def test(self):
epoch = self.scheduler.last_epoch + 1
self.ckpt.write_log('\n[INFO] Test:')
self.model.eval()
self.ckpt.add_log(torch.zeros(1, 5))
# get the encodings/features for the query dataset
# the result size for example in the market query dataset
# is 3368 X 2048 since there are 3368 query photos
qf = self.extract_feature(self.query_loader).numpy()
# get the encodings/features for the query dataset
# the result size for example in the market gallery dataset
# is 15913 X 2048 since there are 15913 gallery photos
gf = self.extract_feature(self.test_loader).numpy()
if self.args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
# dist will end up being a 2D matrix of size #query_photos X #gallery_photos
# in case of market, this is 3368 X 15913
# thus, dist[0][0] is the distance between query_photo[0] to gallery_photo[0]
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
else:
# each image is represented by a vector of size 2048 which are its "features/encoding"
# distance is calculated here using euclidian distances between the cross product
# of each query image with each gallery image
dist = cdist(qf, gf)
r = cmc(dist,
self.queryset.ids,
self.testset.ids,
self.queryset.cameras,
self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
m_ap = mean_ap(dist, epoch, self.queryset.ids, self.testset.ids,
self.queryset.cameras, self.testset.cameras)
self.ckpt.log[-1, 0] = m_ap
self.ckpt.log[-1, 1] = r[0]
self.ckpt.log[-1, 2] = r[2]
self.ckpt.log[-1, 3] = r[4]
self.ckpt.log[-1, 4] = r[9]
best = self.ckpt.log.max(0)
self.ckpt.write_log(
'[INFO] mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'
.format(m_ap, r[0], r[2], r[4], r[9], best[0][0],
(best[1][0] + 1) * self.args.test_every))
if not self.args.test_only:
self.ckpt.save(self,
epoch,
is_best=((best[1][0] + 1) *
self.args.test_every == epoch))
def test(self):
epoch = self.scheduler.last_epoch + 1
# print("test=")
# print(epoch)
self.ckpt.write_log('\n[INFO] Test:')
self.model.eval()
# print("after eval")
self.ckpt.add_log(torch.zeros(1, 5))
qf = self.extract_feature(self.query_loader).numpy()
gf = self.extract_feature(self.test_loader).numpy()
# print("111")
if self.args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
else:
dist = cdist(qf, gf)
# print("222")
r = cmc(dist,
self.queryset.ids,
self.testset.ids,
self.queryset.cameras,
self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
m_ap = mean_ap(dist, self.queryset.ids, self.testset.ids,
self.queryset.cameras, self.testset.cameras)
self.ckpt.log[-1, 0] = m_ap
self.ckpt.log[-1, 1] = r[0]
self.ckpt.log[-1, 2] = r[2]
self.ckpt.log[-1, 3] = r[4]
self.ckpt.log[-1, 4] = r[9]
best = self.ckpt.log.max(0)
# print("333")
self.ckpt.write_log(
'[INFO] mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'
.format(m_ap, r[0], r[2], r[4], r[9], best[0][0],
(best[1][0] + 1) * self.args.test_every))
if not self.args.test_only:
self.ckpt.save(self,
epoch,
is_best=((best[1][0] + 1) *
self.args.test_every == epoch))
def test(self):
epoch = self.scheduler.last_epoch + 1
self.ckpt.write_log('\n[INFO] Test:')
self.model.eval()
# print("$$$$$$$$$$$$$$$$$$$")
# print(self.attackset.ids)
self.ckpt.add_log(torch.zeros(1, 5))
qf = self.extract_feature(self.attack_loader).numpy()
# gradients = torch.autograd.grad(qf, self.query_loader)[0]
# adversarial_examples = self.query_loader+(0.1*gradients.sign())
# adversarial_examples = torch.clamp(adversarial_examples, min=0, max=1).detach()
# qf = self.extract_feature(adversarial_examples)
gf = self.extract_feature(self.test_loader).numpy()
