tinynn/converter/operators/optimize.py [2749:2780]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        remove_ids = []
        ops = []
        restore_mapping = []
        for conv in vertices:
            restore_nodes = []
            # For each node that is next of a transformable node,
            #  a. if it is an output node, remove it anyway since it will always be reconstructed
            #  b. otherwise, record the info of the edge so that we may restore it after reconstruction
            for out_edge in conv.out_edges():
                next_node = self.graph.graph.vs[out_edge.target]
                if next_node['node_type'] == ExtendedOperator.OUTPUT_NODE:
                    remove_ids.append(next_node.index)
                    del self.graph.tensor_map[next_node['outputs'][0]]
                    del self.graph.tensor_node_map[next_node['outputs'][0]]
                else:
                    restore_nodes.append((out_edge['name'], next_node['name']))

            # Remove the mapping since they are going to be removed
            for output_name in conv['outputs']:
                del self.graph.tensor_map[output_name]
                del self.graph.tensor_node_map[output_name]

            restore_mapping.append(restore_nodes)
            remove_ids.append(conv.index)

        # Make sure the nodes are topologically sorted
        sorted_ops = [node['op'] for node in sorted(vertices, key=lambda x: int(re.search(r'\d+', x['name'])[0]))]

        # Delete nodes before transformation in the graph
        self.graph.graph.delete_vertices(remove_ids)

        for conv, mapping in zip(sorted_ops, restore_mapping):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tinynn/converter/operators/optimize.py [2844:2875]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        remove_ids = []
        ops = []
        restore_mapping = []
        for conv in vertices:
            restore_nodes = []
            # For each node that is next of a transformable node,
            #  a. if it is an output node, remove it anyway since it will always be reconstructed
            #  b. otherwise, record the info of the edge so that we may restore it after reconstruction
            for out_edge in conv.out_edges():
                next_node = self.graph.graph.vs[out_edge.target]
                if next_node['node_type'] == ExtendedOperator.OUTPUT_NODE:
                    remove_ids.append(next_node.index)
                    del self.graph.tensor_map[next_node['outputs'][0]]
                    del self.graph.tensor_node_map[next_node['outputs'][0]]
                else:
                    restore_nodes.append((out_edge['name'], next_node['name']))

            # Remove the mapping since they are going to be removed
            for output_name in conv['outputs']:
                del self.graph.tensor_map[output_name]
                del self.graph.tensor_node_map[output_name]

            restore_mapping.append(restore_nodes)
            remove_ids.append(conv.index)

        # Make sure the nodes are topologically sorted
        sorted_ops = [node['op'] for node in sorted(vertices, key=lambda x: int(re.search(r'\d+', x['name'])[0]))]

        # Delete nodes before transformation in the graph
        self.graph.graph.delete_vertices(remove_ids)

        for conv, mapping in zip(sorted_ops, restore_mapping):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -