summaryrefslogtreecommitdiff
path: root/megapixels/app/models/dataset.py
diff options
context:
space:
mode:
Diffstat (limited to 'megapixels/app/models/dataset.py')
-rw-r--r--megapixels/app/models/dataset.py53
1 files changed, 28 insertions, 25 deletions
diff --git a/megapixels/app/models/dataset.py b/megapixels/app/models/dataset.py
index 1b91467b..88986873 100644
--- a/megapixels/app/models/dataset.py
+++ b/megapixels/app/models/dataset.py
@@ -154,36 +154,42 @@ class Dataset:
sim_scores = np.linalg.norm(np.array([query_vec]) - np.array(self._face_vectors), axis=1)
match_idxs = np.argpartition(sim_scores, range(n_results))[:n_results]
- df_vector = self._metadata[types.Metadata.FACE_VECTOR]
df_record = self._metadata[types.Metadata.FILE_RECORD]
+ df_vector = self._metadata[types.Metadata.FACE_VECTOR]
+ df_roi = self._metadata[types.Metadata.FACE_ROI]
if types.Metadata.IDENTITY in self._metadata.keys():
df_identity = self._metadata[types.Metadata.IDENTITY]
else:
df_identity = None
- df_roi = self._metadata[types.Metadata.FACE_ROI]
identities = []
for match_idx in match_idxs:
# get the corresponding face vector row
roi_index = self._face_vector_roi_idxs[match_idx]
- record_idx = df_vector.iloc[roi_index].record_index
+ ds_roi = df_roi.iloc[roi_index]
+ record_idx = int(ds_roi.record_index)
ds_record = df_record.iloc[record_idx]
+
self.log.debug(f'find match index: {match_idx}, --> roi_index: {roi_index}')
fp_im = self.data_store.face(ds_record.subdir, ds_record.fn, ds_record.ext)
s3_url = self.data_store_s3.face(ds_record.uuid)
identities = []
+
+ bbox_norm = BBox.from_xywh_norm(ds_roi.x, ds_roi.y, ds_roi.w, ds_roi.w)
+
if types.Metadata.IDENTITY in self._metadata.keys():
- ds_id = df_identity.loc[df_identity['identity_key'] == ik].iloc[0]
- identity = Identity(idx,
+ ds_id = df_identity.loc[df_identity['identity_key'] == ds_record.identity_key].iloc[0]
+ identity = Identity(record_idx,
name_display=ds_id.name_display,
- name_full=ds_id.name_full,
description=ds_id.description,
gender=ds_id.gender,
- image_index=ds_id.image_index,
- identity_key=ds_id.identity_key)
- identities.append(identity)
- image_record = ImageRecord(ds_record, fp_im, s3_url, identities=identities)
+ roi_index=roi_index,
+ identity_key=ds_id.identity_key,
+ num_images=ds_id.num_images)
+ else:
+ identity = None
+ image_record = ImageRecord(ds_record, fp_im, s3_url, bbox_norm, identity=identity)
image_records.append(image_record)
return image_records
@@ -216,7 +222,7 @@ class Dataset:
class ImageRecord:
- def __init__(self, ds_record, fp, url, rois=None, identities=None):
+ def __init__(self, ds_record, fp, url, bbox_norm, identity=None):
# maybe more other meta will go there
self.image_index = ds_record.index
self.sha256 = ds_record.sha256
@@ -225,15 +231,11 @@ class ImageRecord:
self.width = ds_record.width
self.height = ds_record.height
self.url = url
- self.rois = rois
- self.identities = identities
+ self.bbox = bbox_norm
+ self.identity = identity
# image records contain ROIs
# ROIs are linked to identities
- @property
- def identity(self, index):
- return self._identity
-
def summarize(self):
'''Summarizes data for debugging'''
log = Logger.getLogger()
@@ -241,19 +243,20 @@ class ImageRecord:
log.info(f'sha256: {self.sha256}')
log.info(f'UUID: {self.uuid}')
log.info(f'S3 url: {self.url}')
- for identity in self.identities:
- log.info(f'fullname: {identity.fullname}')
- log.info(f'description: {identity.description}')
- log.info(f'gender: {identity.gender}')
- log.info(f'images: {identity.n_images}')
+ if self.identity:
+ log.info(f'name: {self.identity.name_display}')
+ log.info(f'description: {self.identity.description}')
+ log.info(f'gender: {self.identity.gender}')
+ log.info(f'images: {self.identity.num_images}')
class Identity:
- def __init__(self, idx, name_display=None, name_full=None, description=None, gender=None, roi=None):
+ def __init__(self, idx, identity_key=None, name_display=None, num_images=None,
+ description=None, gender=None, roi_index=None):
self.index = idx
self.name_display = name_display
- self.name_full = name_full
self.description = description
self.gender = gender
- self.roi = roi
+ self.roi_index = roi_index
+ self.num_images = num_images