Remove useless stuf

model/exp_synph_real.py

@@ -106,57 +106,6 @@ class Worker(torchext.Worker):
         out = net(self.data['im0'])
         return out
 
-    @staticmethod
-    def find_corr_points_and_F(left, right):
-        sift = cv2.SIFT_create()
-        # find the keypoints and descriptors with SIFT
-        kp1, des1 = sift.detectAndCompute(cv2.normalize(left, None, 0, 255, cv2.NORM_MINMAX).astype('uint8'), None)
-        kp2, des2 = sift.detectAndCompute(cv2.normalize(right, None, 0, 255, cv2.NORM_MINMAX).astype('uint8'), None)
-        # FLANN parameters
-        FLANN_INDEX_KDTREE = 1
-        index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
-        search_params = dict(checks=50)
-        flann = cv2.FlannBasedMatcher(index_params, search_params)
-        matches = flann.knnMatch(des1, des2, k=2)
-        pts1 = []
-        pts2 = []
-        # ratio test as per Lowe's paper
-        for i, (m, n) in enumerate(matches):
-            if m.distance < 0.8 * n.distance:
-                pts2.append(kp2[m.trainIdx].pt)
-                pts1.append(kp1[m.queryIdx].pt)
-
-        pts1 = np.int32(pts1)
-        pts2 = np.int32(pts2)
-        F, mask = cv2.findFundamentalMat(pts1, pts2, cv2.FM_LMEDS)
-        # We select only inlier points
-        pts1 = pts1[mask.ravel() == 1]
-        pts2 = pts2[mask.ravel() == 1]
-        return pts1, pts2, F
-
-    def calc_sgbm_gt(self):
-        sgbm_matcher = cv2.StereoSGBM_create()
-        disp_gt = []
-        # cam_view = np.array(np.array_split(self.data['im0'].detach().to('cpu').numpy(), 4)[2:])
-        # for i in range(self.data['im0'].shape[0]):
-        for i in range(1):
-            cam_view = self.data['im0'].detach().to('cpu').numpy()[i, 0]
-            pattern = self.pattern_proj.to('cpu').numpy()[i, 0]
-            pts_l, pts_r, F = self.find_corr_points_and_F(cam_view, pattern)
-            H_l, _ = cv2.findHomography(pts_l, pts_r)
-            H_r, _ = cv2.findHomography(pts_r, pts_l)
-
-            left_rect = cv2.warpPerspective(cam_view, H_l, cam_view.shape)
-            right_rect = cv2.warpPerspective(pattern, H_r, pattern.shape)
-
-            transform = transforms.ToTensor()
-            disparity_gt = transform(cv2.normalize(
-                sgbm_matcher.compute(cv2.normalize(left_rect, None, 0, 255, cv2.NORM_MINMAX).astype('uint8'),
-                                     cv2.normalize(right_rect, None, 0, 255, cv2.NORM_MINMAX).astype('uint8')), None,
-                alpha=0, beta=1, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32F).T)
-            disp_gt.append(disparity_gt)
-        return disp_gt
-
     def loss_forward(self, out, train):
         out, edge = out
         if not (isinstance(out, tuple) or isinstance(out, list)):
@@ -181,24 +130,8 @@ class Worker(torchext.Worker):
             edge0 = 1 - torch.sigmoid(edge[0])
         val = 0
         if isinstance(out[0], tuple):
-            # val = self.disparity_loss(out[0][1], edge0)
-            # FIXME disparity_loss ist unsupervised, wir wollen supervised(?)
-            #   warum nicht einfach so die GT die wir eh schon haben?
-            # gt = self.data[f'disp0'].type('torch.LongTensor')
-
+            # NOTE use supervised disparity loss
             val += self.sup_disp_loss(out[0][1], self.data['disp0'])
-            # disp_gt = self.calc_sgbm_gt()
-            # if len(disp_gt) > 1:
-            #     disparity_gt = torch.stack(disp_gt).to('cuda')
-            #     # val += self.sup_disp_loss(out[0][1], disparity_gt)
-            # else:
-            #     disparity_gt = disp_gt[0].to('cuda')
-            #     val += self.sup_disp_loss(out[0][1][0], disparity_gt)
-            # print(disparity_gt)
-            # print(disparity_gt.shape)
-            # print(out[0][1])
-            # print(out[0][1].shape)
-        if isinstance(out[0], tuple):
             val += self.disparity_loss(out[0][0], edge0)
         else:
             val += self.disparity_loss(out[0], edge0)