def _compute_whitening(whitening, net, image_size, transform, ms, msp):
# compute whitening
start = time.time()
print('>> {}: Learning whitening...'.format(whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train', whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root) for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(whitening))
wvecs = extract_vectors(net, images, image_size, transform, ms=ms, msp=msp)
# learning whitening
print('>> {}: Learning...'.format(whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
elapsed = time.time() - start
print('>> {}: elapsed time: {}'.format(whitening, htime(elapsed)))
return Lw, elapsed
def main(unused_argv):
tf.logging.set_verbosity(tf.logging.INFO)
start = time.time()
# Read features.
locations_1, _, descriptors_1, _, _ = feature_io.ReadFromFile(
cmd_args.features_1_path)
num_features_1 = locations_1.shape[0]
tf.logging.info("Loaded image 1's %d features" % num_features_1)
locations_2, _, descriptors_2, _, _ = feature_io.ReadFromFile(
cmd_args.features_2_path)
num_features_2 = locations_2.shape[0]
tf.logging.info("Loaded image 2's %d features" % num_features_2)
# Find nearest-neighbor matches using a KD tree.
d1_tree = spatial.cKDTree(descriptors_1)
_, indices = d1_tree.query(
descriptors_2, distance_upper_bound=_DISTANCE_THRESHOLD)
print('>> feature match elapsed time: {}'.format(htime(time.time() - start)))
# Select feature locations for putative matches.
locations_2_to_use = np.array([
locations_2[i,]
for i in range(num_features_2)
if indices[i] != num_features_1
])
locations_1_to_use = np.array([
locations_1[indices[i],]
for i in range(num_features_2)
if indices[i] != num_features_1
])
# Perform geometric verification using RANSAC.
_, inliers = measure.ransac((locations_1_to_use, locations_2_to_use),
transform.AffineTransform,
min_samples=3,
residual_threshold=20,
max_trials=1000)
tf.logging.info('Found %d inliers' % sum(inliers))
# Visualize correspondences, and save to file.
_, ax = plt.subplots()
img_1 = mpimg.imread(cmd_args.image_1_path)
img_2 = mpimg.imread(cmd_args.image_2_path)
inlier_idxs = np.nonzero(inliers)[0]
feature.plot_matches(
ax,
img_1,
img_2,
locations_1_to_use,
locations_2_to_use,
np.column_stack((inlier_idxs, inlier_idxs)),
matches_color='b')
ax.axis('off')
ax.set_title('DELF correspondences')
plt.savefig(cmd_args.output_image)
def test(datasets, net):
print(">> Evaluating network on test datasets...")
image_size = 1024
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta["mean"],
std=net.meta["std"])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
# Lw = None
Lw = net.meta["Lw"]["retrieval-SfM-120k"]["ss"]
# evaluate on test datasets
# datasets = args.test_datasets.split(",")
for dataset in datasets:
start = time.time()
print(">> {}: Extracting...".format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), "test"))
images = [cfg["im_fname"](cfg, i) for i in range(cfg["n"])]
qimages = [cfg["qim_fname"](cfg, i) for i in range(cfg["nq"])]
bbxs = [tuple(cfg["gnd"][i]["bbx"]) for i in range(cfg["nq"])]
# extract database and query vectors
print(">> {}: database images...".format(dataset))
vecs = extract_vectors(net, images, image_size, transform)
print(">> {}: query images...".format(dataset))
qvecs = extract_vectors(net, qimages, image_size, transform, bbxs)
print(">> {}: Evaluating...".format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset, ranks, cfg["gnd"])
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw["m"], Lw["P"])
qvecs_lw = whitenapply(qvecs, Lw["m"], Lw["P"])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset + " + whiten", ranks, cfg["gnd"])
print(">> {}: elapsed time: {}".format(dataset,
htime(time.time() - start)))
def validate(val_loader, model, criterion, epoch):
batch_time = AverageMeter()
losses = AverageMeter()
# create tuples for validation
t_start = time.time()
avg_neg_distance = val_loader.dataset.create_epoch_tuples(model)
print("Mining time: {}".format(htime(time.time() - t_start)))
# switch to evaluate mode
model.eval()
end = time.time()
for i, (input, target) in enumerate(val_loader):
nq = len(input) # number of training tuples
ni = len(input[0]) # number of images per tuple
output = torch.zeros(model.meta['outputdim'], nq * ni).cuda()
for q in range(nq):
for imi in range(ni):
# compute output vector for image imi of query q
output[:, q * ni + imi] = model(input[q][imi].cuda()).squeeze()
# no need to reduce memory consumption (no backward pass):
# compute loss for the full batch
loss = criterion(output, torch.cat(target).cuda())
# record loss
losses.update(loss.item() / nq, nq)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if (i + 1) % args.print_freq == 0 or i == 0 or (i +
1) == len(val_loader):
print('>> Val: [{0}][{1}/{2}]\t'
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
'Loss {loss.val:.4f} ({loss.avg:.4f})'.format(
epoch + 1,
i + 1,
len(val_loader),
batch_time=batch_time,
loss=losses))
return losses.avg
def train(train_loader, model, criterion, optimizer, epoch):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
# create tuples for training
t_start = time.time()
avg_neg_distance = train_loader.dataset.create_epoch_tuples(model)
print("Mining time: {}".format(htime(time.time() - t_start)))
# switch to train mode
model.train()
model.apply(set_batchnorm_eval)
end = time.time()
for i, (input, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
# zero out gradients so we can accumulate new ones over batches
optimizer.zero_grad()
nq = len(input) # number of training tuples
ni = len(input[0]) # number of images per tuple
for q in range(nq):
output = torch.zeros(model.meta['outputdim'], ni).cuda()
for imi in range(ni):
# compute output vector for image imi
output[:, imi] = model(input[q][imi].cuda()).squeeze()
# reducing memory consumption:
# compute loss for this query tuple only
# then, do backward pass for one tuple only
# each backward pass gradients will be accumulated
# the optimization step is performed for the full batch later
loss = criterion(output, target[q].cuda())
losses.update(loss.item())
loss.backward()
# do one step for multiple batches
# accumulated gradients are used
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if (i + 1) % args.print_freq == 0 or i == 0 or (
i + 1) == len(train_loader):
print('>> Train: [{0}][{1}/{2}]\t'
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
'Loss {loss.val:.4f} ({loss.avg:.4f})'.format(
epoch + 1,
i + 1,
len(train_loader),
batch_time=batch_time,
data_time=data_time,
loss=losses),
flush=True)
return losses.avg
def main():
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
using_cdvs = float(args.using_cdvs)
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path], model_dir=os.path.join(get_data_root(), 'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get('local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta['regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(
mean=net.meta['mean'],
std=net.meta['std']
)
transform = transforms.Compose([
transforms.ToTensor(),
normalize
])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(args.whitening))
if len(ms) > 1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [cid2filename(db['cids'][i], ims_root) for i in range(len(db['cids']))]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening, htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
result_dir=args.network_path[0:-8]
epoch_lun=args.network_path[0:-8].split('/')[-1].replace('model_epoch','')
print(">> Creating directory if it does not exist:\n>> '{}'".format(result_dir))
if not os.path.exists(result_dir):
os.makedirs(result_dir)
for dataset in datasets:
start = time.time()
# search, rank, and print
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
tuple_bbxs_qimlist=None
tuple_bbxs_imlist=None
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
# extract database and query vectors
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net, qimages, args.image_size, transform, bbxs=tuple_bbxs_qimlist, ms=ms, msp=msp, batchsize=1)
qvecs = qvecs.numpy()
qvecs = qvecs.astype(np.float32)
np.save(os.path.join(result_dir, "{}_qvecs_ep{}_resize.npy".format(dataset,epoch_lun)), qvecs)
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms, bbxs=tuple_bbxs_imlist, msp=msp, batchsize=1)
vecs = vecs.numpy()
vecs = vecs.astype(np.float32)
np.save(os.path.join(result_dir, "{}_vecs_ep{}_resize.npy".format(dataset,epoch_lun)), vecs)
scores = np.dot(vecs.T, qvecs)
if using_cdvs!=0:
print('>> {}: cdvs global descriptor loading...'.format(dataset))
qvecs_global = cfg['qimlist_global']
vecs_global = cfg['imlist_global']
scores_global = np.dot(vecs_global, qvecs_global.T)
