def test(model, queryloader, galleryloader, use_gpu, ranks=[1, 5, 10, 20]):
batch_time = AverageMeter()
model.eval(
) # model的测试阶段, 如果不加.eval(),下面人的features = model(imgs)=torch.Size([32, 751])
# querry共有3368人，每个人提取2048维特征，qf.shape=torch.Size([3368, 2048])
with torch.no_grad(): # 不用求导
qf, q_pids, q_camids = [], [], []
for batch_idx, (imgs, pids, camids) in enumerate(queryloader):
# len(queryloader)=106,x32=3392,实际3368人
# imgs.Size([32, 3, 256, 128])
# pids.torch.Size([32]),tensor([1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 6, 6,6, 6, 6, 8, 8, 8, 9, 9])
if use_gpu: imgs = imgs.cuda()
end = time.time()
features = model(
imgs
) # torch.Size([32, 2048])用于距离矩阵返回querry，对于train的model输出来讲是torch.Size([32, 2048])
batch_time.update(time.time() - end)
features = features.data.cpu()
qf.append(features)
q_pids.extend(pids)
q_camids.extend(camids)
qf = torch.cat(qf, 0) # torch.Size([3368, 2048])
q_pids = np.asarray(q_pids) # Out[4]: (3368,)
q_camids = np.asarray(q_camids)
print("Extracted features for query set, obtained {}-by-{} matrix".
format(qf.size(0), qf.size(1)))
# 提取gallery中15913个人，每个人生成2048为向量，gf.shape=torch.Size([15913, 2048])
gf, g_pids, g_camids = [], [], []
end = time.time()
for batch_idx, (imgs, pids, camids) in enumerate(
galleryloader): # 498x32=15936；实际排除-1标签后人数据为15913
if use_gpu: imgs = imgs.cuda()
end = time.time()
features = model(imgs) # torch.Size([32, 2048])
batch_time.update(time.time() - end)
features = features.data.cpu()
gf.append(features)
g_pids.extend(pids)
g_camids.extend(camids)
gf = torch.cat(gf, 0) # torch.Size([15913, 2048])
g_pids = np.asarray(g_pids)
g_camids = np.asarray(g_camids)
print("Extracted features for gallery set, obtained {}-by-{} matrix".
format(gf.size(0), gf.size(1)))
print("==> BatchTime(s)/BatchSize(img): {:.3f}/{}".format(
batch_time.avg, args.test_batch))
m, n = qf.size(0), gf.size(0)
distmat = torch.pow(qf, 2).sum(dim=1, keepdim=True).expand(m, n) + \
torch.pow(gf, 2).sum(dim=1, keepdim=True).expand(n, m).t()
distmat.addmm_(1, -2, qf, gf.t())
distmat = distmat.numpy()
print("Computing CMC and mAP") # 这个cmc就是rank_1--rank_n
cmc, mAP = evaluate(distmat,
q_pids,
g_pids,
q_camids,
g_camids,
use_metric_cuhk03=args.use_metric_cuhk03)
# distmat.shape=(3368, 15913) q_pids.shape=(3368,) g_pids.shape=(15913,) q_camids=(3368,) g_camids=(15913,)
print("Results ----------")
print("mAP: {:.1%}".format(mAP))
print("CMC curve")
for r in ranks:
print("Rank-{:<3}: {:.1%}".format(r, cmc[r - 1]))
print("------------------")
return cmc[0]
def test(model, queryloader, galleryloader, use_gpu, ranks=[1, 5, 10, 20]):
batch_time = AverageMeter()
model.eval()
with torch.no_grad():
qf, q_pids, q_camids = [], [], []
for batch_idx, (imgs, pids, camids) in enumerate(queryloader):
if use_gpu: imgs = imgs.cuda()
end = time.time()
features = model(imgs)
batch_time.update(time.time() - end)
features = features.data.cpu()
qf.append(features)
q_pids.extend(pids)
q_camids.extend(camids)
qf = torch.cat(qf, 0)
q_pids = np.asarray(q_pids)
q_camids = np.asarray(q_camids)
print("Extracted features for query set, obtained {}-by-{} matrix".format(qf.size(0), qf.size(1)))
gf, g_pids, g_camids = [], [], []
for batch_idx, (imgs, pids, camids) in enumerate(galleryloader):
if use_gpu: imgs = imgs.cuda()
end = time.time()
features = model(imgs)
batch_time.update(time.time() - end)
features = features.data.cpu()
gf.append(features)
g_pids.extend(pids)
g_camids.extend(camids)
gf = torch.cat(gf, 0)
g_pids = np.asarray(g_pids)
g_camids = np.asarray(g_camids)
print("Extracted features for gallery set, obtained {}-by-{} matrix".format(gf.size(0), gf.size(1)))
print("==> BatchTime(s)/BatchSize(img): {:.3f}/{}".format(batch_time.avg, args.test_batch))
m, n = qf.size(0), gf.size(0)
distmat = torch.pow(qf, 2).sum(dim=1, keepdim=True).expand(m, n) + \
torch.pow(gf, 2).sum(dim=1, keepdim=True).expand(n, m).t()
distmat.addmm_(1, -2, qf, gf.t())
distmat = distmat.numpy()
print("Computing CMC and mAP")
cmc, mAP = evaluate(distmat, q_pids, g_pids, q_camids, g_camids, use_metric_cuhk03=args.use_metric_cuhk03)
print("Results ----------")
print("mAP: {:.1%}".format(mAP))
print("CMC curve")
for r in ranks:
print("Rank-{:<3}: {:.1%}".format(r, cmc[r-1]))
print("------------------")
return cmc[0]