Update mask_adapter/sam_maskadapter.py

mask_adapter/sam_maskadapter.py

@@ -311,13 +311,13 @@ class SAMPointVisualizationDemo(object):
             # text_features = self.clip_model.encode_text(text.cuda())
             # text_features /= text_features.norm(dim=-1, keepdim=True)
             #np.save("/home/yongkangli/Mask-Adapter/text_embedding/lvis_coco_text_embedding.npy", text_features.cpu().numpy())
-            text_features = self.text_embedding.to(self.clip_model.device)
-            features = self.extract_features_convnext(image.to(self.clip_model.device).float())
+            text_features = self.text_embedding.to(self.mask_adapter.device)
+            features = self.extract_features_convnext(image.to(self.mask_adapter.device).float())
             clip_feature = features['clip_vis_dense']
 
             clip_vis_dense = self.visual_prediction_forward_convnext_2d(clip_feature)
 
-            semantic_activation_maps = self.mask_adapter(clip_vis_dense, pred_masks.tensor.unsqueeze(0).to(self.clip_model.device).float())
+            semantic_activation_maps = self.mask_adapter(clip_vis_dense, pred_masks.tensor.unsqueeze(0).to(self.mask_adapter.device).float())
             maps_for_pooling = F.interpolate(semantic_activation_maps, size=clip_feature.shape[-2:], mode='bilinear', align_corners=False)
 
             B, C = clip_feature.size(0), clip_feature.size(1)