scores+=scores_global*using_cdvs
ranks = np.argsort(-scores, axis=0)
if args.ir_remove!='0':
rank_len=10
rank_re = np.loadtxt(os.path.join(result_dir, '{}_ranks_new_relevent.txt'.format(dataset)))
## the max value of rank_len
MAX_RANK_LEN = int((rank_re.shape[0]) ** 0.5)
rank_re=rank_re.reshape(MAX_RANK_LEN,MAX_RANK_LEN,rank_re.shape[1])
for m in range(rank_re.shape[2]):
for i in range(rank_re.shape[0]):
rank_re[i][i][m]=1.0
quanzhong=[1,0.7,0.4]+[0.1]*(MAX_RANK_LEN-3)
for m in range(rank_re.shape[2]):
#if adaption, then change the rank_len to a adaption params according to the rank_re_q, q_aer, cons_n
if args.ir_adaption:
using_local_query=True
cons_n = 5
q_aer = float(args.ir_adaption)
if using_local_query:
## using local feature scores, please don't forget note the query_q belong to deep
rank_re_q = np.loadtxt(os.path.join(result_dir, '{}_ranks_new_query.txt'.format(dataset)))
query_q = rank_re_q[:, m]
else:
## using deep feature scores
query_q = scores[ranks[:, m], m]
rank_len=0
jishu=0
for idx in range(min(len(query_q),MAX_RANK_LEN)-cons_n):
if jishu<cons_n:
if query_q[idx]>q_aer:
rank_len=idx+1
else:
jishu+=1
else:
break
max_dim = min(rank_len, MAX_RANK_LEN)
print (max_dim)
if max_dim>2:
#put the image to the MAX_RANK_LEN2 location if equals max_dim then re rank in the maxdim length
list2 = []
list_hou = []
MAX_RANK_LEN2 = max_dim
for i in range(MAX_RANK_LEN2):
if i < max_dim:
fenshu = 0
for j in range(max_dim):
fenshu+=rank_re[min(i,j)][max(i,j)][m]*quanzhong[j]
fenshu = fenshu / (max_dim - 1)
if fenshu > float(args.ir_remove):
list2.append(ranks[i][m])
else:
list_hou.append(ranks[i][m])
else:
list2.append(ranks[i][m])
ranks[0:MAX_RANK_LEN2, m] = list2 + list_hou
np.savetxt(os.path.join(result_dir, "{}_ranks.txt".format(dataset)), ranks.astype(np.int))
if dataset == 'cdvs_test_retrieval':
compute_map_and_print(dataset, ranks, cfg['gnd_id'])
else:
compute_map_and_print(dataset, ranks, cfg['gnd'])
# extract whitening vectors
print('>> {}: Extracting...'.format(whitening))
# wvecs = vecs
wvecs = np.hstack((vecs, qvecs))
# learning whitening
print('>> {}: Learning...'.format(whitening))
m, P = pcawhitenlearn(wvecs)
# m, P = whitenlearn(wvecs)
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
whitening, whiten_fn))
# torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(whitening,
htime(time.time() - start)))
else:
Lw = None
if Lw is not None:
for dim in param['pac_dims']:
print('>>>> pac_dim: {}'.format(dim))
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'], dim)
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'], dim)
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks_lw = np.argsort(-scores, axis=0)
qvecs_lw_orig = qvecs_lw
ranks_lw_orig = ranks_lw
def main():
args = parser.parse_args()
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError(
'Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
#download_train(get_data_root())
download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get(
'local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if len(ms) > 1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(
args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train',
args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
"""
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg,i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg,i) for i in range(cfg['nq'])]
try:
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
except:
bbxs = None # for holidaysmanrot and copydays
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net, qimages, args.image_size, transform, bbxs=bbxs, ms=ms, msp=msp)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
print (vecs.shape)
print (qvecs.shape)
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
print (scores.shape)
# to save scores (single query)
# oxford
#f = 'oxf_single.npy'
# paris
#f = 'par_single.npy'
# roxford
#f = 'roxf_single.npy'
# rparis
f = 'rpar_single.npy'
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset, ranks, cfg['gnd'])
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
# save
np.save(f, scores)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset + ' + whiten', ranks, cfg['gnd'])
"""
############################################################
# Test
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
print(qimages)
# to load scores
# oxford
#f = 'oxf_single.npy'
#f = 'oxf_mq_avg.npy'
#f = 'oxf_mq_max.npy'
#f = 'oxf_sc_imf.npy'
# paris
#f = 'par_single.npy'
#f = 'par_mq_avg.npy'
#f = 'par_mq_max.npy'
f = 'par_sc_imf.npy'
# roxford
#f = 'roxf_single.npy'
#f = 'roxf_mq_avg.npy'
#f = 'roxf_mq_max.npy'
#f = 'roxf_sc_imf.npy'
# rparis
#f = 'rpar_single.npy'
#f = 'rpar_mq_avg.npy'
#f = 'rpar_mq_max.npy'
#f = 'rpar_sc_imf.npy'
# load
scores = np.load(f)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset + ' + whiten', ranks, cfg['gnd'])
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def main():
args = parser.parse_args()
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get(
'local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
if "epoch" in state:
print("Model after {} epochs".format(state["epoch"]))
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters: test both single scale and multiscale
ms_singlescale = [1]
msp_singlescale = 1
ms_multiscale = list(eval(args.multiscale))
msp_multiscale = 1
if len(ms_multiscale
) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp_multiscale = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms_multiscale))
print(">>>> msp: {}".format(msp_multiscale))
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
Lw = net.meta['Lw'][args.whitening]
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(
args.whitening)
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
Lw = torch.load(whiten_fn)
else:
Lw = {}
for whiten_type, ms, msp in zip(
["ss", "ms"], [ms_singlescale, ms_multiscale],
[msp_singlescale, msp_multiscale]):
print('>> {0}: Learning whitening {1}...'.format(
args.whitening, whiten_type))
# loading db
db_root = os.path.join(get_data_root(), 'train',
args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(
db_root, '{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw[whiten_type] = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(
args.whitening, htime(time.time() - start)))
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
for whiten_type, ms, msp in zip(["ss", "ms"],
[ms_singlescale, ms_multiscale],
[msp_singlescale, msp_multiscale]):
print('>> Extracting feature on {0}, whitening {1}'.format(
dataset, whiten_type))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
bbxs=bbxs,
ms=ms,
msp=msp)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset, ranks, cfg['gnd'])
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw[whiten_type]['m'],
Lw[whiten_type]['P'])
qvecs_lw = whitenapply(qvecs, Lw[whiten_type]['m'],
Lw[whiten_type]['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(
dataset + ' + whiten {}'.format(whiten_type), ranks,
cfg['gnd'])
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def main():
args = parser.parse_args()
# check if test dataset are downloaded
# and download if they are not
#download_train(get_data_root())
#download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
state = torch.load(args.network_path)
net = init_network(model=state['meta']['architecture'],
pooling=state['meta']['pooling'],
whitening=state['meta']['whitening'],
mean=state['meta']['mean'],
std=state['meta']['std'],
pretrained=False)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
offtheshelf = args.network_offtheshelf.split('-')
if len(offtheshelf) == 3:
if offtheshelf[2] == 'whiten':
offtheshelf_whiten = True
else:
raise (RuntimeError(
"Incorrect format of the off-the-shelf network. Examples: resnet101-gem | resnet101-gem-whiten"
))
else:
offtheshelf_whiten = False
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(model=offtheshelf[0],
pooling=offtheshelf[1],
whitening=offtheshelf_whiten)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = [1]
msp = 1
if args.multiscale:
ms = [1, 1. / math.sqrt(2), 1. / 2]
if net.meta['pooling'] == 'gem' and net.whiten is None:
msp = net.pool.p.data.tolist()[0]
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if args.multiscale:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
bbxs=bbxs,
ms=ms,
msp=msp)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset, ranks, cfg['gnd'])
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset + ' + whiten', ranks, cfg['gnd'])
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def test(datasets, net, noise, image_size):
global base
print(">> Evaluating network on test datasets...")
