def chinese_whispers_fast(feats, prefix, name, knn_method, knn, th_sim, iters, **kwargs): """ Chinese Whispers Clustering Algorithm Paper: Chinese whispers: an efficient graph clustering algorithm and its application to natural language processing problems. This implementation follows the matrix operation as described in Figure.4 int the paper. We switch the `maxrow` and `D^{t-1} * A_G` to make it easier for post-processing. The current result is inferior to `chinese_whispers` as it lacks of the random mechanism as the iterative algorithm. The paper introduce two operations to tackle this issue, namely `random mutation` and `keep class`. However, it is not very clear how to set this two hyper-parameters. """ assert len(feats) > 1 with Timer('create graph'): knn_prefix = os.path.join(prefix, 'knns', name) knns = build_knns(knn_prefix, feats, knn_method, knn) dists, nbrs = knns2ordered_nbrs(knns, sort=True) spmat = fast_knns2spmat(knns, knn, th_sim, use_sim=True) A = build_symmetric_adj(spmat, self_loop=False) node_num = len(feats) edge_num = A.nnz print('#nodes: {}, #edges: {}'.format(node_num, edge_num)) with Timer('whisper iteratively (iters={})'.format(iters)): D = identity(node_num) for _ in range(iters): D = D * A # it is equal to D.dot(A) D = _maxrow(D, node_num) assert D.nnz == node_num clusters = {} assigned_clusters = D.tocoo().col for (node, assigned_cluster) in enumerate(assigned_clusters): if assigned_cluster not in clusters: clusters[assigned_cluster] = [] clusters[assigned_cluster].append(node) print('#cluster: {}'.format(len(clusters))) labels = clusters2labels(clusters.values()) labels = list(labels.values()) return labels
def __init__(self, features, labels, cluster_features=None, k=10, levels=1, faiss_gpu=False): self.k = k self.gs = [] self.nbrs = [] self.dists = [] self.levels = levels # Initialize features and labels features = l2norm(features.astype('float32')) global_features = features.copy() if cluster_features is None: cluster_features = features global_num_nodes = features.shape[0] global_edges = ([], []) global_peaks = np.array([], dtype=np.long) ids = np.arange(global_num_nodes) # Recursive graph construction for lvl in range(self.levels): if features.shape[0] <= self.k: self.levels = lvl break if faiss_gpu: knns = build_knns(features, self.k, 'faiss_gpu') else: knns = build_knns(features, self.k, 'faiss') dists, nbrs = knns2ordered_nbrs(knns) self.nbrs.append(nbrs) self.dists.append(dists) density = density_estimation(dists, nbrs, labels) g = self._build_graph(features, cluster_features, labels, density, knns) self.gs.append(g) if lvl >= self.levels - 1: break # Decode peak nodes new_pred_labels, peaks,\ global_edges, global_pred_labels, global_peaks = decode(g, 0, 'sim', True, ids, global_edges, global_num_nodes, global_peaks) ids = ids[peaks] features, labels, cluster_features = build_next_level(features, labels, peaks, global_features, global_pred_labels, global_peaks)
def __init__(self, cfg): feat_path = cfg['feat_path'] label_path = cfg.get('label_path', None) knn_graph_path = cfg['knn_graph_path'] self.k_at_hop = cfg['k_at_hop'] self.depth = len(self.k_at_hop) self.active_connection = cfg['active_connection'] self.feature_dim = cfg['feature_dim'] self.is_norm_feat = cfg.get('is_norm_feat', True) self.is_sort_knns = cfg.get('is_sort_knns', True) self.is_test = cfg.get('is_test', False) with Timer('read meta and feature'): if label_path is not None: _, idx2lb = read_meta(label_path) self.inst_num = len(idx2lb) self.labels = intdict2ndarray(idx2lb) self.ignore_label = False else: self.labels = None self.inst_num = -1 self.ignore_label = True self.features = read_probs(feat_path, self.inst_num, self.feature_dim) if self.is_norm_feat: self.features = l2norm(self.features) if self.inst_num == -1: self.inst_num = self.features.shape[0] self.size = self.inst_num with Timer('read knn graph'): knns = np.load(knn_graph_path)['data'] _, self.knn_graph = knns2ordered_nbrs(knns, sort=self.is_sort_knns) assert np.mean(self.k_at_hop) >= self.active_connection print('feature shape: {}, norm_feat: {}, sort_knns: {} ' 'k_at_hop: {}, active_connection: {}'.format( self.features.shape, self.is_norm_feat, self.is_sort_knns, self.k_at_hop, self.active_connection))
def __init__(self, cfg): feat_path = cfg['feat_path'] label_path = cfg.get('label_path', None) knn_graph_path = cfg.get('knn_graph_path', None) self.k = cfg['k'] self.feature_dim = cfg['feature_dim'] self.is_norm_feat = cfg.get('is_norm_feat', True) self.th_sim = cfg.get('th_sim', 0.) self.max_conn = cfg.get('max_conn', 1) self.ignore_ratio = cfg.get('ignore_ratio', 0.8) self.ignore_small_confs = cfg.get('ignore_small_confs', True) self.use_candidate_set = cfg.get('use_candidate_set', True) self.nproc = cfg.get('nproc', 1) self.max_qsize = cfg.get('max_qsize', int(1e5)) with Timer('read meta and feature'): if label_path is not None: self.lb2idxs, self.idx2lb = read_meta(label_path) self.inst_num = len(self.idx2lb) self.gt_labels = intdict2ndarray(self.idx2lb) self.ignore_label = False else: self.inst_num = -1 self.ignore_label = True self.features = read_probs(feat_path, self.inst_num, self.feature_dim) if self.is_norm_feat: self.features = l2norm(self.features) if self.inst_num == -1: self.inst_num = self.features.shape[0] self.size = self.inst_num assert self.size == self.features.shape[0] print('feature shape: {}, k: {}, norm_feat: {}'.format( self.features.shape, self.k, self.is_norm_feat)) with Timer('read knn graph'): if knn_graph_path is not None: knns = np.load(knn_graph_path)['data'] else: prefix = osp.dirname(feat_path) name = rm_suffix(osp.basename(feat_path)) # find root folder of `features` prefix = osp.dirname(prefix) knn_prefix = osp.join(prefix, 'knns', name) knns = build_knns(knn_prefix, self.features, cfg.knn_method, cfg.knn) assert self.inst_num == len(knns), "{} vs {}".format( self.inst_num, len(knns)) adj = fast_knns2spmat(knns, self.k, self.th_sim, use_sim=True) # build symmetric adjacency matrix adj = build_symmetric_adj(adj, self_loop=True) self.adj = row_normalize(adj) # convert knns to (dists, nbrs) self.dists, self.nbrs = knns2ordered_nbrs(knns, sort=True) if cfg.pred_confs != '': print('read estimated confidence from {}'.format( cfg.pred_confs)) self.confs = np.load(cfg.pred_confs)['pred_confs'] else: print('use unsupervised density as confidence') assert self.radius from vegcn.confidence import density self.confs = density(self.dists, radius=self.radius) assert 0 <= self.ignore_ratio <= 1 if self.ignore_ratio == 1: self.ignore_set = set(np.arange(len(self.confs))) else: num = int(len(self.confs) * self.ignore_ratio) confs = self.confs if not self.ignore_small_confs: confs = -confs self.ignore_set = set(np.argpartition(confs, num)[:num]) print( 'ignore_ratio: {}, ignore_small_confs: {}, use_candidate_set: {}'. format(self.ignore_ratio, self.ignore_small_confs, self.use_candidate_set)) print('#ignore_set: {} / {} = {:.3f}'.format( len(self.ignore_set), self.inst_num, 1. * len(self.ignore_set) / self.inst_num)) with Timer('Prepare sub-graphs'): # construct subgraphs with larger confidence self.peaks = {i: [] for i in range(self.inst_num)} self.dist2peak = {i: [] for i in