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 __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 __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)