class TMVA_SOFIE_GNN.MLPGraphNetwork class TMVA_SOFIE_GNN.SofieGNN

Functions

TMVA_SOFIE_GNN.CopyData (input_data) TMVA_SOFIE_GNN.GenerateData () TMVA_SOFIE_GNN.get_graph_data_dict (num_nodes, num_edges, NODE_FEATURE_SIZE=2, EDGE_FEATURE_SIZE=2, GLOBAL_FEATURE_SIZE=1) TMVA_SOFIE_GNN.make_mlp_model () TMVA_SOFIE_GNN.PrintSofie (output, printShape=False) TMVA_SOFIE_GNN.RunGNet (inputGraphData) TMVA_SOFIE_GNN.c2 = c0.cd(2) TMVA_SOFIE_GNN.core = ROOT.TMVA.Experimental.SOFIE.RModel_GNN.ParseFromMemory(ep_model._core._network, CoreGraphData, filename = "gnn_core") TMVA_SOFIE_GNN.CoreGraphData = get_graph_data_dict(num_nodes, num_edges, 2*LATENT_SIZE, 2*LATENT_SIZE, 2*LATENT_SIZE) TMVA_SOFIE_GNN.data = GenerateData() list TMVA_SOFIE_GNN.dataSet = [] TMVA_SOFIE_GNN.DecodeGraphData = get_graph_data_dict(num_nodes,num_edges, LATENT_SIZE, LATENT_SIZE, LATENT_SIZE) TMVA_SOFIE_GNN.decoder = ROOT.TMVA.Experimental.SOFIE.RModel_GraphIndependent.ParseFromMemory(ep_model._decoder._network, DecodeGraphData, filename = "gnn_decoder") TMVA_SOFIE_GNN.edge_data TMVA_SOFIE_GNN.edge_index int TMVA_SOFIE_GNN.edge_size = 4 TMVA_SOFIE_GNN.edgesG = outGnet[1].edges.numpy() TMVA_SOFIE_GNN.edgesS = np.asarray(outSofie[1].edge_data) TMVA_SOFIE_GNN.encoder = ROOT.TMVA.Experimental.SOFIE.RModel_GraphIndependent.ParseFromMemory(ep_model._encoder._network, GraphData, filename = "gnn_encoder") TMVA_SOFIE_GNN.end = time.time() TMVA_SOFIE_GNN.endSC = time.time() TMVA_SOFIE_GNN.ep_model = EncodeProcessDecode() TMVA_SOFIE_GNN.g = out[1].globals.numpy() str TMVA_SOFIE_GNN.gen_code TMVA_SOFIE_GNN.global_data int TMVA_SOFIE_GNN.global_size = 1 TMVA_SOFIE_GNN.globG = outGnet[1].globals.numpy() TMVA_SOFIE_GNN.globS = np.asarray(outSofie[1].global_data) TMVA_SOFIE_GNN.gnet_data_i = utils_tf.data_dicts_to_graphs_tuple([graphData]) list TMVA_SOFIE_GNN.gnetData = [] TMVA_SOFIE_GNN.gnn = SofieGNN() TMVA_SOFIE_GNN.GraphData = get_graph_data_dict(num_nodes,num_edges, node_size, edge_size, global_size) list TMVA_SOFIE_GNN.graphData = dataSet[i] TMVA_SOFIE_GNN.hDe = ROOT.TH1D("hDe","Difference for edge data",40,1,0) TMVA_SOFIE_GNN.hDg = ROOT.TH1D("hDg","Difference for global data",40,1,0) TMVA_SOFIE_GNN.hDn = ROOT.TH1D("hDn","Difference for node data",40,1,0) TMVA_SOFIE_GNN.hG = ROOT.TH1D("hG","Result from graphnet",20,1,0) TMVA_SOFIE_GNN.hS = ROOT.TH1D("hS","Result from SOFIE",20,1,0) TMVA_SOFIE_GNN.input_core_graph_data = utils_tf.data_dicts_to_graphs_tuple([CoreGraphData]) TMVA_SOFIE_GNN.input_data = ROOT.TMVA.Experimental.SOFIE.GNN_Data() TMVA_SOFIE_GNN.input_graph_data = utils_tf.data_dicts_to_graphs_tuple([GraphData]) int TMVA_SOFIE_GNN.LATENT_SIZE = 100 TMVA_SOFIE_GNN.node_data int TMVA_SOFIE_GNN.node_size = 4 TMVA_SOFIE_GNN.nodesG = outGnet[1].nodes.numpy() TMVA_SOFIE_GNN.nodesS = np.asarray(outSofie[1].node_data) int TMVA_SOFIE_GNN.num_edges = 20 int TMVA_SOFIE_GNN.NUM_LAYERS = 4 int TMVA_SOFIE_GNN.num_nodes = 5 int TMVA_SOFIE_GNN.numevts = 40 TMVA_SOFIE_GNN.out = RunGNet(gnetData[i]) TMVA_SOFIE_GNN.outGnet = RunGNet(gnetData[i]) TMVA_SOFIE_GNN.output_gn = ep_model(input_graph_data, processing_steps) TMVA_SOFIE_GNN.output_transform = ROOT.TMVA.Experimental.SOFIE.RModel_GraphIndependent.ParseFromMemory(ep_model._output_transform._network, DecodeGraphData, filename = "gnn_output_transform") TMVA_SOFIE_GNN.outSofie = gnn.infer(sofieData[i]) int TMVA_SOFIE_GNN.processing_steps = 5 TMVA_SOFIE_GNN.rec = np.array([0,0,0,0,1,1,1,2,2,3,1,2,3,4,2,3,4,3,4,4], dtype='int32') TMVA_SOFIE_GNN.snd = np.array([1,2,3,4,2,3,4,3,4,4,0,0,0,0,1,1,1,2,2,3], dtype='int32') list TMVA_SOFIE_GNN.sofieData = [] TMVA_SOFIE_GNN.start = time.time() TMVA_SOFIE_GNN.start0 = time.time()

Detailed Description

Definition in file TMVA_SOFIE_GNN.py.