range(self.inst_num)} if self.nproc > 1: # multi-process import multiprocessing as mp pool = mp.Pool(self.nproc) results = [] num = int(self.inst_num / self.max_qsize) + 1 for i in tqdm(range(num)): beg = int(i * self.max_qsize) end = min(beg + self.max_qsize, self.inst_num) lst = [j for j in range(beg, end)] results.extend( list( tqdm(pool.map(self.get_subgraph, lst), total=len(lst)))) pool.close() pool.join() else: results = [ self.get_subgraph(i) for i in tqdm(range(self.inst_num)) ] self.adj_lst = [] self.feat_lst = [] self.lb_lst = [] self.subset_gt_labels = [] self.subset_idxs = [] self.subset_nbrs = [] self.subset_dists = [] for result in results: if result is None: continue elif len(result) == 3: i, nbr, dist = result self.peaks[i].extend(nbr) self.dist2peak[i].extend(dist) continue i, nbr, dist, feat, adj, lb = result self.subset_idxs.append(i) self.subset_nbrs.append(nbr) self.subset_dists.append(dist) self.feat_lst.append(feat) self.adj_lst.append(adj) if not self.ignore_label: self.subset_gt_labels.append(self.idx2lb[i]) self.lb_lst.append(lb) self.subset_gt_labels = np.array(self.subset_gt_labels) self.size = len(self.feat_lst) assert self.size == len(self.adj_lst) if not self.ignore_label: assert self.size == len(self.lb_lst)
def __init__(self, cfg): feat_path = cfg['feat_path'] label_path = cfg.get('label_path', None) knn_graph_path = cfg.get('knn_graph_path', None) self.k = cfg['k'] self.feature_dim = cfg['feature_dim'] self.is_norm_feat = cfg.get('is_norm_feat', True) self.save_decomposed_adj = cfg.get('save_decomposed_adj', False) self.th_sim = cfg.get('th_sim', 0.) self.max_conn = cfg.get('max_conn', 1) self.conf_metric = cfg.get('conf_metric') with Timer('read meta and feature'): if label_path is not None: self.lb2idxs, self.idx2lb = read_meta(label_path) self.inst_num = len(self.idx2lb) self.gt_labels = intdict2ndarray(self.idx2lb) self.ignore_label = False else: self.inst_num = -1 self.ignore_label = True self.features = read_probs(feat_path, self.inst_num, self.feature_dim) if self.is_norm_feat: self.features = l2norm(self.features) if self.inst_num == -1: self.inst_num = self.features.shape[0] self.size = 1 # take the entire graph as input with Timer('read knn graph'): if os.path.isfile(knn_graph_path): knns = np.load(knn_graph_path)['data'] else: if knn_graph_path is not None: print('knn_graph_path does not exist: {}'.format( knn_graph_path)) prefix = osp.dirname(feat_path) name = rm_suffix(osp.basename(feat_path)) # find root folder of `features` prefix = osp.dirname(prefix) knn_prefix = osp.join(prefix, 'knns', name) knns = build_knns(knn_prefix, self.features, cfg.knn_method, cfg.knn) adj = fast_knns2spmat(knns, self.k, self.th_sim, use_sim=True) # build symmetric adjacency matrix adj = build_symmetric_adj(adj, self_loop=True) adj = row_normalize(adj) if self.save_decomposed_adj: adj = sparse_mx_to_indices_values(adj) self.adj_indices, self.adj_values, self.adj_shape = adj else: self.adj = adj # convert knns to (dists, nbrs) self.dists, self.nbrs = knns2ordered_nbrs(knns) print('feature shape: {}, k: {}, norm_feat: {}'.format( self.features.shape, self.k, self.is_norm_feat)) if not self.ignore_label: with Timer('Prepare ground-truth label'): self.labels = confidence(feats=self.features, dists=self.dists, nbrs=self.nbrs, metric=self.conf_metric, idx2lb=self.idx2lb, lb2idxs=self.lb2idxs) if cfg.eval_interim: _, self.peaks = confidence_to_peaks( self.dists, self.nbrs, self.labels, self.max_conn)
