coremltools/converters/keras/_topology.py [586:622]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                for pred in node.inbound_layers:
                    if pred.name not in self.layer_list:
                        self.layer_list.append(pred.name)
                        self.keras_layer_map[pred.name] = pred
                    self._add_edge(pred.name, layer.name)
            self.layer_list.append(layer.name)
            self.keras_layer_map[layer.name] = layer

        # Duplicate models for weight sharing
        idx = self._get_first_shared_layer()
        while idx >= 0:
            layer = self.layer_list[idx]
            keras_layer = self.keras_layer_map[layer]
            predecessors = self.reverse_edge_map[layer]
            successors = self.edge_map[layer]
            new_layers = [layer + "_" + str(i) for i in range(len(predecessors))]
            self.layer_list[idx : idx + 1] = new_layers
            for i, new_layer in enumerate(new_layers):
                self.edge_map[new_layer] = []
                self.reverse_edge_map[new_layer] = []
                self.keras_layer_map[new_layer] = keras_layer
                pred = predecessors[i]
                self._add_edge(pred, new_layer)
                for succ in successors:
                    self._add_edge(new_layer, succ)
            self._remove_old_edges(layer)
            self.keras_layer_map.pop(layer)
            idx = self._get_first_shared_layer()

        # Expand the sub-models
        idx = self._get_first_embedded_model()
        while idx >= 0:
            # grab the input and output edges of the embedded model
            embedded_model = self.layer_list[idx]
            # build the embedded model
            embedded_keras_model = self.keras_layer_map[embedded_model]
            embedded_graph = NetGraph(embedded_keras_model)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



coremltools/converters/keras/_topology2.py [703:739]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                for pred in node.inbound_layers:
                    if pred.name not in self.layer_list:
                        self.layer_list.append(pred.name)
                        self.keras_layer_map[pred.name] = pred
                    self._add_edge(pred.name, layer.name)
            self.layer_list.append(layer.name)
            self.keras_layer_map[layer.name] = layer

        # Duplicate models for weight sharing
        idx = self._get_first_shared_layer()
        while idx >= 0:
            layer = self.layer_list[idx]
            keras_layer = self.keras_layer_map[layer]
            predecessors = self.reverse_edge_map[layer]
            successors = self.edge_map[layer]
            new_layers = [layer + "_" + str(i) for i in range(len(predecessors))]
            self.layer_list[idx : idx + 1] = new_layers
            for i, new_layer in enumerate(new_layers):
                self.edge_map[new_layer] = []
                self.reverse_edge_map[new_layer] = []
                self.keras_layer_map[new_layer] = keras_layer
                pred = predecessors[i]
                self._add_edge(pred, new_layer)
                for succ in successors:
                    self._add_edge(new_layer, succ)
            self._remove_old_edges(layer)
            self.keras_layer_map.pop(layer)
            idx = self._get_first_shared_layer()

        # Expand the sub-models
        idx = self._get_first_embedded_model()
        while idx >= 0:
            # grab the input and output edges of the embedded model
            embedded_model = self.layer_list[idx]
            # build the embedded model
            embedded_keras_model = self.keras_layer_map[embedded_model]
            embedded_graph = NetGraph(embedded_keras_model)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -