_freep(&native_model);
+ }
av_freep(model);
}
}