def test_gcn_v(model, cfg, logger): for k, v in cfg.model['kwargs'].items(): setattr(cfg.test_data, k, v) dataset = build_dataset(cfg.model['type'], cfg.test_data) folder = '{}_gcnv_k_{}_th_{}'.format(cfg.test_name, cfg.knn, cfg.th_sim) oprefix = osp.join(cfg.work_dir, folder) oname = osp.basename(rm_suffix(cfg.load_from)) opath_pred_confs = osp.join(oprefix, 'pred_confs', '{}.npz'.format(oname)) if osp.isfile(opath_pred_confs) and not cfg.force: data = np.load(opath_pred_confs) pred_confs = data['pred_confs'] inst_num = data['inst_num'] if inst_num != dataset.inst_num: logger.warn( 'instance number in {} is different from dataset: {} vs {}'. format(opath_pred_confs, inst_num, len(dataset))) else: pred_confs, gcn_feat = test(model, dataset, cfg, logger) inst_num = dataset.inst_num logger.info('pred_confs: mean({:.4f}). max({:.4f}), min({:.4f})'.format( pred_confs.mean(), pred_confs.max(), pred_confs.min())) logger.info('Convert to cluster') with Timer('Predition to peaks'): pred_dist2peak, pred_peaks = confidence_to_peaks( dataset.dists, dataset.nbrs, pred_confs, cfg.max_conn) if not dataset.ignore_label and cfg.eval_interim: # evaluate the intermediate results for i in range(cfg.max_conn): num = len(dataset.peaks) pred_peaks_i = np.arange(num) peaks_i = np.arange(num) for j in range(num): if len(pred_peaks[j]) > i: pred_peaks_i[j] = pred_peaks[j][i] if len(dataset.peaks[j]) > i: peaks_i[j] = dataset.peaks[j][i] acc = accuracy(pred_peaks_i, peaks_i) logger.info('[{}-th conn] accuracy of peak match: {:.4f}'.format( i + 1, acc)) acc = 0. for idx, peak in enumerate(pred_peaks_i): acc += int(dataset.idx2lb[peak] == dataset.idx2lb[idx]) acc /= len(pred_peaks_i) logger.info( '[{}-th conn] accuracy of peak label match: {:.4f}'.format( i + 1, acc)) with Timer('Peaks to clusters (th_cut={})'.format(cfg.tau_0)): pred_labels = peaks_to_labels(pred_peaks, pred_dist2peak, cfg.tau_0, inst_num) if cfg.save_output: logger.info('save predicted confs to {}'.format(opath_pred_confs)) mkdir_if_no_exists(opath_pred_confs) np.savez_compressed(opath_pred_confs, pred_confs=pred_confs, inst_num=inst_num) # save clustering results idx2lb = list2dict(pred_labels, ignore_value=-1) opath_pred_labels = osp.join( cfg.work_dir, folder, 'tau_{}_pred_labels.txt'.format(cfg.tau_0)) logger.info('save predicted labels to {}'.format(opath_pred_labels)) mkdir_if_no_exists(opath_pred_labels) write_meta(opath_pred_labels, idx2lb, inst_num=inst_num) # evaluation if not dataset.ignore_label: print('==> evaluation') for metric in cfg.metrics: evaluate(dataset.gt_labels, pred_labels, metric) if cfg.use_gcn_feat: # gcn_feat is saved to disk for GCN-E opath_feat = osp.join(oprefix, 'features', '{}.bin'.format(oname)) if not osp.isfile(opath_feat) or cfg.force: mkdir_if_no_exists(opath_feat) write_feat(opath_feat, gcn_feat) name = rm_suffix(osp.basename(opath_feat)) prefix = oprefix ds = BasicDataset(name=name, prefix=prefix, dim=cfg.model['kwargs']['nhid'], normalize=True) ds.info() # use top embedding of GCN to rebuild the kNN graph with Timer('connect to higher confidence with use_gcn_feat'): knn_prefix = osp.join(prefix, 'knns', name) knns = build_knns(knn_prefix, ds.features, cfg.knn_method, cfg.knn, is_rebuild=True) dists, nbrs = knns2ordered_nbrs(knns) pred_dist2peak, pred_peaks = confidence_to_peaks( dists, nbrs, pred_confs, cfg.max_conn) pred_labels = peaks_to_labels(pred_peaks, pred_dist2peak, cfg.tau, inst_num) # save clustering results if cfg.save_output: oname_meta = '{}_gcn_feat'.format(name) opath_pred_labels = osp.join( oprefix, oname_meta, 'tau_{}_pred_labels.txt'.format(cfg.tau)) mkdir_if_no_exists(opath_pred_labels) idx2lb = list2dict(pred_labels, ignore_value=-1) write_meta(opath_pred_labels, idx2lb, inst_num=inst_num) # evaluation