optimisation masks ok

compute_features.py

@@ -7,15 +7,9 @@ import json
 from utils import compute_categories_id, compute_id_good_occ
 from scipy.spatial.transform import Rotation
 from bbox_2d import bbox_2d
-
-
-def convert2(xyz):
-    (R, P, Y) = (xyz[0], xyz[1], xyz[2])
-    Q = Rotation.from_euler(seq='xyz', angles=[R, P, Y], degrees=False).as_quat()
-    r = Rotation.from_quat(Q)
-    rotation = r.as_matrix()
-
-    return rotation
+import cv2
+from instance_mask import instance
+from pose import convert2
 
 
 def process_compute(data_name, Nb_camera, Nb_world, list_categories, occ_target):
@@ -46,11 +40,11 @@ def process_compute(data_name, Nb_camera, Nb_world, list_categories, occ_target)
             if len(data_Bbox_2d) != len(data_3D_pose) :
                 raise TypeError("size of datas are differents !!")
 
-            for k in range(len(data_3D_pose)):
+            for categories in list_categories:
 
-                for categories in list_categories:
+                if len(catergories_occ_array[categories]) == 1 :
 
-                    if len(catergories_occ_array[categories]) == 1 :
+                    for k in range(len(data_3D_pose)):
 
                         if data_3D_pose[k]['id'] == catergories_occ_array[categories][0]:
                             cont1 += 1
@@ -75,6 +69,16 @@ def process_compute(data_name, Nb_camera, Nb_world, list_categories, occ_target)
                         else:
                             continue
 
+
+                    id = catergories_occ_array[categories][0]
+                    img = cv2.imread(f"{data_name}/Instance_Segmentation/{p}.png", cv2.IMREAD_UNCHANGED) # plt.imread(path)
+
+                    instance_img = instance(img, id)
+                    cv2.imwrite(f"{data_name}/Generated/Instance_Mask/{categories}/{p}.png", 255*instance_img)
+
+
+
+
     print(cont1, cont2, cont3)
 
 

instance_mask.py

@@ -5,95 +5,6 @@ from pathlib import Path
 
 
 
-def compute_categories_id(data_name, world):
-    #Category = 'banana1'
-    #Category = 'pear2'
-    #Category = "orange2"
-    # Opening JSON file
-    f = open(f'{data_name}/Meta/{world}.json')
-    
-    # returns JSON object as 
-    # a dictionary
-    data = json.load(f)
-    
-    # Iterating through the json
-    # list
-
-    catergories_label_to_id={}
-    catergories_id_to_label={}
-    catergories_instance_array_cat_to_id={}
-    catergories_instance_array_id_to_cat={}
-
-    for k in data['categories']:
-        catergories_label_to_id[k['label']]=k['id']
-        catergories_id_to_label[k['id']]=k['label']
-        catergories_instance_array_cat_to_id[k['label']]=[]
-
-    for k in data['objects']:
-        #print(k)
-        #catergories_instance_array[catergories_id_to_label[i['category_id']]]
-        catergories_instance_array_id_to_cat[k['id']] = catergories_id_to_label[k['category_id']]
-        catergories_instance_array_cat_to_id[catergories_id_to_label[k['category_id']]].append(k['id'])
-        # if i['category_id'] == id_category :
-        #     print("Hello fruits instance")
-        #     id_instances.append(i['id'])
-        #     print(i['id']) 
-
-    # print("catergories_instance_array_cat_to_id : ", catergories_instance_array_cat_to_id)
-    # print("catergories_instance_array_id_to_cat : ", catergories_instance_array_id_to_cat)
-
-
-    # Closing file
-    f.close()
-
-
-    return catergories_instance_array_id_to_cat, catergories_instance_array_cat_to_id
-
-
-
-def compute_id_good_occ(data_name, count, catergories_instance_array_id_to_cat, catergories_instance_array_cat_to_id, Occ_wanted):
-
-    f2 = open(f'{data_name}/Occlusion/{count}.json')
-
-    data2 = json.load(f2)
-
-
-    catergories_occ_array = {}
-
-    for cat in catergories_instance_array_cat_to_id :
-        #print(cat)
-
-        catergories_occ_array[cat] = []
-
-    for i in data2:
-        #print('i : ',i)
-        #print(i['id'])
-        #print(id_instances)
-        if i['occlusion_value'] > 0.5 :
-            catergories_occ_array[catergories_instance_array_id_to_cat[i['id']]].append(i['id'])
-
-
-
-        # if i['id'] in id_instances :
-        #     print("Hello banana instance occ")
-        #     if i['occlusion_value'] > 0.5 :
-        #         id_instances_good.append(i['id'])
-        #         print(i['id'])
-        #         print(i['occlusion_value'])
-
-    print(catergories_occ_array)
-
-
-
-
-    # Closing file
-    f2.close()
-
-    return catergories_occ_array
-
-
-
-
 def instance(im, id):
     #im = im * 255
     im[im == id] = 255
@@ -104,36 +15,36 @@ def instance(im, id):
     return im
 
