add save results

app.py

@@ -19,7 +19,7 @@ import math
 import os
 import yaml
 from model.models import DownloadModel
-
+from save_results import save_results
 import pdb
 
 #########################################
@@ -112,8 +112,7 @@ 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
-    #pdb.set_trace()
+    
     return results  
 
 ##########################################
@@ -122,8 +121,6 @@ def crop_animal_detections(img_in,
                            likelihood_th):
 
     ## Extract animal crops
-    #print(yolo_results)
-    #pdb.set_trace()
     list_labels_as_str = [i for i in yolo_results.names.values()]  # ['animal', 'person', 'vehicle'] 
     list_np_animal_crops = []
 
@@ -145,9 +142,7 @@ def crop_animal_detections(img_in,
 
             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)
@@ -162,7 +157,8 @@ def crop_animal_detections(img_in,
     return list_np_animal_crops
 
 def draw_rectangle_text(img,results,font_style='amiko',font_size=8, keypt_color="white",):
-    bbxyxy = results.xyxy[0].tolist()[0]
+    #pdb.set_trace()
+    bbxyxy = results
     w, h = bbxyxy[2], bbxyxy[3]
     shape = [(bbxyxy[0], bbxyxy[1]), (w , h)]
     imgR = ImageDraw.Draw(img)  
@@ -185,22 +181,24 @@ def predict_dlc(list_np_crops,
                 kpts_likelihood_th,
                 DLCmodel,
                 dlc_proc):
-    print(DLCmodel)
+    
     # run dlc thru list of crops
     dlc_live = DLCLive(DLCmodel, processor=dlc_proc)
     dlc_live.init_inference(list_np_crops[0])
 
     list_kpts_per_crop = []
+    all_kypts  = []
     np_aux = np.empty((1,3)) # can I avoid hardcoding here?
     for crop in list_np_crops:
         # scale crop here?
         keypts_xyp = dlc_live.get_pose(crop) # third column is llk!
         # set kpts below threhsold to nan
-        print(keypts_xyp)
+        
         #pdb.set_trace()
         keypts_xyp[keypts_xyp[:,-1] < kpts_likelihood_th,:] = np_aux.fill(np.nan)
         # add kpts of this crop to list 
         list_kpts_per_crop.append(keypts_xyp)
+        all_kypts.append(keypts_xyp)
     #return confidence here
     return list_kpts_per_crop
 
@@ -230,6 +228,7 @@ def predict_pipeline(img_input,
     # pose_cfg_dict['all_joints'] is a list of one-element lists,
     with open(pose_cfg_path, "r") as stream:
         pose_cfg_dict = yaml.safe_load(stream) 
+    
     map_label_id_to_str = dict([(k,v) for k,v in zip([el[0] for el in pose_cfg_dict['all_joints']], 
                                                      pose_cfg_dict['all_joints_names'])])
 
@@ -275,19 +274,10 @@ def predict_pipeline(img_input,
                                          kpts_likelihood_th,
                                          path_to_DLCmodel,
                                          dlc_proc)
-
-        # Produce final image
-        # 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)
         
-        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
-        # img_background = img_background.resize((int(x * g) for x in img_background.size), Image.ANTIALIAS)  # resize
+        img_background = img_input.resize((md_results.ims[0].shape[1],md_results.ims[0].shape[0]))
+        print('I have ' + str(len(list_crops)) + ' bounding box')
+        
         for ic, (np_crop, kpts_crop) in enumerate(zip(list_crops,
                                                       list_kpts_per_crop)):
 
@@ -304,17 +294,23 @@ def predict_pipeline(img_input,
                                     marker_size=marker_size)
 
             ## Paste crop in original image https://pillow.readthedocs.io/en/stable/reference/Image.html#PIL.Image.Image.paste
-            img_background.paste(img_crop,
-                                 box = tuple([int(t) for t in md_results.xyxy[0][ic,:2]]))
+            img_background.paste(img_crop, box = tuple([int(t) for t in md_results.xyxy[0][ic,:2]]))
+
+
+            #set trh!! FIXME
+            bb_per_animal = md_results.xyxy[0].tolist()[ic]
+            pred = md_results.xyxy[0].tolist()[ic][4]
+            if bbox_likelihood_th < pred:
+                draw_rectangle_text(img_background, bb_per_animal ,font_style=font_style,font_size=font_size, keypt_color=keypt_color)  
 
-            draw_rectangle_text(img_background, md_results ,font_style=font_style,font_size=font_size, keypt_color=keypt_color)       
-            #draw_rectangle_text(img,results,font_style='amiko',font_size=8, keypt_color="#ff0000",):                                             
-        return img_background
+            print(pred)
+
+        download_file  = save_results(md_results,list_kpts_per_crop,map_label_id_to_str,bbox_likelihood_th)         
+
+        return img_background, download_file
 
 #############################################
-# %% 
 # User interface: inputs
-
 # Input image
 gr_image_input = gr.inputs.Image(type="pil", label="Input Image")
 
@@ -334,7 +330,7 @@ gr_dlc_only_checkbox = gr.inputs.Checkbox(False,
 gr_str_labels_checkbox = gr.inputs.Checkbox(True,
                                             label='Show bodypart labels?')   
 