if not dataset.ignore_label: print('==> evaluation') for metric in cfg.metrics: evaluate(dataset.gt_labels, pred_labels, metric) import json import os import pdb pdb.set_trace() img_labels = json.load( open(r'/home/finn/research/data/clustering_data/test_index.json', 'r', encoding='utf-8')) import shutil output = r'/home/finn/research/data/clustering_data/mr_gcn_output' for label in set(pred_labels): if not os.path.exists(os.path.join(output, f'cluter_{label}')): os.mkdir(os.path.join(output, f'cluter_{label}')) for image in img_labels: shutil.copy2( image, os.path.join( os.path.join(output, f'cluter_{pred_labels[img_labels[image]]}'), os.path.split(image)[-1]))
def chinese_whispers(feats, prefix, name, knn_method, knn, th_sim, iters, **kwargs): """ Chinese Whispers Clustering Algorithm Paper: Chinese whispers: an efficient graph clustering algorithm and its application to natural language processing problems. Reference code: - http://alexloveless.co.uk/data/chinese-whispers-graph-clustering-in-python/ - https://github.com/zhly0/facenet-face-cluster-chinese-whispers- """ import networkx as nx assert len(feats) > 1 with Timer('create graph'): knn_prefix = os.path.join(prefix, 'knns', name) knns = build_knns(knn_prefix, feats, knn_method, knn) dists, nbrs = knns2ordered_nbrs(knns, sort=True) spmat = fast_knns2spmat(knns, knn, th_sim, use_sim=True) size = len(feats) nodes = [(n_i, {'cluster': n_i}) for n_i in range(size)] c = spmat.tocoo() edges = [(n_i, n_j, { 'weight': s }) for n_i, n_j, s in zip(c.row, c.col, c.data)] G = nx.Graph() G.add_nodes_from(nodes) G.add_edges_from(edges) node_num = G.number_of_nodes() edge_num = G.number_of_edges() assert size == node_num print('#nodes: {}, #edges: {}'.format(node_num, edge_num)) with Timer('whisper iteratively (iters={})'.format(iters)): cluster_nodes = list(G.nodes()) for _ in range(iters): idxs = [i for i in range(node_num)] random.shuffle(idxs) for idx in idxs: node = cluster_nodes[idx] nbrs = G[node] if len(nbrs) == 0: continue cluster2weight = {} for nbr in nbrs: assigned_cluster = G.node[nbr]['cluster'] edge_weight = G[node][nbr]['weight'] if assigned_cluster not in cluster2weight: cluster2weight[assigned_cluster] = 0 cluster2weight[assigned_cluster] += edge_weight # set the class of node to its neighbor with largest weight cluster2weight = sorted(cluster2weight.items(), key=lambda kv: kv[1], reverse=True) G.node[node]['cluster'] = cluster2weight[0][0] clusters = {} for (node, data) in G.node.items(): assigned_cluster = data['cluster'] if assigned_cluster not in clusters: clusters[assigned_cluster] = [] clusters[assigned_cluster].append(node) print('#cluster: {}'.format(len(clusters))) labels = clusters2labels(clusters.values()) labels = list(labels.values()) return labels
def __init__(self, cfg): feat_path = cfg['feat_path'] label_path = cfg.get('label_path', None) knn_graph_path = cfg.get('knn_graph_path', None) self.k = cfg['k'] self.feature_dim = cfg['feature_dim'] self.is_norm_feat = cfg.get('is_norm_feat', True) self.save_decomposed_adj = cfg.get('save_decomposed_adj', False) self.th_sim = cfg.get('th_sim', 0.) self.max_conn = cfg.get('max_conn', 1) self.conf_metric = cfg.get('conf_metric') self.num_process = cfg.get('num_process',16) with Timer('read meta and feature'): if label_path is not None: self.lb2idxs, self.idx2lb = read_meta(label_path) self.inst_num = len(self.idx2lb) self.gt_labels = intdict2ndarray(self.idx2lb) self.ignore_label = False else: self.inst_num = -1 self.ignore_label = True self.features = read_probs(feat_path, self.inst_num, self.feature_dim) if