net.cuda()
net.eval()
normalize = transforms.Normalize(mean=net.meta["mean"],
std=net.meta["std"])
def add_noise(img):
n = noise
n = F.interpolate(n.unsqueeze(0),
mode=MODE,
size=tuple(img.shape[-2:]),
align_corners=True).squeeze()
return torch.clamp(img + n, 0, 1)
transform_base = transforms.Compose([transforms.ToTensor(), normalize])
transform_query = transforms.Compose(
[transforms.ToTensor(),
transforms.Lambda(add_noise), normalize])
if "Lw" in net.meta:
Lw = net.meta["Lw"]["retrieval-SfM-120k"]["ss"]
else:
Lw = None
# evaluate on test datasets
datasets = args.test_datasets.split(",")
attack_result = {}
for dataset in datasets:
start = time.time()
print(">> {}: Extracting...".format(dataset))
cfg = configdataset(dataset, os.path.join(get_data_root(), "test"))
images = [cfg["im_fname"](cfg, i) for i in range(cfg["n"])]
qimages = [cfg["qim_fname"](cfg, i) for i in range(cfg["nq"])]
bbxs = [tuple(cfg["gnd"][i]["bbx"]) for i in range(cfg["nq"])]
# extract database and query vectors
print(">> {}: database images...".format(dataset))
with torch.no_grad():
if dataset in base and str(image_size) in base[dataset]:
vecs = base[dataset][str(image_size)]
else:
vecs = extract_vectors(net, images, image_size, transform_base)
if dataset not in base:
base[dataset] = {}
base[dataset][str(image_size)] = vecs
fname = args.network_path.replace("/", "_") + ".pkl"
with open(f"base/{fname}", "wb") as f:
pickle.dump(base, f)
print(">> {}: query images...".format(dataset))
qvecs = extract_vectors(net, qimages, image_size, transform_query,
bbxs)
print(">> {}: Evaluating...".format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw["m"], Lw["P"])
qvecs_lw = whitenapply(qvecs, Lw["m"], Lw["P"])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
r = compute_map_and_print(dataset + " + whiten", ranks, cfg["gnd"])
attack_result[dataset] = r
print(">> {}: elapsed time: {}".format(dataset,
htime(time.time() - start)))
return inv_gfr(
attack_result,
baseline_result[net.meta["architecture"]][net.meta["pooling"]])
def main():
args = parser.parse_args()
# check if test dataset are downloaded
# and download if they are not
download_train(get_data_root())
download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
net = load_network(args.network_path)
# loading offtheshelf network
elif args.network_offtheshelf is not None:
net = load_offtheshelf(args.network_offtheshelf)
# setting up the multi-scale parameters
ms = [1]
msp = 1
if args.multiscale:
ms = [1, 1./math.sqrt(2), 1./2]
if net.meta['pooling'] == 'gem' and net.whiten is None:
msp = net.pool.p.data.tolist()[0]
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(
mean=net.meta['mean'],
std=net.meta['std']
)
transform = transforms.Compose([
transforms.ToTensor(),
normalize
])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(args.whitening))
if args.multiscale:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
print('>> {}: Learning whitening...'.format(args.whitening))
if args.whitening == "scores":
# special logic for scores database
from score_retrieval.exports import (
db,
train_images as images,
)
else:
# loading db
db_root = os.path.join(get_data_root(), 'train', args.test_whiten)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(args.test_whiten))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [cid2filename(db['cids'][i], ims_root) for i in range(len(db['cids']))]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(args.whitening, htime(time.time()-start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
if dataset == "scores":
# Special added logic to handle loading our score dataset
from score_retrieval.exports import (
images,
qimages,
gnd,
)
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net, qimages, args.image_size, transform, ms=ms, msp=msp)
else:
# extract ground truth
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
gnd = cfg['gnd']
# prepare config structure for the test dataset
images = [cfg['im_fname'](cfg,i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg,i) for i in range(cfg['nq'])]
bbxs = [tuple(gnd[i]['bbx']) for i in range(cfg['nq'])]
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net, qimages, args.image_size, transform, bbxs=bbxs, ms=ms, msp=msp)
# validation
print(">> {}: gnd stats: {}, {}, {}".format(
dataset,
len(gnd),
[len(x["ok"]) for x in gnd[10:]],
[len(x["junk"]) for x in gnd[10:]],
))
print(">> {}: image stats: {}, {}".format(dataset, len(images), len(qimages)))
assert len(gnd) == len(qimages), (len(gnd), len(qimages))
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
print(">> {}: qvecs.shape: {}".format(dataset, qvecs.shape))
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
print(">> {}: ranks (shape {}) head: {}".format(dataset, ranks.shape, ranks[10:,10:]))
print(">> {}: gnd head: {}".format(dataset, gnd[5:]))
# Compute and print metrics
compute_acc(ranks, gnd, dataset)
compute_mrr(ranks, gnd, dataset)
compute_map_and_print(dataset, ranks, gnd)
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
compute_acc(ranks, gnd, dataset + " + whiten")
compute_mrr(ranks, gnd, dataset + " + whiten")
compute_map_and_print(dataset + " + whiten", ranks, gnd)
print('>> {}: elapsed time: {}'.format(dataset, htime(time.time()-start)))
def main():
args = parser.parse_args()
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
result_dir = 'retreival_results'
if args.network_path is not None:
result_dir = os.path.join(result_dir, args.network_path)
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
state = torch.load(args.network_path)
net = init_network(model=state['meta']['architecture'],
pooling=state['meta']['pooling'],
whitening=state['meta']['whitening'],
mean=state['meta']['mean'],
std=state['meta']['std'],
pretrained=False)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
result_dir = os.path.join(result_dir, args.network_offtheshelf)
offtheshelf = args.network_offtheshelf.split('-')
if len(offtheshelf) == 3:
if offtheshelf[2] == 'whiten':
offtheshelf_whiten = True
else:
raise (RuntimeError(
"Incorrect format of the off-the-shelf network. Examples: resnet101-gem | resnet101-gem-whiten"
))
else:
offtheshelf_whiten = False
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(model=offtheshelf[0],
pooling=offtheshelf[1],
whitening=offtheshelf_whiten)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = [1]
msp = 1
if args.multiscale:
ms = [1, 1. / math.sqrt(2), 1. / 2]
if net.meta['pooling'] == 'gem' and net.whiten is None:
msp = net.pool.p.data.tolist()[0]
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if args.multiscale:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# Save whitening TODO
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
data_root = args.data_root
datasets = datasets_names[args.dataset]
result_dict = {}
for dataset in datasets:
start = time.time()
result_dict[dataset] = {}
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
images = get_imlist(data_root, dataset, args.train_txt)
qimages = get_imlist(data_root, dataset, args.query_txt)
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net,
images,
args.image_size,
transform,
root=os.path.join(data_root, dataset),
ms=ms,
msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
root=os.path.join(data_root, dataset),
ms=ms,
msp=msp)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
scores, ranks = cal_ranks(vecs, vecs, Lw)
result_dict[dataset]['train'] = {'scores': scores, 'ranks': ranks}
scores, ranks = cal_ranks(vecs, qvecs, Lw)
result_dict[dataset]['test'] = {'scores': scores, 'ranks': ranks}
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
# Save retrieval results
if not os.path.exists(result_dir):
os.makedirs(result_dir)
result_file = os.path.join(result_dir, args.outfile)
np.save(result_file, result_dict)
print('Save retrieval results to {}'.format(result_file))
def main():
args = parser.parse_args()
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError('Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
# download_train(get_data_root())
# download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path], model_dir=os.path.join(get_data_root(), 'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get('local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
net_params['multi_layer_cat'] = state['meta']['multi_layer_cat']
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
print(">> image size: {}".format(args.image_size))
ms = list(eval(args.multiscale))
if len(ms)>1 and net.meta['pooling'] == 'gem' and not net.meta['regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(
mean=net.meta['mean'],
std=net.meta['std']
)
transform = transforms.Compose([
transforms.ToTensor(),
normalize
])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(args.whitening))
if len(ms)>1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [cid2filename(db['cids'][i], ims_root) for i in range(len(db['cids']))]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening, htime(time.time()-start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg,i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg,i) for i in range(cfg['nq'])]
# bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
print('>> not use bbxs...')
bbxs = None
# key_url_list = ParseData(os.path.join(get_data_root(), 'index.csv'))
# index_image_path = os.path.join(get_data_root(), 'resize_index_image')
# images = [os.path.join(index_image_path, key_url_list[i][0]) for i in range(len(key_url_list))]
# key_url_list = ParseData(os.path.join(get_data_root(), 'test.csv'))
# test_image_path = os.path.join(get_data_root(), 'resize_test_image')
# qimages = [os.path.join(test_image_path, key_url_list[i][0]) for i in range(len(key_url_list))]
# # bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
# csvfile = open(os.path.join(get_data_root(), 'index_clear.csv'), 'r')
# csvreader = csv.reader(csvfile)
# images = [line[:1][0] for line in csvreader]
#
# csvfile = open(os.path.join(get_data_root(), 'test_clear.csv'), 'r')
# csvreader = csv.reader(csvfile)
# qimages = [line[:1][0] for line in csvreader]
# bbxs = None
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms, msp=msp)
# vecs = torch.randn(2048, 5063)
# vecs = torch.randn(2048, 4993)
# hxq modified
# bbxs = None
# print('>> set no bbxs...')
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net, qimages, args.image_size, transform, bbxs=bbxs, ms=ms, msp=msp)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
# hxq modified, test add features map for retrieval
# vecs = [vecs[i].numpy() for i in range(len(vecs))]
# qvecs_temp = np.zeros((qvecs[0].shape[0], len(qvecs)))
# for i in range(len(qvecs)):
# qvecs_temp[:, i] = qvecs[i][:, 0].numpy()
# qvecs = qvecs_temp
#
# scores = np.zeros((len(vecs), qvecs.shape[-1]))
# for i in range(len(vecs)):
# scores[i, :] = np.amax(np.dot(vecs[i].T, qvecs), 0)
ranks = np.argsort(-scores, axis=0)
mismatched_info = compute_map_and_print(dataset, ranks, cfg['gnd'], kappas=[1, 5, 10, 100])
# hxq added
show_false_img = False
if show_false_img == True:
print('>> Save mismatched image tuple...')
for info in mismatched_info:
mismatched_img_show_save(info, qimages, images, args, bbxs=bbxs)
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
mismatched_info = compute_map_and_print(dataset + ' + whiten', ranks, cfg['gnd'])
# hxq added
# show_false_img = False
if show_false_img == True:
print('>> Save mismatched image tuple...')
