camids.extend(camid)
feats = torch.cat(feats, dim=0)
q_feat = feats[:num_query]
g_feat = feats[num_query:]
q_pids = np.asarray(pids[:num_query])
g_pids = np.asarray(pids[num_query:])
q_camids = np.asarray(camids[:num_query])
g_camids = np.asarray(camids[num_query:])
# compute cosine distance
distmat = 1 - torch.mm(q_feat, g_feat.t())
distmat = distmat.numpy()
logger.info("Computing APs for all query images ...")
cmc, all_ap, all_inp = evaluate_rank(distmat, q_pids, g_pids, q_camids,
g_camids)
logger.info("Finish computing APs for all query images!")
visualizer = Visualizer(test_loader.dataset)
visualizer.get_model_output(all_ap, distmat, q_pids, g_pids, q_camids,
g_camids)
logger.info("Start saving ROC curve ...")
fpr, tpr, pos, neg = visualizer.vis_roc_curve(args.output)
visualizer.save_roc_info(args.output, fpr, tpr, pos, neg)
logger.info("Finish saving ROC curve!")
logger.info("Saving rank list result ...")
query_indices = visualizer.vis_rank_list(args.output, args.vis_label,
args.num_vis, args.rank_sort,
args.label_sort, args.max_rank)
dim = 512
max_rank = 5
q_feats = np.random.rand(num_q, dim).astype(np.float32) * 20
q_feats = q_feats / np.linalg.norm(q_feats, ord=2, axis=1, keepdims=True)
g_feats = np.random.rand(num_g, dim).astype(np.float32) * 20
g_feats = g_feats / np.linalg.norm(g_feats, ord=2, axis=1, keepdims=True)
distmat = 1 - np.dot(q_feats, g_feats.transpose())
q_pids = np.random.randint(0, num_q, size=num_q)
g_pids = np.random.randint(0, num_g, size=num_g)
q_camids = np.random.randint(0, 5, size=num_q)
g_camids = np.random.randint(0, 5, size=num_g)
cmc_py_d, mAP_py_d, mINP_py_d = evaluate_rank(distmat,
q_feats,
g_feats,
q_pids,
g_pids,
q_camids,
g_camids,
max_rank,
use_distmat=True,
use_cython=False)
cmc_py, mAP_py, mINP_py = evaluate_rank(distmat,
q_feats,
g_feats,
q_pids,
g_pids,
q_camids,
g_camids,
max_rank,
use_distmat=False,
use_cython=False)
np.testing.assert_allclose(cmc_py_d, cmc_py, rtol=1e-3, atol=1e-6)
# print('Python time: {} s'.format(pytime))
# print('Cython time: {} s'.format(cytime))
# print('Cython is {} times faster than python\n'.format(pytime / cytime))
from fastreid.evaluation import evaluate_rank
print("=> Check precision")
num_q = 30
num_g = 300
max_rank = 5
distmat = np.random.rand(num_q, num_g) * 20
q_pids = np.random.randint(0, num_q, size=num_q)
g_pids = np.random.randint(0, num_g, size=num_g)
q_camids = np.random.randint(0, 5, size=num_q)
g_camids = np.random.randint(0, 5, size=num_g)
cmc, mAP, mINP = evaluate_rank(distmat,
q_pids,
g_pids,
q_camids,
g_camids,
max_rank,
use_cython=False)
print("Python:\nmAP = {} \ncmc = {}\nmINP = {}".format(mAP, cmc, mINP))
cmc, mAP, mINP = evaluate_rank(distmat,
q_pids,
g_pids,
q_camids,
g_camids,
max_rank,
use_cython=True)
print("Cython:\nmAP = {} \ncmc = {}\nmINP = {}".format(mAP, cmc, mINP))