# print(qf.shape())
# print(gf.shape())
# print("###############")
if self.args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
else:
dist = cdist(qf, gf)
r = cmc(dist,
self.attackset.ids,
self.testset.ids,
self.attackset.cameras,
self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
m_ap = mean_ap(dist, self.attackset.ids, self.testset.ids,
self.attackset.cameras, self.testset.cameras)
self.ckpt.log[-1, 0] = m_ap
self.ckpt.log[-1, 1] = r[0]
self.ckpt.log[-1, 2] = r[2]
self.ckpt.log[-1, 3] = r[4]
self.ckpt.log[-1, 4] = r[9]
best = self.ckpt.log.max(0)
self.ckpt.write_log(
'[INFO] mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'
.format(m_ap, r[0], r[2], r[4], r[9], best[0][0],
(best[1][0] + 1) * self.args.test_every))
if not self.args.test_only:
self.ckpt.save(self,
epoch,
is_best=((best[1][0] + 1) *
self.args.test_every == epoch))
def test(self):
self.epoch = self.scheduler.last_epoch + 1
self.ckpt.write_log('\n[INFO] Test:')
self.ckpt.add_log(torch.zeros(1, 5))
qf = self.extract_feature(self.query_loader)
gf = self.extract_feature(self.test_loader)
# save feature, cam, label, frames
#pytorch_result = {'query_f':qf, 'query_cam':self.queryset.cameras,
# 'query_label':self.queryset.ids, 'query_frames':self.queryset.frames,
# 'gallery_f':gf, 'gallery_cam':self.testset.cameras,
# 'gallery_label':self.testset.ids, 'gallery_frames':self.testset.frames}
#savemat('./pytorch_result.mat',pytorch_result)
#print('saved')
if self.args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
else:
dist = cdist(qf, gf)
r = cmc(dist, self.queryset.ids, self.testset.ids, self.queryset.cameras, self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
m_ap = mean_ap(dist, self.queryset.ids, self.testset.ids, self.queryset.cameras, self.testset.cameras)
self.ckpt.log[-1, 0] = m_ap
self.ckpt.log[-1, 1] = r[0]
self.ckpt.log[-1, 2] = r[2]
self.ckpt.log[-1, 3] = r[4]
self.ckpt.log[-1, 4] = r[9]
best = self.ckpt.log.max(0)
self.ckpt.write_log(
'[INFO] mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'.format(
m_ap,
r[0], r[2], r[4], r[9],
best[0][0],
(best[1][0] + 1)*self.args.test_every
)
)
if not self.args.test:
self.ckpt.save(self, self.epoch, is_best=((best[1][0] + 1)*self.args.test_every == self.epoch))
def test(self):
epoch = self.scheduler.last_epoch + 1
self.ckpt.write_log('\n[INFO] Test:')
self.model.eval()
self.ckpt.add_log(torch.zeros(1, 5))
qf, q_image_paths = self.extract_feature(self.query_loader)
gf, _ = self.extract_feature(self.test_loader)
qf = qf.numpy() # (31, 2048) for debug
gf = gf.numpy() # (154, 2048) for
if self.args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
else:
dist = cdist(qf, gf, metric='cosine')
if self.args.multi_query:
# Suitable for boxes dataset only
# Use several same id query samples to retrieval one gallery
print(dist.shape) # (31, 154)
ids = [
int(x.split(os.sep)[-1].split('_')[0]) for x in q_image_paths
]
ids_set = set(ids)
ids_np = np.asarray(ids, dtype=np.int32)
for id in ids_set:
indices = np.where(ids_np == id)[0]
mean = np.mean(dist[indices, :], axis=0)
for index in indices:
dist[index, :] = mean
r = cmc(dist,
self.queryset.ids,
self.testset.ids,
self.queryset.cameras,
self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
m_ap = mean_ap(dist, self.queryset.ids, self.testset.ids,
self.queryset.cameras, self.testset.cameras)
self.ckpt.log[-1, 0] = m_ap
self.ckpt.log[-1, 1] = r[0]
self.ckpt.log[-1, 2] = r[2]
self.ckpt.log[-1, 3] = r[4]
self.ckpt.log[-1, 4] = r[9]
best = self.ckpt.log.max(0)
self.ckpt.write_log(
'[INFO] mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'
.format(m_ap, r[0], r[2], r[4], r[9], best[0][0],
(best[1][0] + 1) * self.args.test_every))