for info in mismatched_info:
mismatched_img_show_save(info, qimages, images, args, bbxs=bbxs)
print('>> {}: elapsed time: {}'.format(dataset, htime(time.time()-start)))
def main():
#def process(network_path, datasets='oxford5k,paris6k', whitening=None, image_size=1024, multiscale = '[1]', query=None):
args = parser.parse_args()
#args.query = None
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError(
'Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
#download_train(get_data_root())
#download_test(get_data_root())
# setting up the visible GPU
#os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get(
'local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
# moving network to gpu and eval mode
#net.cuda()
#net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if len(ms) > 1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(
args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
print(whiten_fn)
return
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train',
args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
# query type
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
#for i in cfg: print(i)
#print(cfg['gnd'][0]['bbx'])
#return
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
feas_dir = os.path.join(cfg['dir_data'], 'features')
if not os.path.isdir(feas_dir):
os.mkdir(feas_dir)
feas_sv = os.path.join(
feas_dir, dataset + '_' + args.network_path + '_features.pkl')
if not os.path.isfile(feas_sv):
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
vecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
with open(feas_sv, 'wb') as f:
pickle.dump(vecs, f)
else:
with open(feas_sv, 'rb') as f:
vecs = pickle.load(f)
print('>> {}: query images...'.format(dataset))
if args.query is not None:
qimages = [args.query]
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
ms=ms,
msp=msp)
else:
qfeas_dir = feas_dir
qfeas_sv = os.path.join(
qfeas_dir,
dataset + '_' + args.network_path + '_qfeatures.pkl')
if not os.path.isfile(qfeas_sv):
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
try:
bbxs = [
tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])
]
except:
bbxs = None
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
bbxs=bbxs,
ms=ms,
msp=msp)
with open(qfeas_sv, 'wb') as f:
pickle.dump(qvecs, f)
else:
with open(qfeas_sv, 'rb') as f:
qvecs = pickle.load(f)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
#qvecs = qvecs[:, 0].reshape(-1, 1)
#args.query = True
# search, rank, and print
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranksw = np.argsort(-scores, axis=0)
if args.query is None:
#compute_map_and_print(dataset + ' + whiten', ranksw, cfg['gnd'])
compute_map_and_print1(dataset + ' + whiten', ranksw,
cfg['gnd'])
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
# compute_map_and_print(dataset, ranks, cfg['gnd'])
compute_map_and_print1(dataset, ranks, cfg['gnd'])
else:
a = []
for i in ranksw:
a.append(
os.path.join(cfg['dir_images'], cfg['imlist'][i[0]]) +
cfg['ext'])
print(a[:10])
result = cfg['dir_data'] + '_result'
with open(result + '.pkl', 'wb') as f:
pickle.dump(a[:10], f)
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def main():
args = parser.parse_args()
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError(
'Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
#download_train(get_data_root())
#download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get(
'local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if len(ms) > 1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(
args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train',
args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
#cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = []
gallery_file = open(
'/home/zzd/University1652-Baseline/gallery_name.txt')
for line in gallery_file:
images.append('/home/zzd/University1652-Baseline/' +
line.replace('\n', '')[2:])
#qimages = [cfg['qim_fname'](cfg,i) for i in range(cfg['nq'])]
qimages = []
query_file = open('/home/zzd/University1652-Baseline/query_name.txt')
for line in query_file:
qimages.append('/home/zzd/University1652-Baseline/' +
line.replace('\n', '')[2:])
gallery_label = get_id(images)
query_label = get_id(qimages)
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
gallery_feature = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
gallery_feature = torch.transpose(gallery_feature, 0, 1)
print('>> {}: query images...'.format(dataset))
query_feature = extract_vectors(net,
qimages,
args.image_size,
transform,
ms=ms,
msp=msp)
query_feature = torch.transpose(query_feature, 0, 1)
result = {
'gallery_f': gallery_feature.numpy(),
'gallery_label': gallery_label,
'query_f': query_feature.numpy(),
'query_label': query_label
}
scipy.io.savemat('pytorch_result.mat', result)
os.system('python evaluate_gpu.py')
print('>> {}: Evaluating...'.format(dataset))
def main():
args = parser.parse_args()
# check if test dataset are downloaded
# and download if they are not
download_train(get_data_root())
download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
state = torch.load(args.network_path)
net = init_network(model=state['meta']['architecture'],
pooling=state['meta']['pooling'],
whitening=state['meta']['whitening'],
mean=state['meta']['mean'],
std=state['meta']['std'],
pretrained=False)
net.load_state_dict(state['state_dict'])
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
offtheshelf = args.network_offtheshelf.split('-')
if len(offtheshelf) == 3:
if offtheshelf[2] == 'whiten':
offtheshelf_whiten = True
else:
raise (RuntimeError(
"Incorrect format of the off-the-shelf network. Examples: resnet101-gem | resnet101-gem-whiten"
))
else:
offtheshelf_whiten = False
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(model=offtheshelf[0],
pooling=offtheshelf[1],
whitening=offtheshelf_whiten)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = [1]
msp = 1
if args.multiscale:
ms = [1, 1. / math.sqrt(2), 1. / 2]
if net.meta['pooling'] == 'gem' and net.whiten is None:
msp = net.pool.p.data.tolist()[0]
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
if dataset == 'reco':
images, qimages = landmark_recognition_dataset()
bbxs = [None for x in qimages]
elif dataset == 'retr':
images, _ = landmark_retrieval_dataset()
qimages = []
bbxs = [None for x in qimages]
else:
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
with open('%s_fnames.pkl' % dataset, 'wb') as f:
pickle.dump([images, qimages], f)
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
vecs = vecs.numpy()
print('>> saving')
np.save('{}_vecs.npy'.format(dataset), vecs)
if len(qimages) > 0:
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
bbxs=bbxs,
ms=ms,
msp=msp)
qvecs = qvecs.numpy()
np.save('{}_qvecs.npy'.format(dataset), qvecs)
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# TODO
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def test(args, config, model, rank=None, world_size=None, **varargs):
log_debug('Evaluating network on test datasets...')
# Eval mode
model.eval()
data_config = config["dataloader"]
local_config = config["local"]
# Average score
avg_score = 0.0
# Evaluate on test datasets
list_datasets = data_config.getstruct("test_datasets")
for dataset in list_datasets:
start = time.time()
Avg_F_score = 0.
log_debug('{%s}: Loading Dataset', dataset)
for split in {"v", "i"}:
test_tf = ISSTestTransform(
rgb_mean=data_config.getstruct("rgb_mean"),
rgb_std=data_config.getstruct("rgb_std"),
shortest_size=data_config.getint("test_shortest_size"),
longest_max_size=data_config.getint("test_longest_max_size"),
num_kpt=2000,
kpt_type='superpoint')
test_db = HPacthes(root_dir=args.data,
name=dataset,
split=split,
transform=test_tf)
test_sampler = DistributedARBatchSampler(
data_source=test_db,
batch_size=data_config.getint("test_batch_size"),
num_replicas=world_size,
rank=rank,
drop_last=True,
shuffle=False)
test_dl = torch.utils.data.DataLoader(test_db,
batch_sampler=test_sampler,
collate_fn=iss_collate_fn,
pin_memory=True,
num_workers=0,
shuffle=False)
log_debug('{%s}: Feature Extraction %s...', dataset, split)
for it, batch in tqdm(enumerate(test_dl), total=len(test_dl)):
with torch.no_grad():
# Upload batch
img1_path, img2_path = batch["img1_path"][0], batch[
"img2_path"][0]
scores1 = batch["scores1"][0]
scores2 = batch["scores2"][0]
batch = {
k: batch[k].cuda(device=varargs["device"],
non_blocking=True)
for k in HP_INPUTS
}
# Run Image 1
_, pred1 = model(img=batch["img1"],
kpts=batch["kpts1"],
do_prediction=True,
do_augmentaton=False)
distributed.barrier()
kpts1, _ = batch["kpts1"].contiguous
pred1, _ = pred1["local_pred"].contiguous
kpts1 = kpts1.squeeze(0)
pred1 = pred1.squeeze(0)
with open(img1_path + ".npz", 'wb') as output_file:
np.savez(output_file,
keypoints=kpts1.cpu().numpy(),
descriptors=pred1.cpu().numpy(),
scores=scores1)
# Run Image 2
_, pred2 = model(img=batch["img2"],
kpts=batch["kpts2"],
do_prediction=True,
do_augmentaton=False)
distributed.barrier()
kpts2, _ = batch["kpts2"].contiguous
pred2, _ = pred2["local_pred"].contiguous
kpts2 = kpts2.squeeze(0)
pred2 = pred2.squeeze(0)
with open(img2_path + ".npz", 'wb') as output_file:
np.savez(output_file,
keypoints=kpts2.cpu().numpy(),
descriptors=pred2.cpu().numpy(),
scores=scores2)
log_debug('{%s}: Run Evalution %s...', dataset, split)
# run evaluation
config = {'correctness_threshold': 3, 'max_mma_threshold': 10}
H_estimation, Precision, Recall, MMA = run_descriptor_evaluation(
config, test_dl)
# compute F score
F_score = 2 * ((Precision * Recall) / (Precision + Recall + 1e-10))
Avg_F_score += 0.5 * F_score
np.set_printoptions(precision=3)
log_info('{%s}: H_estimation_%s = %s', dataset, split,
format(H_estimation, '.3f'))
log_info('{%s}: Precision_%s = %s', dataset, split,
format(Precision, '.3f'))
log_info('{%s}: Recall_%s = %s', dataset, split,
format(Recall, '.3f'))
log_info('{%s}: MMA_%s = %s', dataset, split, MMA)
log_info('{%s}: F_score_%s = %s', dataset, split,
format(F_score, '.3f'))
log_info('{%s}: Running time = %s', dataset,
htime(time.time() - start))
log_info('{%s}: Avg_F_score = %s', dataset,
format(Avg_F_score, '.3f'))
return Avg_F_score
def main():
args = parser.parse_args()
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError(
'Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
download_train(get_data_root())
download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network
# pretrained networks (downloaded automatically)
print(">> Loading network:\n>>>> '{}'".format(args.network))
state = load_url(PRETRAINED[args.network],
model_dir=os.path.join(get_data_root(), 'networks'))
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get('local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# network initialization
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
print(">>>> Evaluating scales: {}".format(ms))
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
try:
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
except:
bbxs = None # for holidaysmanrot and copydays
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
args.image_size,
transform,
bbxs=bbxs,
ms=ms)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
top_k = 100
ranks_fnames_qs = []
for q_id in range(len(cfg["qimlist"])):
ranks_q = list(ranks[:top_k, q_id])
ranks_fname_per_q = []
for img_id in ranks_q:
ranks_fname_per_q.append(cfg["imlist"][img_id])
ranks_fnames_qs.append(ranks_fname_per_q)
compute_map_and_print(dataset, ranks, cfg['gnd'])
compute_map_and_print_top_k(dataset, ranks_fnames_qs, cfg['gnd'],
cfg["imlist"])
sys.exit()
with open(dataset + "_gl18_tl_resnet101_gem_w_m.pkl", "wb") as f:
data = {"ranks": ranks, "db_images": images, "q_images": qimages}
pickle.dump(data, f)
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def test(datasets, net):
print('>> Evaluating network on test datasets...')
