def testmodel(mymodel, args, cuda_gpu):
mytraindata = myDataset(path=args.json_file,
height=args.height,
width=args.width,
autoaugment=args.autoaugment)
mytrainloader = torch.utils.data.DataLoader(mytraindata,
batch_size=1,
shuffle=False)
gnd = loadquery(args.valdata_dir)
mymodel.eval()
with torch.no_grad():
print('>> Extracting descriptors for query images...')
qloader = torch.utils.data.DataLoader(ImagesFromList(
root='',
images=[i['queryimgid'] for i in gnd],
imsize=mytraindata.height,
transform=mytraindata.transform),
batch_size=1,
shuffle=False,
num_workers=0,
pin_memory=True)
# qoolvecs = torch.zeros(args.classnum, len(gnd)).cuda()
qoolvecs = torch.zeros(OUTPUT_DIM[args.backbone], len(gnd)).cuda()
lenq = len(qloader)
for i, input in enumerate(qloader):
out = mymodel(input.cuda())
qoolvecs[:, i] = out.data.squeeze()
if (i + 1) % 10 == 0:
print('\r>>>> {}/{} done...'.format(i + 1, lenq), end='')
print('')
poolvecs = torch.zeros(OUTPUT_DIM[args.backbone],
len(mytrainloader)).cuda()
idlist = []
print('>> Extracting descriptors for database images...')
for index, data in enumerate(mytrainloader):
batch_x, batch_y, batch_id = data
idlist.append(batch_id[0])
if cuda_gpu:
batch_x = batch_x.cuda()
batch_x = batch_x.float()
# batch_x, batch_y = Variable(batch_x), Variable(batch_y)
out = mymodel(batch_x)
poolvecs[:, index] = out
if (index + 1) % 10 == 0:
print('\r>>>> {}/{} done...'.format(index + 1,
len(mytrainloader)),
end='')
vecs = poolvecs.cpu().numpy()
qvecs = qoolvecs.cpu().numpy()
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
dataset = args.json_file.split('/')[-1].replace("all.json", "")
compute_map_and_print(dataset, ranks, gnd, idlist)
def testmultibranch(args,cuda_gpu):
args.train_dir='/mnt/sdb/shibaorong/logs/paris/triplet/usmine/withclass_cluster11/parameter_61.pkl'
mymodel = builGraph.getModel(args.backbone, args.classnum, args.gpu,
'extractor', cuda_gpu=cuda_gpu, pretrained=False)
if os.path.exists(args.train_dir):
checkpoint = torch.load(args.train_dir)
mymodel.load_state_dict(checkpoint['model_state_dict'])
mytraindata = myDataset(path=args.json_file, height=args.height, width=args.width,
autoaugment=args.autoaugment)
mytrainloader = torch.utils.data.DataLoader(mytraindata, batch_size=1, shuffle=False)
gnd = loadquery(args.valdata_dir)
mymodel.eval()
with torch.no_grad():
poolvecs = torch.zeros(OUTPUT_DIM[args.backbone], len(mytrainloader)).cuda()
idlist = []
print('>> Extracting descriptors for database images...')
for index, data in enumerate(mytrainloader):
batch_x, batch_y, batch_id = data
idlist.append(batch_id[0])
if cuda_gpu:
batch_x = batch_x.cuda()
batch_x = batch_x.float()
# batch_x, batch_y = Variable(batch_x), Variable(batch_y)
out = mymodel(batch_x)
#out=torch.cat((out1,out2),-1)
poolvecs[:, index] = out
if (index + 1) % 10 == 0:
print('\r>>>> {}/{} done...'.format(index + 1, len(mytrainloader)), end='')
qindexs=np.arange(len(mytrainloader))[np.in1d(idlist,[i['queryimgid'] for i in gnd])]
newgnd=[idlist[i] for i in qindexs]
g=[[i['queryimgid'] for i in gnd].index(j) for j in newgnd]
gnd=[gnd[i] for i in g]
vecs = poolvecs.cpu().numpy()
qvecs = vecs[:,qindexs]
# search, rank, and print
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
dataset = args.json_file.split('/')[-1].replace("all.json", "")
compute_map_and_print(dataset, ranks, gnd, idlist)
def create_triplet_clusterbased(self, mymodel, ClusterInfo, args):
print('create_triplet....................')
iddict, _, _ = ClusterInfo
gnd = loadquery(args.valdata_dir)
mymodel.eval()
with torch.no_grad():
featurelist = []
#pathlist = []
clusterlabelist = []
#classlabelist = []
for i in range(len(self.filenames)):
ID = str(self.ids[i])
feature = iddict[ID]['feature']
featurelist.append(feature)
clusterlabel = iddict[ID]['label']
clusterlabelist.append(clusterlabel)
qindexs = random.sample([i for i in range(len(featurelist))],
self.qsize)
#qindexs = np.arange(len(self.filenames))[np.in1d(self.filenames, [i['queryimgid'] for i in gnd])]
'''newgnd = [self.filenames[i] for i in qindexs]
g = [[i['queryimgid'] for i in gnd].index(j) for j in newgnd]
gnd = [gnd[i] for i in g]'''
vecs = np.transpose(np.array(featurelist))
qvecs = vecs[:, qindexs]
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
triplet_pool = []
for i in range(ranks.shape[1]):
rank = ranks[:, i]
aimg = self.filenames[qindexs[i]]
aclusterlabel = clusterlabelist[qindexs[i]]
aclasslabel = self.labels[qindexs[i]]
mark = False
'''p=[self.filenames[g] for g in rank]
po=gnd[i]['ok']
pos = np.arange(len(p))[np.in1d(p, po)]'''
for j in range(rank.shape[0]):
if j >= self.qscale:
continue
#jmark=pos[j]
rindex = rank[j]
jpath = self.filenames[rindex]
jclusterlabel = clusterlabelist[rindex]
jclasslabel = self.labels[rindex]
if jclasslabel == aclasslabel and jclusterlabel == aclusterlabel:
if mark:
pimg = jpath
nimg = self.filenames[rank[j - 1]]
triplet_pool.append([(aimg, aclasslabel),
(pimg, jclasslabel),
(nimg,
self.labels[rank[j - 1]])])
mark = False
else:
mark = True
'''elif jclasslabel!=aclasslabel and jclusterlabel!=aclusterlabel:
mark = True'''
self.triplet_pool = triplet_pool
def testOnlinepair(args,cuda_gpu,type='extractor',similartype='dot'):
mymodel = builGraph.getModel(args.backbone, args.classnum, args.gpu,
type, cuda_gpu=cuda_gpu, pretrained=False)
if os.path.exists(args.train_dir):
print(args.train_dir)
checkpoint = torch.load(args.train_dir,map_location='cpu')
mymodel.load_state_dict(checkpoint['model_state_dict'])
for index,jfile in enumerate(args.json_file):
dataset = jfile.split('/')[-1].replace("all.json", "")
mytraindata = myDataset(path=jfile, height=args.height, width=args.width,
autoaugment=args.autoaugment)
mytrainloader = torch.utils.data.DataLoader(mytraindata, batch_size=1, shuffle=False)
gnd = loadquery(args.valdata_dir[index])
mymodel.eval()
with torch.no_grad():
poolvecs = torch.zeros(OUTPUT_DIM[args.backbone], len(mytrainloader)).cuda()
idlist = []
print('>> Extracting descriptors for {} images...'.format(dataset))
for index, data in enumerate(mytrainloader):
batch_x, batch_y, batch_id = data
idlist.append(batch_id[0])
if cuda_gpu:
batch_x = batch_x.cuda()
batch_x = batch_x.float()
# batch_x, batch_y = Variable(batch_x), Variable(batch_y)
out = mymodel(batch_x)
poolvecs[:, index] = out
if (index + 1) % 10 == 0:
print('\r>>>> {}/{} done...'.format(index + 1, len(mytrainloader)), end='')
qindexs = np.arange(len(mytrainloader))[np.in1d(idlist, [i['queryimgid'] for i in gnd])]
newgnd = [idlist[i] for i in qindexs]
g = [[i['queryimgid'] for i in gnd].index(j) for j in newgnd]
gnd = [gnd[i] for i in g]
vecs = poolvecs.cpu().numpy()
'''pca = PCA(whiten=True,n_components=1000,random_state=732)
vecst=pca.fit_transform(np.transpose(vecs))
vecst=l2n(totensor(vecst))
vecs=np.transpose(tonumpy(vecst))'''
qvecs = vecs[:, qindexs]
# search, rank, and print
if similartype=='dot':
scores = np.dot(vecs.T, qvecs)
ranks = np.argsort(-scores, axis=0)
elif similartype=='euclidean':
dis=np.zeros([vecs.shape[1],qvecs.shape[1]])
for j in range(qvecs.shape[1]):
d = (vecs - np.reshape(qvecs[:, j], (qvecs.shape[0], 1))) ** 2
disj = np.sum(d, axis=0)
dis[:, j] = disj
ranks=np.argsort(dis,axis=0)
compute_map_and_print(dataset, ranks, gnd, idlist)