def predict_image_class(query_folder, target_features, cache_dict, class_minimum):
minimum = (float('inf'), 0)
for query_image_path in os.listdir(os.path.join(query_path, query_folder)):
t = time.time()
query = os.path.join(query_path, query_folder, query_image_path)
t1 = time.time() - t
cache_dict, query_features = memory_cache(cache_dict, model.model, query, os.path.join(cache_path, query_folder, query_image_path + '.pth'), transform)
t2 = time.time() - t
y = LSHash.euclidean_dist(target_features.cpu().numpy()[0], query_features.cpu().numpy()[0])
t3 = time.time() - t
print(t1, t2, t3)
if y < minimum[0]:
minimum = (y, query_folder)
class_minimum[query_folder] = minimum
target_image = transform(target_image_ori)
x = torch.zeros((1, 3, 224, 224))
x[0] = target_image
target_features = model.model._forward_impl(x.cuda())
for query_folder in os.listdir(query_path):
for query_image_path in os.listdir(
os.path.join(query_path, query_folder)):
query = os.path.join(query_path, query_folder,
query_image_path)
cache_dict, query_features = memory_cache(
cache_dict, model.model, query,
os.path.join(cache_path, query_folder,
query_image_path + '.pth'),
transform)
y = LSHash.euclidean_dist(
target_features.cpu().numpy()[0],
query_features.cpu().numpy()[0])
if y < minimum[0]:
minimum = (y, query_folder)
if minimum[0] > 1:
minimum = (minimum[0], 'obj')
# print(minimum)
obj = ET.SubElement(root, 'object')
ET.SubElement(obj, 'name').text = minimum[1]
bndbx = ET.SubElement(obj, 'bndbox')
ET.SubElement(bndbx, 'xmin').text = str(b[0])
ET.SubElement(bndbx, 'ymin').text = str(b[1])
ET.SubElement(bndbx, 'xmax').text = str(b[2])
ET.SubElement(bndbx, 'ymax').text = str(b[3])
print(time.time() - start_time)
# cv2.imshow(f'im_{i}', draw)
def predict():
model = Model(ResNet(predict=True))
model.compile(torch.optim.SGD(model.model.parameters(),
lr=0.001,
momentum=0.9,
weight_decay=1e-4),
ContrastiveLoss(),
metric=None,
device='cuda')
model.load_weights(
'/home/palm/PycharmProjects/seven2/snapshots/pairs/5/epoch_1_0.012463876953125.pth'
)
model.model.eval()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform = transforms.Compose(
[transforms.Resize((224, 224)),
transforms.ToTensor(), normalize])
target_path = '/home/palm/PycharmProjects/seven/images/test6/train'
query_path = '/home/palm/PycharmProjects/seven/images/cropped6/train'
cache_path = '/home/palm/PycharmProjects/seven/caches'
cache_dict = {}
predicted_dict = {}
correct = 0
count = 0
with torch.no_grad():
for target_image_folder in os.listdir(target_path):
if target_image_folder not in os.listdir(query_path):
continue
predicted_dict[target_image_folder] = {}
for target_image_path in os.listdir(
os.path.join(target_path, target_image_folder)):
count += 1
target = os.path.join(target_path, target_image_folder,
target_image_path)
target_image_ori = Image.open(target)
target_image = transform(target_image_ori)
x = torch.zeros((1, 3, 224, 224))
x[0] = target_image
target_features = model.model._forward_impl(x.cuda())
minimum = (float('inf'), 0)
for query_folder in os.listdir(query_path):
for query_image_path in os.listdir(
os.path.join(query_path, query_folder)):
query = os.path.join(query_path, query_folder,
query_image_path)
cache_dict, query_features = memory_cache(
cache_dict, model.model, query,
os.path.join(cache_path, query_folder,
query_image_path + '.pth'), transform)
y = LSHash.euclidean_dist(
target_features.cpu().numpy()[0],
query_features.cpu().numpy()[0])
if y < minimum[0]:
minimum = (y, query_folder)
print(*minimum, target_image_folder)
predicted_dict[target_image_folder][
target_image_path] = minimum[1]
if minimum[1] == target_image_folder:
correct += 1
print(count / correct)
pk.dump(predicted_dict, open('cls_eval.pk', 'wb'))