# for testing we use image size of max 1024
image_size = 1024
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.test_whiten:
start = time.time()
print('>> {}: Learning whitening...'.format(args.test_whiten))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.test_whiten)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(args.test_whiten))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.test_whiten))
wvecs = extract_vectors(net,
images,
image_size,
transform,
print_freq=10,
batchsize=20) # implemented with torch.no_grad
# learning whitening
print('>> {}: Learning...'.format(args.test_whiten))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(args.test_whiten,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.test_datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
if dataset == 'cdvs_test_retrieval':
bbxs = None
else:
bbxs = None
print('>> {}: database images...'.format(dataset))
if args.pool == 'gem':
ms = [1, 1 / 2**(1 / 2), 1 / 2]
else:
ms = [1]
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
vecs = extract_vectors(net,
images,
image_size,
transform,
bbxs,
ms=ms,
msp=msp,
print_freq=1000,
batchsize=1) # implemented with torch.no_grad
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
image_size,
transform,
bbxs,
ms=ms,
msp=msp,
print_freq=1000,
batchsize=1) # implemented with torch.no_grad
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
if dataset == 'cdvs_test_retrieval':
compute_map_and_print(dataset, ranks, cfg['gnd_id'])
else:
compute_map_and_print(dataset, ranks, cfg['gnd'])
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset + ' + whiten', ranks, cfg['gnd'])
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def test(args, config, model, rank=None, world_size=None, **varargs):
log_debug('Evaluating network on test datasets...')
# Eval mode
model.eval()
data_config = config["dataloader"]
# Average score
avg_score = 0.0
# Evaluate on test datasets
list_datasets = data_config.getstruct("test_datasets")
if data_config.get("multi_scale"):
scales = eval(data_config.get("multi_scale"))
else:
scales = [1]
for dataset in list_datasets:
start = time.time()
log_debug('{%s}: Loading Dataset', dataset)
# Prepare database
db = ParisOxfordTestDataset(root_dir=path.join(args.data, 'test',
dataset),
name=dataset)
batch_size = data_config.getint("test_batch_size")
with torch.no_grad():
""" Paris and Oxford are :
1 - resized to a ratio of desired max size, after bbx cropping
2 - normalized after that
3 - not flipped and not scaled (!! important for evaluation)
"""
# Prepare query loader
log_debug('{%s}: Extracting descriptors for query images', dataset)
query_tf = ISSTestTransform(
shortest_size=data_config.getint("test_shortest_size"),
longest_max_size=data_config.getint("test_longest_max_size"),
random_scale=data_config.getstruct("random_scale"))
query_data = ISSDataset(root_dir='',
name="query",
images=db['query_names'],
bbx=db['query_bbx'],
transform=query_tf)
query_sampler = DistributedARBatchSampler(
data_source=query_data,
batch_size=data_config.getint("test_batch_size"),
num_replicas=world_size,
rank=rank,
drop_last=True,
shuffle=False)
query_dl = torch.utils.data.DataLoader(
query_data,
batch_sampler=query_sampler,
collate_fn=iss_collate_fn,
pin_memory=True,
num_workers=data_config.getstruct("num_workers"),
shuffle=False)
# Extract query vectors
qvecs = torch.zeros(varargs["output_dim"], len(query_data)).cuda()
for it, batch in tqdm(enumerate(query_dl), total=len(query_dl)):
# Upload batch
batch = {
k: batch[k].cuda(device=varargs["device"],
non_blocking=True)
for k in INPUTS
}
_, pred = model(**batch,
scales=scales,
do_prediction=True,
do_augmentaton=False)
distributed.barrier()
qvecs[:,
it * batch_size:(it + 1) * batch_size] = pred["ret_pred"]
del pred
# Prepare negative database data loader
log_debug('{%s}: Extracting descriptors for database images',
dataset)
database_tf = ISSTestTransform(
shortest_size=data_config.getint("test_shortest_size"),
longest_max_size=data_config.getint("test_longest_max_size"),
random_scale=data_config.getstruct("random_scale"))
database_data = ISSDataset(root_dir='',
name="database",
images=db['img_names'],
transform=database_tf)
database_sampler = DistributedARBatchSampler(
data_source=database_data,
batch_size=data_config.getint("test_batch_size"),
num_replicas=world_size,
rank=rank,
drop_last=True,
shuffle=False)
database_dl = torch.utils.data.DataLoader(
database_data,
batch_sampler=database_sampler,
collate_fn=iss_collate_fn,
pin_memory=True,
num_workers=data_config.getstruct("num_workers"),
shuffle=False)
# Extract negative pool vectors
database_vecs = torch.zeros(varargs["output_dim"],
len(database_data)).cuda()
for it, batch in tqdm(enumerate(database_dl),
total=len(database_dl)):
# Upload batch
batch = {
k: batch[k].cuda(device=varargs["device"],
non_blocking=True)
for k in INPUTS
}
_, pred = model(**batch,
scales=scales,
do_prediction=True,
do_augmentaton=False)
distributed.barrier()
database_vecs[:, it * batch_size:(it + 1) *
batch_size] = pred["ret_pred"]
del pred
# Compute dot product scores and ranks on GPU
# scores = torch.mm(database_vecs.t(), qvecs)
# scores, scores_indices = torch.sort(-scores, dim=0, descending=False)
# convert to numpy
qvecs = qvecs.cpu().numpy()
database_vecs = database_vecs.cpu().numpy()
# search, rank, and print
scores = np.dot(database_vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
score = compute_map_and_print(dataset, ranks, db['gnd'], log_info)
log_info('{%s}: Running time = %s', dataset,
htime(time.time() - start))
avg_score += 0.5 * score["mAP"]
# As Evaluation metrics
log_info('Average score = %s', avg_score)
return avg_score
def main():
args = parser.parse_args()
# check if there are unknown datasets
# for dataset in args.datasets.split(','):
# if dataset not in datasets_names:
# raise ValueError('Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
# download_train(get_data_root())
# download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
#datasets = args.datasets.split(',')
for dataset in datasets_names:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join('/data', 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
global_feature_dict, gloabal_feature_size = build_global_feature_dict(
'/home/ubuntu/DELG/extract/roxf5k.delf.global', 'global_features')
# # extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_feature(global_feature_dict, images,
gloabal_feature_size)
print('>> {}: query images...'.format(dataset))
qvecs = extract_feature(global_feature_dict, qimages,
gloabal_feature_size)
print('>> {}: Evaluating...'.format(dataset))
# search, rank, and print
# using cosine similarity of two vectors
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset, ranks, cfg['gnd'])
feature_location, feature_descriptor = build_local_feature_dict(
'/home/ubuntu/DELG/extract/roxf5k.delf.local')
new_ranks = [] #np.empty_like(ranks)
# for i, qimage in enumerate(qimages):
# new_ranks[:, i] = RerankByGeometricVerification(i, ranks[:, i], scores[:, i], qimage,
# images, feature_location,
# feature_descriptor, [])
from functools import partial
re_rank_func = partial(RerankByGeometricVerification,
input_ranks=ranks,
initial_scores=scores,
query_name=qimages,
index_names=images,
feature_location=feature_location,
feature_descriptor=feature_descriptor,
junk_ids=[])
new_ranks = p_map(re_rank_func, range(len(qimages)))
new_ranks = np.concatenate(new_ranks, axis=0)
compute_map_and_print(dataset, new_ranks, cfg['gnd'])
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def main():
args = parser.parse_args()
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError(
'Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
download_train(get_data_root())
download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get(
'local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if len(ms) > 1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(
args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(args.whitening))
# loading db
db_root = os.path.join(get_data_root(), 'train',
args.whitening)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(args.whitening))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
images = get_imlist("E:\\PycharmProjects\\image-retrieval\\holiday2\\")
names = []
for i, img_path in enumerate(images):
img_name = os.path.split(img_path)[1]
print(img_name)
names.append(img_name)
# prepare config structure for the test dataset
# cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
# images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
# try:
# bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
# except:
# bbxs = None # for holidaysmanrot and copydays
# names = []
# for i, img_path in enumerate(images):
# img_name = os.path.split(img_path)[1]
# print(img_name)
# names.append(img_name)
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net,
images,
args.image_size,
transform,
ms=ms,
msp=msp)
# convert to numpy
vecs = vecs.numpy()
vecs = vecs.T
print("--------------------------------------------------")
print(" writing feature extraction results ...")