-gr_slider_conf_bboxes = gr.inputs.Slider(0,1,.05,0.8,
+gr_slider_conf_bboxes = gr.inputs.Slider(0,1,.02,0.8,
                                         label='Set confidence threshold for animal detections')
 gr_slider_conf_keypoints = gr.inputs.Slider(0,1,.05,0,
                                             label='Set confidence threshold for keypoints')
@@ -368,7 +364,8 @@ inputs = [gr_image_input,
 # %% 
 # User interface: outputs
 gr_image_output = gr.outputs.Image(type="pil", label="Output Image")
-outputs = [gr_image_output]
+out_smpl_npy_download = gr.File(label="Download JSON file")
+outputs = [gr_image_output,out_smpl_npy_download]
 
 ##############################################
 # User interace: description
@@ -382,7 +379,7 @@ gr_description = "Contributed by Sofia Minano, Neslihan Wittek, Nirel Kadzo, Vic
 # article = "<p style='text-align: center'>This app makes predictions using a YOLOv5x6 model that was trained to detect animals, humans, and vehicles in camera trap images; find out more about the project on <a href='https://github.com/microsoft/CameraTraps'>GitHub</a>. This app was built by Henry Lydecker but really depends on code and models developed by <a href='http://ecologize.org/'>Ecologize</a> and <a href='http://aka.ms/aiforearth'>Microsoft AI for Earth</a>. Find out more about the YOLO model from the original creator, <a href='https://pjreddie.com/darknet/yolo/'>Joseph Redmon</a>. YOLOv5 is a family of compound-scaled object detection models trained on the COCO dataset and developed by Ultralytics, and includes simple functionality for Test Time Augmentation (TTA), model ensembling, hyperparameter evolution, and export to ONNX, CoreML and TFLite. <a href='https://github.com/ultralytics/yolov5'>Source code</a> | <a href='https://pytorch.org/hub/ultralytics_yolov5'>PyTorch Hub</a></p>"
 
 examples = [['example/monkey_full.jpg', 'md_v5a','full_macaque', False, True, 0.5, 0.3, 'amiko', 9, 'blue', 3],
-            ['example/dog.jpeg', 'md_v5a', 'full_dog', False, True, 0.5, 0.05, 'amiko',9, 'yellow', 3],
+            ['example/dog.jpeg', 'md_v5a', 'full_dog', False, True, 0.5, 0.00, 'amiko',9, 'yellow', 3],
             ['example/cat.jpg', 'md_v5a', 'full_cat', False, True, 0.5, 0.05, 'amiko', 9, 'purple', 3]]
 
 ################################################

save_results.py

@@ -0,0 +1,59 @@
+import json 
+import numpy as np
+import pdb
+
+dict_pred = {0: 'animal', 1: 'person', 2: 'vehicle'}
+
+
+def save_results(md_results, dlc_outputs,map_label_id_to_str,thr,output_file = 'dowload_predictions.json'):
+
+    """
+
+    write json
+
+    """
+    info = {}
+    ## info megaDetector
+    info['file']= md_results.files[0]
+    number_bb = len(md_results.xyxy[0].tolist())
+    info['number_of_bb'] = number_bb
+    number_bb_thr = len(dlc_outputs)
+    labels = [n for n in map_label_id_to_str.values()]
+    #pdb.set_trace()
+    new_index = []
+    for i in range(number_bb):
+        corner_x1,corner_y1,corner_x2,corner_y2,confidence, _ =  md_results.xyxy[0].tolist()[i]
+
+        if confidence > thr:
+            new_index.append(i)
+
+
+    for i in range(number_bb_thr):
+        aux={}
+        corner_x1,corner_y1,corner_x2,corner_y2,confidence, _ =  md_results.xyxy[0].tolist()[new_index[i]]
+        aux['corner_1'] = (corner_x1,corner_y1)
+        aux['corner_2'] = (corner_x2,corner_y2)
+        aux['predict MD'] = md_results.names[0]
+        aux['confidence MD'] = confidence
+        
+        ## info dlc
+        kypts = []
+        pdb.set_trace()
+        for s in dlc_outputs[i]:
+            #print(s)
+            aux1 = []
+            for j in s:
+                aux1.append(float(j))
+
+            kypts.append(aux1)
+        pdb.set_trace()
+        aux['dlc_pred']  = dict(zip(labels,kypts))
+        info['bb_' + str(new_index[i]) ]=aux
+
+
+    with open(output_file, 'w') as f:
+        json.dump(info, f, indent=1)
+        print('Output file saved at {}'.format(output_file))
+
+    return output_file
+