self.is_norm_feat: self.features = l2norm(self.features) if self.inst_num == -1: self.inst_num = self.features.shape[0] self.size = 1 # take the entire graph as input with Timer('read knn graph'): if os.path.isfile(knn_graph_path): knns = np.load(knn_graph_path)['data'] # num_imgs*2*k else: if knn_graph_path is not None: print('knn_graph_path does not exist: {}'.format( knn_graph_path)) knn_prefix = os.path.join(cfg.prefix, 'knns', cfg.name) # 通过faiss实现k近邻搜索,此处作者faiss_gpu版本实现可能有问题,但faiss大规模在cpu上跑还是慢 # 当然faiss有针内存和计算速度方面的优化,PQ,IVF等,可参考faiss knns = build_knns(knn_prefix, self.features, cfg.knn_method, cfg.knn,self.num_process) # 依据k近邻搜索结果构建邻接矩阵 adj = fast_knns2spmat(knns, self.k, self.th_sim, use_sim=True) # build symmetric adjacency matrix adj = build_symmetric_adj(adj, self_loop=True) adj = row_normalize(adj) if self.save_decomposed_adj: adj = sparse_mx_to_indices_values(adj) self.adj_indices, self.adj_values, self.adj_shape = adj else: self.adj = adj # convert knns to (dists, nbrs) self.dists, self.nbrs = knns2ordered_nbrs(knns) # num_imgs*k print('feature shape: {}, k: {}, norm_feat: {}'.format( self.features.shape, self.k, self.is_norm_feat)) if not self.ignore_label: with Timer('Prepare ground-truth label'): self.labels = confidence(feats=self.features, dists=self.dists, nbrs=self.nbrs, metric=self.conf_metric, idx2lb=self.idx2lb, lb2idxs=self.lb2idxs) if cfg.eval_interim: _, self.peaks = confidence_to_peaks( self.dists, self.nbrs, self.labels, self.max_conn)
def __init__(self, cfg): feat_path = cfg['feat_path'] label_path = cfg.get('label_path', None) knn_graph_path = cfg.get('knn_graph_path', None) self.k = cfg['k'] self.feature_dim = cfg['feature_dim'] self.is_norm_feat = cfg.get('is_norm_feat', True) self.save_decomposed_adj = cfg.get('save_decomposed_adj', False) self.th_sim = cfg.get('th_sim', 0.) self.conf_metric = cfg.get('conf_metric') with Timer('read meta and feature'): if label_path is not None: self.lb2idxs, self.idx2lb = read_meta(label_path) self.inst_num = len(self.idx2lb) self.cls_num = len(self.lb2idxs) self.gt_labels = intdict2ndarray(self.idx2lb) self.ignore_label = False else: self.inst_num = -1 self.ignore_label = True self.features = read_probs(feat_path, self.inst_num, self.feature_dim) if self.is_norm_feat: self.features = l2norm(self.features) if self.inst_num == -1: self.inst_num = self.features.shape[0] self.size = 1 # take the entire graph as input with Timer('Compute center feature'): self.center_fea = np.zeros((self.cls_num, self.features.shape[1])) for i in range(self.cls_num): self.center_fea[i] = np.mean(self.features[self.lb2idxs[i]], 0) self.center_fea = l2norm(self.center_fea) with Timer('read knn graph'): if os.path.isfile(knn_graph_path): print("load knns from the knn_path") self.knns = np.load(knn_graph_path)['data'] else: if knn_graph_path is not None: print('knn_graph_path does not exist: {}'.format( knn_graph_path)) knn_prefix = os.path.join(cfg.prefix, 'knns', cfg.name) self.knns = build_knns(knn_prefix, self.features, cfg.knn_method, cfg.knn) adj = fast_knns2spmat(self.knns, self.k, self.th_sim, use_sim=True) # build symmetric adjacency matrix adj = build_symmetric_adj(adj, self_loop=True) #print('adj before norm') #print(adj) adj = row_normalize(adj) if self.save_decomposed_adj: adj = sparse_mx_to_indices_values(adj) self.adj_indices, self.adj_values, self.adj_shape = adj else: self.adj = adj # convert knns to (dists, nbrs) self.dists, self.nbrs = knns2ordered_nbrs(self.knns) print('feature shape: {}, k: {}, norm_feat: {}'.format( self.features.shape, self.k, self.is_norm_feat))