print("--------------------------------------------------")
output = "gem_res_holiday_3.h5"
h5f = h5py.File(output, 'w')
h5f.create_dataset('dataset_1', data=vecs)
h5f.create_dataset('dataset_2', data=np.string_(names))
h5f.close()
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
def main():
args = parser.parse_args()
# check if there are unknown datasets
for scene in args.scenes.split(','):
if scene not in datasets_names:
raise ValueError('Unsupported or unknown scene: {}!'.format(scene))
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network
# pretrained networks (downloaded automatically)
print(">> Loading network:\n>>>> '{}'".format(args.network))
state = load_url(PRETRAINED[args.network],
model_dir=os.path.join(get_data_root(), 'networks'))
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get('local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# network initialization
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
print(">>>> Evaluating scales: {}".format(ms))
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# evaluate on test datasets
scenes = args.scenes.split(',')
for scene in scenes:
start = time.time()
print('>> {}: Extracting...'.format(scene))
img_path = osp.join(args.data_path, scene, "images")
images = [
osp.join(img_path, fname) for fname in os.listdir(img_path)
if fname[-3:].lower() in ['jpg', 'png']
]
# extract vectors
vecs = extract_vectors(net, images, args.image_size, transform, ms=ms)
print('>> {}: Evaluating...'.format(scene))
# convert to numpy
vecs = vecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, vecs)
ranks = np.argsort(-scores, axis=0)
images = [img.split('/')[-1] for img in images]
for top_k in list(eval(args.top_n)):
pairs = []
for q_id in range(len(images)):
img_q = images[q_id]
pairs_per_q = [
" ".join([img_q, images[db_id]])
for db_id in list(ranks[1:top_k + 1, q_id])
]
pairs += pairs_per_q
with open(
osp.join(args.data_path, scene,
"image_pairs_" + str(top_k) + ".txt"), "w") as f:
for pair in pairs:
f.write(pair + "\n")
print('>> {}: elapsed time: {}'.format(scene,
htime(time.time() - start)))
def test(datasets, net, wandb_enabled=False, epoch=-1):
global global_step
print('>> Evaluating network on test datasets...')
# for testing we use image size of max 1024
image_size = 1024
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(
mean=net.meta['mean'],
std=net.meta['std']
)
transform = transforms.Compose([
transforms.ToTensor(),
normalize
])
# compute whitening
if args.test_whiten:
start = time.time()
print('>> {}: Learning whitening...'.format(args.test_whiten))
# loading db
db_root = os.path.join(get_data_root(), 'train', args.test_whiten)
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root, '{}-whiten.pkl'.format(args.test_whiten))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [cid2filename(db['cids'][i], ims_root) for i in range(len(db['cids']))]
# extract whitening vectors
print('>> {}: Extracting...'.format(args.test_whiten))
wvecs = extract_vectors(net, images, image_size, transform) # implemented with torch.no_grad
# learning whitening
print('>> {}: Learning...'.format(args.test_whiten))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(args.test_whiten, htime(time.time()-start)))
else:
Lw = None
# evaluate on test datasets
datasets = args.test_datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg,i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg,i) for i in range(cfg['nq'])]
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net, images, image_size, transform) # implemented with torch.no_grad
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net, qimages, image_size, transform, bbxs) # implemented with torch.no_grad
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset, ranks, cfg['gnd'], wandb_enabled=wandb_enabled, epoch=epoch, global_step=global_step)
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
compute_map_and_print(dataset + ' + whiten', ranks, cfg['gnd'], wandb_enabled=wandb_enabled, epoch=epoch, global_step=global_step)
print('>> {}: elapsed time: {}'.format(dataset, htime(time.time()-start)))
wvecs = np.hstack((vecs, qvecs))
# learning whitening
print('>> {}: Learning...'.format(whitening))
m, P = pcawhitenlearn(wvecs)
Lw = {'m': m, 'P': P}
del wvecs
gc.collect()
# saving whitening if whiten_fn exists
if whiten_fn is not None:
whiten_fn = os.path.join(
get_data_root(), 'whiten',
'R101_FC_GL_362_IS1024_MS1,0.707,1.414.pth')
print('>> {}: Saving to {}...'.format(whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(whitening,
htime(time.time() - start)))
else:
Lw = None
#%%
print('>> apply PCA whiten...')
if Lw is not None:
# whiten the vectors and shrinkage
split_num = 4
for i in range(split_num):
vecs_lw_temp = np.dot(
Lw['P'],
vecs[:,
int(vecs.shape[1] / split_num *
i):int(vecs.shape[1] / split_num * (i + 1))] - Lw['m'])
if i == 0:
def testOxfordParisHolidays(net, eConfig):
#datasets = eConfig['test-datasets'].split(',')
#results = []
#
#for dataset in datasets:
# results.append((dataset, np.random.rand(1)[0]))
#
#return results
print('>> Evaluating network on test datasets...')
# for testing we use image size of max 1024
image_size = 1024
# setting up the multi-scale parameters
ms = [1]
msp = 1
if (eConfig['multiscale']):
ms = [1, 1. / math.sqrt(2), 1. / 2]
if net.meta['pooling'] == 'gem' and net.whiten is None:
msp = net.pool.p.data.tolist()[0]
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# compute whitening
if eConfig['whitening']:
start = time.time()
print('>> {}: Learning whitening...'.format(eConfig['test-whiten']))
# loading db
db_root = os.path.join(get_data_root(), 'train',
eConfig['test-whiten'])
ims_root = os.path.join(db_root, 'ims')
db_fn = os.path.join(db_root,
'{}-whiten.pkl'.format(eConfig['test-whiten']))
with open(db_fn, 'rb') as f:
db = pickle.load(f)
images = [
cid2filename(db['cids'][i], ims_root)
for i in range(len(db['cids']))
]
# extract whitening vectors
print('>> {}: Extracting...'.format(eConfig['test-whiten']))
wvecs = extract_vectors(net,
images,
image_size,
transform,
ms=ms,
msp=msp)
# learning whitening
print('>> {}: Learning...'.format(eConfig['test-whiten']))
wvecs = wvecs.numpy()
m, P = whitenlearn(wvecs, db['qidxs'], db['pidxs'])
Lw = {'m': m, 'P': P}
print('>> {}: elapsed time: {}'.format(eConfig['test-whiten'],
htime(time.time() - start)))
else:
Lw = None
# evaluate on test datasets
datasets = eConfig['test-datasets'].split(',')
results = []
for dataset in datasets:
start = time.time()
if (dataset != 'holidays' and dataset != 'rholidays'):
print('>> {}: Extracting...'.format(dataset))
# prepare config structure for the test dataset
cfg = configdataset(dataset, os.path.join(get_data_root(), 'test'))
images = [cfg['im_fname'](cfg, i) for i in range(cfg['n'])]
qimages = [cfg['qim_fname'](cfg, i) for i in range(cfg['nq'])]
bbxs = [tuple(cfg['gnd'][i]['bbx']) for i in range(cfg['nq'])]
if (dataset == 'oxford105k' or dataset == 'paris106k'):
images.extend(cfg['distractors'])
# extract database and query vectors
print('>> {}: database images...'.format(dataset))
vecs = extract_vectors(net,
images,
image_size,
transform,
ms=ms,
msp=msp)
print('>> {}: query images...'.format(dataset))
qvecs = extract_vectors(net,
qimages,
image_size,
transform,
bbxs,
ms=ms,
msp=msp)
print('>> {}: Evaluating...'.format(dataset))
# convert to numpy
vecs = vecs.numpy()
qvecs = qvecs.numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
results.append(
compute_map_and_print(
dataset +
('+ multiscale' if eConfig['multiscale'] else ''), ranks,
cfg['gnd']))
if Lw is not None:
# whiten the vectors
vecs_lw = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs_lw = whitenapply(qvecs, Lw['m'], Lw['P'])
# search, rank, and print
scores = np.dot(vecs_lw.T, qvecs_lw)
ranks = np.argsort(-scores, axis=0)
results.append(
compute_map_and_print(dataset + ' + whiten', ranks,
cfg['gnd']))
else:
results.append(testHolidays(net, eConfig, dataset, Lw))
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))
return results
def main():
args = parser.parse_args()
# check if there are unknown datasets
for dataset in args.datasets.split(','):
if dataset not in datasets_names:
raise ValueError(
'Unsupported or unknown dataset: {}!'.format(dataset))
# check if test dataset are downloaded
# and download if they are not
# download_train(get_data_root())
# download_test(get_data_root())
# setting up the visible GPU
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_id
# loading network from path
if args.network_path is not None:
print(">> Loading network:\n>>>> '{}'".format(args.network_path))
if args.network_path in PRETRAINED:
# pretrained networks (downloaded automatically)
state = load_url(PRETRAINED[args.network_path],
model_dir=os.path.join(get_data_root(),
'networks'))
else:
# fine-tuned network from path
state = torch.load(args.network_path)
# parsing net params from meta
# architecture, pooling, mean, std required
# the rest has default values, in case that is doesnt exist
net_params = {}
net_params['architecture'] = state['meta']['architecture']
net_params['pooling'] = state['meta']['pooling']
net_params['local_whitening'] = state['meta'].get(
'local_whitening', False)
net_params['regional'] = state['meta'].get('regional', False)
net_params['whitening'] = state['meta'].get('whitening', False)
net_params['mean'] = state['meta']['mean']
net_params['std'] = state['meta']['std']
net_params['pretrained'] = False
# load network
net = init_network(net_params)
net.load_state_dict(state['state_dict'])
# if whitening is precomputed
if 'Lw' in state['meta']:
net.meta['Lw'] = state['meta']['Lw']
print(">>>> loaded network: ")
print(net.meta_repr())
# loading offtheshelf network
elif args.network_offtheshelf is not None:
# parse off-the-shelf parameters
offtheshelf = args.network_offtheshelf.split('-')
net_params = {}
net_params['architecture'] = offtheshelf[0]
net_params['pooling'] = offtheshelf[1]
net_params['local_whitening'] = 'lwhiten' in offtheshelf[2:]
net_params['regional'] = 'reg' in offtheshelf[2:]
net_params['whitening'] = 'whiten' in offtheshelf[2:]
net_params['pretrained'] = True
# load off-the-shelf network
print(">> Loading off-the-shelf network:\n>>>> '{}'".format(
args.network_offtheshelf))
net = init_network(net_params)
print(">>>> loaded network: ")
print(net.meta_repr())
# setting up the multi-scale parameters
ms = list(eval(args.multiscale))
if len(ms) > 1 and net.meta['pooling'] == 'gem' and not net.meta[
'regional'] and not net.meta['whitening']:
msp = net.pool.p.item()
print(">> Set-up multiscale:")
print(">>>> ms: {}".format(ms))
print(">>>> msp: {}".format(msp))
else:
msp = 1
# moving network to gpu and eval mode
net.cuda()
net.eval()
# set up the transform
normalize = transforms.Normalize(mean=net.meta['mean'],
std=net.meta['std'])
transform = transforms.Compose([transforms.ToTensor(), normalize])
# evaluate on test datasets
datasets = args.datasets.split(',')
for dataset in datasets:
start = time.time()
print('>> {}: Extracting...'.format(dataset))
print('>> Prepare data information...')
index_file_path = os.path.join(get_data_root(), 'index.csv')
index_mark_path = os.path.join(get_data_root(), 'index_mark.csv')
index_miss_path = os.path.join(get_data_root(), 'index_miss.csv')
test_file_path = os.path.join(get_data_root(), 'test.csv')
test_mark_path = os.path.join(get_data_root(), 'test_mark.csv')
test_mark_add_path = os.path.join(get_data_root(), 'test_mark_add.csv')
test_miss_path = os.path.join(get_data_root(), 'test_miss.csv')
if dataset == 'google-landmarks-dataset':
index_img_path = os.path.join(get_data_root(), 'index')
test_img_path = os.path.join(get_data_root(),
'google-landmarks-dataset-test')
elif dataset == 'google-landmarks-dataset-resize':
index_img_path = os.path.join(get_data_root(),
'resize_index_image')
test_img_path = os.path.join(get_data_root(), 'resize_test_image')
if not (os.path.isfile(index_mark_path)
or os.path.isfile(index_miss_path)):
clear_no_exist(index_file_path, index_mark_path, index_miss_path,
index_img_path)
if not (os.path.isfile(test_mark_path)
or os.path.isfile(test_miss_path)):
clear_no_exist(test_file_path, test_mark_path, test_miss_path,
test_img_path)
print('>> load index image path...')
retrieval_other_dataset = '/home/iap205/Datasets/google-landmarks-dataset-resize'
csvfile = open(index_mark_path, 'r')
csvreader = csv.reader(csvfile)
images = []
miss, add = 0, 0
for line in csvreader:
if line[0] == '1':
images.append(os.path.join(index_img_path, line[1] + '.jpg'))
elif line[0] == '0':
retrieval_img_path = os.path.join(retrieval_other_dataset,
'resize_index_image',
line[1] + '.jpg')
if os.path.isfile(retrieval_img_path):
images.append(retrieval_img_path)
add += 1
miss += 1
csvfile.close()
print(
'>>>> index image miss: {}, supplement: {}, still miss: {}'.format(
miss, add, miss - add))
print('>> load query image path...')
csvfile = open(test_mark_path, 'r')
csvreader = csv.reader(csvfile)
savefile = open(test_mark_add_path, 'w')
save_writer = csv.writer(savefile)
qimages = []
miss, add = 0, 0
for line in csvreader:
if line[0] == '1':
qimages.append(os.path.join(test_img_path, line[1] + '.jpg'))
save_writer.writerow(line)
elif line[0] == '0':
retrieval_img_path = os.path.join(retrieval_other_dataset,
'resize_test_image',
line[1] + '.jpg')
if os.path.isfile(retrieval_img_path):
qimages.append(retrieval_img_path)
save_writer.writerow(['1', line[1]])
add += 1
else:
save_writer.writerow(line)
miss += 1
csvfile.close()
savefile.close()
print(
'>>>> test image miss: {}, supplement: {}, still miss: {}'.format(
miss, add, miss - add))
# extract index vectors
print('>> {}: index images...'.format(dataset))
split_num = 6
extract_num = int(len(images) / split_num)
num_list = list(range(0, len(images), extract_num))
num_list.append(len(images))
# k = 0
# print('>>>> extract part {} of {}'.format(k, split_num-1))
# vecs = extract_vectors(net, images[num_list[k]:num_list[k+1]], args.image_size, transform, ms=ms, msp=msp)
# vecs = vecs.numpy()
# print('>>>> save index vecs to pkl...')
# vecs_file_path = os.path.join(get_data_root(), 'index_vecs{}_of_{}.pkl'.format(k+1, split_num))
# vecs_file = open(vecs_file_path, 'wb')
# pickle.dump(vecs[:, num_list[k]:num_list[k+1]], vecs_file)
# vecs_file.close()
# print('>>>> index_vecs{}_of_{}.pkl save done...'.format(k+1, split_num))
for i in range(split_num):
# vecs_temp = np.loadtxt(open(os.path.join(get_data_root(), 'index_vecs{}_of_{}.csv'.format(i+1, split_num)), "rb"),
# delimiter=",", skiprows=0)
with open(
os.path.join(
get_data_root(),
'index_vecs{}_of_{}.pkl'.format(i + 1, split_num)),
'rb') as f:
vecs_temp = pickle.load(f)
if i == 0:
vecs = vecs_temp
else:
vecs = np.hstack((vecs, vecs_temp[:, :]))
del vecs_temp
gc.collect()
print('\r>>>> index_vecs{}_of_{}.pkl load done...'.format(
i + 1, split_num),
end='')
print('')
# extract query vectors
print('>> {}: query images...'.format(dataset))
split_num = 1
extract_num = int(len(qimages) / split_num)
num_list = list(range(0, len(qimages), extract_num))
num_list.append(len(qimages))
# k = 0
# print('>>>> extract part {} of {}'.format(k, split_num - 1))
# qvecs = extract_vectors(net, qimages[num_list[k]:num_list[k + 1]], args.image_size, transform, ms=ms, msp=msp)
# qvecs = qvecs.numpy()
# for i in range(split_num):
# qvecs_file_path = os.path.join(get_data_root(), 'test_vecs{}_of_{}.pkl'.format(i+1, split_num))
# qvecs_file = open(qvecs_file_path, 'wb')
# pickle.dump(qvecs[:, num_list[i]:num_list[i+1]], qvecs_file)
# qvecs_file.close()
# print('\r>>>> test_vecs{}_of_{}.pkl save done...'.format(i+1, split_num), end='')
# print('')
for i in range(split_num):
# qvecs_temp = np.loadtxt(open(os.path.join(get_data_root(), 'test_vecs{}_of_{}.csv'.format(i+1, split_num)), "rb"),
# delimiter=",", skiprows=0)
with open(
os.path.join(
get_data_root(),
'test_vecs{}_of_{}.pkl'.format(i + 1, split_num)),
'rb') as f:
qvecs_temp = pickle.load(f)
if i == 0:
qvecs = qvecs_temp
else:
qvecs = np.hstack((qvecs, qvecs_temp[:, :]))
del qvecs_temp
gc.collect()
print('\r>>>> test_vecs{}_of_{}.pkl load done...'.format(
i + 1, split_num),
end='')
print('')
# vecs = np.zeros((2048, 1093278))
# qvecs = np.zeros((2048, 115921))
# save vecs to csv file
# np.savetxt(os.path.join(get_data_root(), 'index_vecs{}_of_{}.csv'.format(k, split_num-1)), vecs, delimiter=',')
# np.savetxt(os.path.join(get_data_root(), 'test_vecs{}_of_{}.csv'.format(k, split_num-1)), qvecs, delimiter=',')
# compute whitening
if args.whitening is not None:
start = time.time()
if 'Lw' in net.meta and args.whitening in net.meta['Lw']:
print('>> {}: Whitening is precomputed, loading it...'.format(
args.whitening))
if len(ms) > 1:
Lw = net.meta['Lw'][args.whitening]['ms']
else:
Lw = net.meta['Lw'][args.whitening]['ss']
else:
# if we evaluate networks from path we should save/load whitening
# not to compute it every time
if args.network_path is not None:
whiten_fn = args.network_path + '_{}_whiten'.format(
args.whitening)
if len(ms) > 1:
whiten_fn += '_ms'
whiten_fn += '.pth'
else:
whiten_fn = None
if whiten_fn is not None and os.path.isfile(whiten_fn):
print('>> {}: Whitening is precomputed, loading it...'.
