May be mistake about copy_weights_net(...) of network.c

[chgoatherd]

if (l->type == CRNN)
{
	layer tmp_input_layer, tmp_self_layer, tmp_output_layer;

	copy_cudnn_descriptors(*net_map->layers[k].input_layer, &tmp_input_layer);     // "net_map" should be "net_train"
	copy_cudnn_descriptors(*net_map->layers[k].self_layer, &tmp_self_layer);           // "net_map" should be "net_train"
	copy_cudnn_descriptors(*net_map->layers[k].output_layer, &tmp_output_layer);   // "net_map" should be "net_train"
	net_map->layers[k].input_layer = net_train.layers[k].input_layer;
	net_map->layers[k].self_layer = net_train.layers[k].self_layer;
	net_map->layers[k].output_layer = net_train.layers[k].output_layer;
	//net_map->layers[k].output_gpu = net_map->layers[k].output_layer->output_gpu;  // already copied out of if()

	copy_cudnn_descriptors(tmp_input_layer, net_map->layers[k].input_layer);   // "net_map" should be "net_train"
	copy_cudnn_descriptors(tmp_self_layer, net_map->layers[k].self_layer);        // "net_map" should be "net_train"
	copy_cudnn_descriptors(tmp_output_layer, net_map->layers[k].output_layer);  // "net_map" should be "net_train"
}
else if (l->input_layer) // for AntiAliasing
{
	layer tmp_input_layer;

	copy_cudnn_descriptors(*net_map->layers[k].input_layer, &tmp_input_layer);  // "net_map" should be "net_train"
	net_map->layers[k].input_layer = net_train.layers[k].input_layer;
	copy_cudnn_descriptors(tmp_input_layer, net_map->layers[k].input_layer);    // "net_map" should be "net_train"
}

[lrf19991230]

I want to know what kind of consequences this error will lead to？ like #8669？ why