change bbox to norm, refine face extractor

1 files changed, 37 insertions, 5 deletions

diff --git a/megapixels/app/processors/face_extractor.py b/megapixels/app/processors/face_extractor.py
index 2666e090..f618cd36 100644
--- a/megapixels/app/processors/face_extractor.py
+++ b/megapixels/app/processors/face_extractor.py
@@ -44,6 +44,9 @@ class Extractor:
       vec_flat[f'd{idx}'] = val
     return vec_flat
 
+  def to_str(self, vec):
+    return ','.join([str(x) for x in vec])
+
   def unflatten_df(self, df):
     # convert from
     return [df[f'd{i}'] for i in range(1,257)]
@@ -64,25 +67,54 @@ class ExtractorVGG(Extractor):
     self.dnn = cv.dnn.readNetFromCaffe(fp_prototxt, fp_model)
     self.feat_layer = self.dnn.getLayerNames()[-2]
 
-  def extract(self, im, bbox_norm, padding=0.3):
+  def extract_jitter(self, im, bbox_norm):
+    '''(experimental) Extracts feature vector for face crop
+    :param im:
+    :param bbox_norm: (BBox) normalized
+    :param padding: (float) percent to extend ROI
+    :param jitters: not used here
+    :returns (list) of (float)'''
+    dim = im.shape[:2][::-1]
+    num_jitters = cfg.DEFAULT_NUM_JITTERS
+    padding = cfg.DEFAULT_FACE_PADDING_VGG_FACE2
+    pad_adj = .00875 * padding  # percentage of padding to vary
+    paddings = np.linspace(padding - pad_adj, padding + pad_adj, num=num_jitters)
+    jitter_amt = cfg.DEFAULT_JITTER_AMT
+    vecs = []
+    for i in range(num_jitters):
+      bbox_norm_jit = bbox_norm.jitter(jitter_amt)  # jitters w, h, center
+      bbox_ext = bbox_norm_jit.expand(paddings[i])
+      #bbox_ext = bbox_norm.expand(paddings[i])
+      x1,y1,x2,y2 = bbox_ext.to_dim(dim).to_xyxy()
+      im_crop = im[y1:y2, x1:x2]
+      # According to VGG, model trained using Bilinear interpolation (INTER_LINEAR)
+      im_crop = cv.resize(im_crop, self.dnn_dim, interpolation=cv.INTER_LINEAR)
+      blob = cv.dnn.blobFromImage(im_crop, 1.0, self.dnn_dim, self.dnn_mean)
+      self.dnn.setInput(blob)
+      vec = np.array(self.dnn.forward(self.feat_layer)[0])
+      vec_norm = vec/np.linalg.norm(vec)  # normalize
+      vecs.append(vec_norm)
+    vec_norm = np.mean(np.array(vecs), axis=0)
+    return vec_norm
+
+  def extract(self, im, bbox_norm):
     '''Extracts feature vector for face crop
     :param im:
     :param bbox_norm: (BBox) normalized
     :param padding: (float) percent to extend ROI
     :param jitters: not used here
     :returns (list) of (float)'''
-    
+    padding = cfg.DEFAULT_FACE_PADDING_VGG_FACE2
     bbox_ext = bbox_norm.expand(padding)
     dim = im.shape[:2][::-1]
-    bbox_ext_dim = bbox_ext.to_dim(dim)
-    x1,y1,x2,y2 = bbox_ext_dim.to_xyxy()
+    x1,y1,x2,y2 = bbox_ext.to_dim(dim).to_xyxy()
     im = im[y1:y2, x1:x2]
     # According to VGG, model trained using Bilinear interpolation (INTER_LINEAR)
     im = cv.resize(im, self.dnn_dim, interpolation=cv.INTER_LINEAR)
     blob = cv.dnn.blobFromImage(im, 1.0, self.dnn_dim, self.dnn_mean)
     self.dnn.setInput(blob)
     vec = np.array(self.dnn.forward(self.feat_layer)[0])
-    vec_norm = np.array(vec)/np.linalg.norm(vec)  # normalize
+    vec_norm = vec/np.linalg.norm(vec)  # normalize
     return vec_norm