def prepare_data(dataset: DatasetEnum, index: Index):
cursor = MongoDescriptor.objects(dataset=dataset)
pbar = tqdm.tqdm(cursor,
total=cursor.count(),
desc=f"Processing {dataset} dataset")
new_dataset = []
dataset_info = {}
for query in pbar: # type: MongoDescriptor
dists, ids = index.search(np.expand_dims(query.descriptor, axis=0), 70)
dataset_object = {"query": query.photo_id, "neighbours": []}
dataset_info[query.photo_id] = {"neighbours": [], "num_neighbours": 0}
for neighbour_id, dist in zip(ids[0, :], dists[0, :]):
dataset_object['neighbours'].append(int(neighbour_id))
neighbour_doc: MongoDescriptor = MongoDescriptor.objects(
dataset=DatasetEnum.DATABASE, photo_id=neighbour_id).first()
geo_dist = compute_geo_distance(
np.array([query.coordinates]),
np.array([neighbour_doc.coordinates]))
dataset_info[query.photo_id]["neighbours"].append({
"id":
int(neighbour_id),
"geo_dist":
float(geo_dist[0]),
"desc_dist":
float(dist)
})
new_dataset.append(dataset_object)
return new_dataset, dataset_info
def prepare_data(dataset: DatasetEnum):
cursor = MongoDescriptor.objects(dataset=dataset)
pbar = tqdm.tqdm(cursor,
total=cursor.count(),
desc=f"Processing {dataset} dataset")
new_dataset = []
dataset_info = {}
for query in pbar: # type: MongoDescriptor
dataset_object = {"query": query.photo_id, "neighbours": []}
dataset_info[query.photo_id] = {"neighbours": [], "num_neighbours": 0}
neighbours = MongoDescriptor.objects(
dataset=DatasetEnum.DATABASE, coords__near=query.coordinates)[:50]
for neighbour in neighbours: # type: MongoDescriptor
dataset_object['neighbours'].append(neighbour.photo_id)
geo_dist = compute_geo_distance(np.array([query.coordinates]),
np.array([neighbour.coordinates]))
dist = np.linalg.norm(query.descriptor - neighbour.descriptor)
dataset_info[query.photo_id]["neighbours"].append({
"id":
neighbour.photo_id,
"geo_dist":
float(geo_dist[0]),
"desc_dist":
float(dist)
})
new_dataset.append(dataset_object)
return new_dataset, dataset_info
def _get_benchmark_results(pred_locations,
true_locations,
image_ids: np.ndarray = None) -> BenchmarkResult:
result = BenchmarkResult()
distance_err = metric.compute_geo_distance(true_locations, pred_locations)
result.accuracy = metric.localization_accuracy(distance_err)
result.errors = metric.avg_errors(distance_err)
result.predictions_by_dist = metric.distribution_of_predictions_by_distance(
distance_err)
if image_ids is not None:
for img_id, dist_err, pred_loc in zip(image_ids, distance_err,
pred_locations):
img_id = int(img_id)
result.img_dist_error[img_id] = dist_err
result.img_predicted_coords[img_id] = pred_loc.tolist()
return result
desc="Processing train query")
for i, train_query in enumerate(pbar):
neighbours = MongoDescriptor.objects(
dataset=DatasetEnum.DATABASE,
coords__near=train_query.coordinates)[:25]
dists, ids = index.search(np.expand_dims(train_query.descriptor, axis=0),
25)
neighbour_ids = set()
train_object = {"query": train_query.photo_id, "neighbours": []}
train_info[train_query.photo_id] = {"neighbours": [], "num_neighbours": 0}
for neighbour in neighbours:
train_object['neighbours'].append(neighbour.photo_id)
neighbour_ids.add(neighbour.photo_id)
geo_dist = compute_geo_distance(np.array([train_query.coordinates]),
np.array([neighbour.coordinates]))
desc_dist = np.linalg.norm(train_query.descriptor -
neighbour.descriptor)
train_info[train_query.photo_id]['neighbours'].append({
"id":
neighbour.photo_id,
"geo_dist":
float(geo_dist[0]),
"desc_dist":
float(desc_dist)
})
count = 0
for n_id, desc_dist in zip(ids[0, :], dists[0, :]):
if n_id not in neighbour_ids:
def prepare_data(dataset: DatasetEnum, index: Index):
cursor = MongoDescriptor.objects(dataset=dataset)
pbar = tqdm.tqdm(cursor,
total=cursor.count(),
desc=f"Processing {dataset} dataset")
new_dataset = []
dataset_info = {}
count = 0
for query in pbar: # type: MongoDescriptor
dataset_object = {
"query": query.photo_id,
"neighbours": [],
"target_id": -1
}
dataset_info[query.photo_id] = {
"neighbours": [],
"num_neighbours": 0,
"target_id": -1
}
d_dists, d_neighbours_ids = index.search(
np.expand_dims(query.descriptor, axis=0), 100)
c_neighbours = [
desc_doc for desc_doc in
MongoDescriptor.objects(dataset=DatasetEnum.DATABASE,
coords__near=query.coordinates)[:500]
]
n_descriptors = np.array(
[desc_doc.descriptor for desc_doc in c_neighbours])
c_neighbours_ids_set = {
neighbour.photo_id
for neighbour in c_neighbours
}
d_neighbours_ids_set = set(d_neighbours_ids[0])
intersection = d_neighbours_ids_set.intersection(c_neighbours_ids_set)
desc_dists = np.linalg.norm(query.descriptor - n_descriptors, axis=1)
candidates = []
if len(intersection) == 0:
# find closest in d-space among c_neighbours
target_neighbour_idx = np.argmin(desc_dists)
target_neighbour = c_neighbours[target_neighbour_idx].photo_id
candidates.append(target_neighbour)
candidates.extend(d_neighbours_ids[0][:50].tolist())
count = 0
for neighbour in c_neighbours:
if neighbour.photo_id == target_neighbour:
continue
candidates.append(neighbour.photo_id)
count += 1
if count == 49:
break
else:
# find closest in c-space among intersection
candidates.extend(list(intersection))
intersection_length = len(intersection)
max_neighbours = 100 - intersection_length
max_d_neighbours = round(max_neighbours / 2)
max_c_neighbours = max_neighbours - max_d_neighbours
count = 0
for d_id in d_neighbours_ids[0].tolist():
if d_id in intersection:
continue
candidates.append(d_id)
count += 1
if count == max_d_neighbours:
break
target_neighbour = -1
for n in c_neighbours:
if n.photo_id in intersection:
target_neighbour = n.photo_id
break
count = 0
for neighbour in c_neighbours:
if neighbour.photo_id in intersection:
continue
candidates.append(neighbour.photo_id)
count += 1
if count == max_c_neighbours:
break
dataset_object['target_id'] = target_neighbour
for neighbour_id in candidates:
dataset_object['neighbours'].append(int(neighbour_id))
# add info
neighbour_doc: MongoDescriptor = MongoDescriptor.objects(
dataset=DatasetEnum.DATABASE, photo_id=neighbour_id).first()
geo_dist = compute_geo_distance(
np.array([query.coordinates]),
np.array([neighbour_doc.coordinates]))
desc_dist = np.linalg.norm(query.descriptor -
neighbour_doc.descriptor)
dataset_info[query.photo_id]["neighbours"].append({
"id":
int(neighbour_id),
"geo_dist":
float(geo_dist[0]),
"desc_dist":
float(desc_dist)
})
new_dataset.append(dataset_object)
print(count)
return new_dataset, dataset_info