format(args.whitening))
Lw = torch.load(whiten_fn)
else:
print('>> {}: Learning whitening...'.format(
args.whitening))
# extract whitening vectors
print('>> {}: Extracting...'.format(args.whitening))
wvecs = vecs
# learning whitening
print('>> {}: Learning...'.format(args.whitening))
m, P = pcawhitenlearn(wvecs)
Lw = {'m': m, 'P': P}
# saving whitening if whiten_fn exists
if whiten_fn is not None:
print('>> {}: Saving to {}...'.format(
args.whitening, whiten_fn))
torch.save(Lw, whiten_fn)
print('>> {}: elapsed time: {}'.format(args.whitening,
htime(time.time() - start)))
else:
Lw = None
print('>> apply PCAwhiten...')
if Lw is not None:
# whiten the vectors and shrinkage
vecs = whitenapply(vecs, Lw['m'], Lw['P'])
qvecs = whitenapply(qvecs, Lw['m'], Lw['P'])
print('>>>> save index PCAwhiten vecs to pkl...')
split_num = 6
extract_num = int(len(images) / split_num)
num_list = list(range(0, len(images), extract_num))
num_list.append(len(images))
for i in range(split_num):
vecs_file_path = os.path.join(
get_data_root(),
'index_PCAwhiten_vecs{}_of_{}.pkl'.format(i + 1, split_num))
vecs_file = open(vecs_file_path, 'wb')
pickle.dump(vecs[:, num_list[i]:num_list[i + 1]], vecs_file)
vecs_file.close()
print(
'\r>>>> index_PCAwhiten_vecs{}_of_{}.pkl save done...'.format(
i + 1, split_num),
end='')
print('')
print('>>>> save test PCAwhiten vecs to pkl...')
split_num = 1
extract_num = int(len(qimages) / split_num)
num_list = list(range(0, len(qimages), extract_num))
num_list.append(len(images))
for i in range(split_num):
qvecs_file_path = os.path.join(
get_data_root(),
'test_PCAwhiten_vecs{}_of_{}.pkl'.format(i + 1, split_num))
qvecs_file = open(qvecs_file_path, 'wb')
pickle.dump(qvecs[:, num_list[i]:num_list[i + 1]], qvecs_file)
qvecs_file.close()
print('\r>>>> test_PCAwhiten_vecs{}_of_{}.pkl save done...'.format(
i + 1, split_num),
end='')
print('')
print('>>>> load index PCAwhiten vecs from pkl...')
for i in range(split_num):
with open(
os.path.join(
get_data_root(),
'index_PCAwhiten_vecs{}_of_{}.pkl'.format(
i + 1, split_num)), 'rb') as f:
vecs_temp = pickle.load(f)
if i == 0:
vecs = vecs_temp
else:
vecs = np.hstack((vecs, vecs_temp[:, :]))
del vecs_temp
gc.collect()
print(
'\r>>>> index_PCAwhiten_vecs{}_of_{}.pkl load done...'.format(
i + 1, split_num),
end='')
print('')
print('>>>> load test PCAwhiten vecs from pkl...')
for i in range(split_num):
with open(
os.path.join(
get_data_root(),
'test_PCAwhiten_vecs{}_of_{}.pkl'.format(
i + 1, split_num)), 'rb') as f:
qvecs_temp = pickle.load(f)
if i == 0:
qvecs = qvecs_temp
else:
qvecs = np.hstack((qvecs, qvecs_temp[:, :]))
del qvecs_temp
gc.collect()
print('\r>>>> test_PCAwhiten_vecs{}_of_{}.pkl load done...'.format(
i + 1, split_num),
end='')
print('')
# extract principal components and dimension shrinkage
ratio = 0.8
vecs = vecs[:int(vecs.shape[0] * ratio), :]
qvecs = vecs[:int(qvecs.shape[0] * ratio), :]
print('>> {}: Evaluating...'.format(dataset))
split_num = 50
top_num = 100
vecs_T = np.zeros((vecs.shape[1], vecs.shape[0])).astype('float32')
vecs_T[:] = vecs.T[:]
QE_iter = 0
QE_weight = (np.arange(top_num, 0, -1) / top_num).reshape(
1, top_num, 1)
print('>> find {} nearest neighbour...'.format(top_num))
import faiss # place it in the file top will cause network load so slowly
# ranks_top_100 = np.loadtxt(open(os.path.join(get_data_root(), 'ranks_top_{}.csv'.format(top_num)), "rb"),
# delimiter=",", skiprows=0).astype('int')
for iter in range(0, QE_iter + 1):
if iter != 0:
# ranks_top_100 = np.ones((100, 115921)).astype('int')
print('>> Query expansion iteration {}'.format(iter))
ranks_split = 50
for i in range(ranks_split):
ranks_top_100_split = ranks_top_100[:,
int(ranks_top_100.
shape[1] /
ranks_split * i
):int(ranks_top_100
.shape[1] /
ranks_split *
(i + 1))]
top_100_vecs = vecs[:,
ranks_top_100_split] # (2048, 100, query_split_size)
qvecs_temp = (top_100_vecs * QE_weight).sum(axis=1)
qvecs_temp = qvecs_temp / (np.linalg.norm(
qvecs_temp, ord=2, axis=0, keepdims=True) + 1e-6)
if i == 0:
qvecs = qvecs_temp
else:
qvecs = np.hstack((qvecs, qvecs_temp))
del ranks_top_100_split, top_100_vecs, qvecs_temp
gc.collect()
print('\r>>>> calculate new query vectors {}/{} done...'.
format(i + 1, ranks_split),
end='')
print('')
qe_iter_qvecs_path = os.path.join(
get_data_root(), 'QE_iter{}_qvecs.pkl'.format(iter))
qe_iter_qvecs_file = open(qe_iter_qvecs_path, 'wb')
pickle.dump(qvecs, qe_iter_qvecs_file)
qe_iter_qvecs_file.close()
print('>>>> QE_iter{}_qvecs.pkl save done...'.format(iter))
del ranks_top_100
gc.collect()
for i in range(split_num):
# scores = np.dot(vecs.T, qvecs[:, int(qvecs.shape[1]/split_num*i):int(qvecs.shape[1]/split_num*(i+1))])
# ranks = np.argsort(-scores, axis=0)
# kNN search
k = top_num
index = faiss.IndexFlatL2(vecs.shape[0])
index.add(vecs_T)
query_vecs = qvecs[:,
int(qvecs.shape[1] / split_num *
i):int(qvecs.shape[1] / split_num *
(i + 1))]
qvecs_T = np.zeros((query_vecs.shape[1],
query_vecs.shape[0])).astype('float32')
qvecs_T[:] = query_vecs.T[:]
_, ranks = index.search(qvecs_T, k)
ranks = ranks.T
if i == 0:
ranks_top_100 = ranks[:top_num, :]
else:
ranks_top_100 = np.hstack(
(ranks_top_100, ranks[:top_num, :]))
# del scores, ranks
del index, query_vecs, qvecs_T, ranks
gc.collect()
print('\r>>>> kNN search {} nearest neighbour {}/{} done...'.
format(top_num, i + 1, split_num),
end='')
del qvecs
gc.collect()
print('')
del vecs, vecs_T
gc.collect()
# save to csv file
print(">> save to submission.csv file...")
submission_file = open(os.path.join(get_data_root(), 'submission.csv'),
'w')
writer = csv.writer(submission_file)
test_mark_file = open(test_mark_add_path, 'r')
csvreader = csv.reader(test_mark_file)
cnt = 0
writer.writerow(['id', 'images'])
for index, line in enumerate(csvreader):
(flag, img_name) = line[:2]
if flag == '1':
select = []
for i in range(top_num):
select.append(images[int(
ranks_top_100[i,
cnt])].split('/')[-1].split('.jpg')[0])
cnt += 1
writer.writerow([
img_name.split('/')[-1].split('.jpg')[0], ' '.join(select)
])
else:
# random_list = random.sample(range(0, len(images)), top_num)
random_list = np.random.choice(len(images),
top_num,
replace=False)
select = []
for i in range(top_num):
select.append(
images[random_list[i]].split('/')[-1].split('.jpg')[0])
writer.writerow([
img_name.split('/')[-1].split('.jpg')[0], ' '.join(select)
])
if cnt % 10 == 0 or cnt == len(qimages):
print('\r>>>> {}/{} done...'.format(cnt, len(qimages)), end='')
submission_file.close()
test_mark_file.close()
print('')
print('>> {}: elapsed time: {}'.format(dataset,
htime(time.time() - start)))