# Another method to calculate cmc and mAP, it get the same result!
# print(eval_market1501(dist, self.queryset.ids, self.testset.ids,
# self.queryset.cameras, self.testset.cameras, 100))
if not self.args.test_only:
self.ckpt.save(self,
epoch,
is_best=((best[1][0] + 1) *
self.args.test_every == epoch))
def test(self):
epoch = self.scheduler.last_epoch + 1
self.ckpt.write_log('\n[INFO] Test:')
self.model.eval()
self.ckpt.add_log(torch.zeros(1, 5))
qf = self.extract_feature(self.query_loader).numpy()
gf = self.extract_feature(self.test_loader).numpy()
# distence threshold
norms_q = np.linalg.norm(qf, axis=1) # axis=1, l1范数
norms_g = np.linalg.norm(gf, axis=1)
qf = qf / np.reshape(norms_q, ((qf.shape)[0], 1))
gf = gf / np.reshape(norms_g, ((gf.shape)[0], 1))
# no rerank
dist = cdist(
qf,
gf) # metric='cosine'，计算两个矩阵行间的所有向量对的距离,默认：euclidean; 3368*15913
m_ap = mean_ap(dist, self.queryset.ids, self.testset.ids,
self.queryset.cameras, self.testset.cameras)
r = cmc(dist,
self.queryset.ids,
self.testset.ids,
self.queryset.cameras,
self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
self.ckpt.log[-1, 0] = m_ap
self.ckpt.log[-1, 1] = r[0]
self.ckpt.log[-1, 2] = r[2]
self.ckpt.log[-1, 3] = r[4]
self.ckpt.log[-1, 4] = r[9]
best = self.ckpt.log.max(0)
self.ckpt.write_log(
'[INFO]( ^_^ ) mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'
.format(m_ap, r[0], r[2], r[4], r[9], best[0][0],
(best[1][0] + 1) * self.args.test_every))
# rerank
if self.args.re_rank:
q_g_dist = np.dot(qf, np.transpose(gf))
q_q_dist = np.dot(qf, np.transpose(qf))
g_g_dist = np.dot(gf, np.transpose(gf))
dist_rerank = re_ranking(q_g_dist, q_q_dist, g_g_dist)
r_rerank = cmc(dist_rerank,
self.queryset.ids,
self.testset.ids,
self.queryset.cameras,
self.testset.cameras,
separate_camera_set=False,
single_gallery_shot=False,
first_match_break=True)
map_rerank = mean_ap(dist_rerank, self.queryset.ids, self.testset.ids,
self.queryset.cameras, self.testset.cameras)
self.ckpt.log[-1, 0] = map_rerank
self.ckpt.log[-1, 1] = r_rerank[0]
self.ckpt.log[-1, 2] = r_rerank[2]
self.ckpt.log[-1, 3] = r_rerank[4]
self.ckpt.log[-1, 4] = r_rerank[9]
best = self.ckpt.log.max(0)
self.ckpt.write_log(
'[INFO](rerank) mAP: {:.4f} rank1: {:.4f} rank3: {:.4f} rank5: {:.4f} rank10: {:.4f} (Best: {:.4f} @epoch {})'
.format(map_rerank, r_rerank[0], r_rerank[2], r_rerank[4],
r_rerank[9], best[0][0],
(best[1][0] + 1) * self.args.test_every))
if not self.args.test_only:
self.ckpt.save(self,
epoch,
is_best=((best[1][0] + 1) *
self.args.test_every == epoch))