 
-def generate_instance_mask(data_name, Nb_camera, Nb_world,list_categories, occ_target):
+# def generate_instance_mask(data_name, Nb_camera, Nb_world,list_categories, occ_target):
 
-    for i in range(1, Nb_world + 1): # worlds
+#     for i in range(1, Nb_world + 1): # worlds
         
-        catergories_instance_array_id_to_cat, catergories_instance_array_cat_to_id = compute_categories_id(data_name, i)
+#         catergories_instance_array_id_to_cat, catergories_instance_array_cat_to_id = compute_categories_id(data_name, i)
         
 
 
-        for j in range(1, Nb_camera+1): # cameras
-            p = ((i-1)*Nb_camera) + j
+#         for j in range(1, Nb_camera+1): # cameras
+#             p = ((i-1)*Nb_camera) + j
 
-            catergories_occ_array = compute_id_good_occ(data_name, p, catergories_instance_array_id_to_cat, catergories_instance_array_cat_to_id, occ_target)
+#             catergories_occ_array = compute_id_good_occ(data_name, p, catergories_instance_array_id_to_cat, catergories_instance_array_cat_to_id, occ_target)
 
 
-            for categories in list_categories:
+#             for categories in list_categories:
 
-                if len(catergories_occ_array[categories]) == 1 :
+#                 if len(catergories_occ_array[categories]) == 1 :
 
-                    id = catergories_occ_array[categories][0]
-                    print("iddd : ",id)
-                    img = cv2.imread(f"{data_name}/Instance_Segmentation/{p}.png", cv2.IMREAD_UNCHANGED) # plt.imread(path)
+#                     id = catergories_occ_array[categories][0]
+#                     print("iddd : ",id)
+#                     img = cv2.imread(f"{data_name}/Instance_Segmentation/{p}.png", cv2.IMREAD_UNCHANGED) # plt.imread(path)
 
-                    #print("img[817][308] : ", img[817][308])
-                    print("img[308][817] : ", img[308][817])
+#                     #print("img[817][308] : ", img[817][308])
+#                     print("img[308][817] : ", img[308][817])
 
 
-                    instance_img = instance(img, id)
-                    print("instance_img[308][817] : ", instance_img[308][817])
+#                     instance_img = instance(img, id)
+#                     print("instance_img[308][817] : ", instance_img[308][817])
 
 
-                    cv2.imwrite(f"{data_name}/Generated/Instance_Mask/{categories}/{p}.png", 255*instance_img)
+#                     cv2.imwrite(f"{data_name}/Generated/Instance_Mask/{categories}/{p}.png", 255*instance_img)
 
 

main.py

@@ -4,13 +4,12 @@ import json
 from prepare_data import reform_data
 #from pose import transform_pose
 #from bbox_2d import generate_2d_bbox
-from instance_mask import generate_instance_mask
+#from instance_mask import generate_instance_mask
 from fps_alg import generate_fps
 from bbox_3d import generate_3d_bbox
 from compute_features import process_compute
 import shutil
 
-
 def generate_folders(name, list_categories):
     is_exist = os.path.exists(name)
     if not is_exist:
@@ -66,6 +65,6 @@ if __name__ == '__main__':
     process_compute(dataset_name, Nb_camera, Nb_world, list_categories, occ_target)
     #transform_pose(dataset_name, Nb_camera, Nb_world, list_categories, occ_target)
     #generate_2d_bbox(dataset_name, Nb_camera, Nb_world, list_categories, occ_target)
-    generate_instance_mask(dataset_name, Nb_camera, Nb_world, list_categories, occ_target)
+    #generate_instance_mask(dataset_name, Nb_camera, Nb_world, list_categories, occ_target)
     generate_fps(dataset_name, camera, Nb_camera, Nb_world, list_categories, True)
     #generate_3d_bbox(dataset_name)