add crop in orig img

app.py

@@ -112,22 +112,25 @@ def predict_md(im,
     
     ## detect objects
     results = MD_model(im)  # inference # vars(results).keys()= dict_keys(['imgs', 'pred', 'names', 'files', 'times', 'xyxy', 'xywh', 'xyxyn', 'xywhn', 'n', 't', 's'])
-    results.render()  # updates results.imgs with boxes and labels
-
+    # results.render()  # updates results.imgs with boxes and labels
+    #pdb.set_trace()
     return results  
 
 ##########################################
-def crop_animal_detections(yolo_results, 
+def crop_animal_detections(img_in,
+                           yolo_results, 
                            likelihood_th):
 
     ## Extract animal crops
     #print(yolo_results)
     list_labels_as_str = [i for i in yolo_results.names.values()]  # ['animal', 'person', 'vehicle'] 
     list_np_animal_crops = []
-    # for every image
-    #pdb.set_trace()
-    for img, det_array in zip(yolo_results.ims,
-                              yolo_results.xyxy):
+
+    # image to crop (scale as input for megadetector)
+    img_in = img_in.resize((yolo_results.ims[0].shape[1],
+                            yolo_results.ims[0].shape[0]))
+    # for every detection in the img                        
+    for det_array in yolo_results.xyxy:
 
         # for every detection
         for j in range(det_array.shape[0]):
@@ -141,14 +144,15 @@ def crop_animal_detections(yolo_results,
 
             pred_llk = det_array[j,4] 
             pred_label = det_array[j,5]
-
+            #pdb.set_trace()
             # keep animal crops above threshold
             #pdb.set_trace()
             if (pred_label == list_labels_as_str.index('animal')) and \
                 (pred_llk >= likelihood_th):
                 area = (xmin_rd, ymin_rd, xmax_rd, ymax_rd)
 
-                crop = Image.fromarray(img).crop(area)
+                #pdb.set_trace()
+                crop = img_in.crop(area) #Image.fromarray(img_in).crop(area)
                 crop_np = np.asarray(crop)
 
                 # add to list
@@ -199,8 +203,8 @@ def predict_pipeline(img_input,
     ## Get DLC model and labels as strings   
     # TODO: make a dict as for megadetector
     # pdb.set_trace()
-    path_to_DLCmodel = DownloadModel(dlc_model_input_str, '/home/sabrina/MegaDetector_DeepLabCut/model/')
-    pose_cfg_path = '/home/sabrina/MegaDetector_DeepLabCut/model/pose_cfg.yaml'      
+    path_to_DLCmodel = DownloadModel(dlc_model_input_str, 'model/')
+    pose_cfg_path = 'model/pose_cfg.yaml'      
     #pdb.set_trece()
     # extract map label ids to strings
     # pose_cfg_dict['all_joints'] is a list of one-element lists,
@@ -218,7 +222,8 @@ def predict_pipeline(img_input,
     ################################################################
     # Obtain animal crops for bboxes with confidence above th
 
-    list_crops = crop_animal_detections(md_results,
+    list_crops = crop_animal_detections(img_input,
+                                        md_results,
                                         bbox_likelihood_th)
 
     ##############################################################
@@ -250,13 +255,15 @@ def predict_pipeline(img_input,
                                          kpts_likelihood_th,
                                          path_to_DLCmodel,
                                          dlc_proc)
-        print(list_kpts_per_crop)
-        print(list_crops)
+
         # Produce final image
-        img_background = Image.fromarray(md_results.ims[0]) # img_input or Image.fromarray(md_results.imgs[0])? 
+        # img_background = Image.fromarray(md_results.ims[0]) # img_input or Image.fromarray(md_results.imgs[0])? 
         # Image.fromarray(md_results.imgs[0]) --> (640, 479)
         # img_input.size ---> (259, 194)
-        # pdb.set_trace()
+        
+        img_background = img_input.resize((md_results.ims[0].shape[1],
+                                           md_results.ims[0].shape[0]))
+        #pdb.set_trace()
 
         # resize image to match  megadetector output
         # g = (640 / max(img_background.size))  # gain

model/models.py

@@ -33,7 +33,7 @@ def DownloadModel(modelname, target_dir):
                 member.path = member.path[l:]
                 yield member
 
-    neturls = read_plainconfig("/home/sabrina/MegaDetector_DeepLabCut/model/pretrained_model_urls.yaml") #FIXME
+    neturls = read_plainconfig("model/pretrained_model_urls.yaml") #FIXME
     
     if modelname in neturls.keys():
         url = neturls[modelname]