以下のgithubからスクリプトをもってきて試しているのですが、クイックスタート4番「python main.py」で以下のエラーがでます。デコーデのコード(decode('utf-8'))を全て無くしてもうまくいかず。。。どうすれば良いかよくわかりません。
宜しくお願いします。
github
1https://github.com/yehengchen/Object-Detection-and-Tracking/tree/master/OneStage/yolo/deep_sort_yolov3
error
1Using TensorFlow backend. 2/Users/takehsi.ono/field_1/.venv/lib/python3.6/site-packages/sklearn/utils/linear_assignment_.py:21: DeprecationWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead. 3 DeprecationWarning) 42020-11-11 15:24:40.294855: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 52020-11-11 15:24:40.307349: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7ff9cbddf940 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 62020-11-11 15:24:40.307365: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 7Traceback (most recent call last): 8 File "main.py", line 172, in <module> 9 main(YOLO()) 10 File "/Users/takehsi.ono/field_1/deep_sort_yolov3/yolo.py", line 50, in __init__ 11 self.boxes, self.scores, self.classes = self.generate() 12 File "/Users/takehsi.ono/field_1/deep_sort_yolov3/yolo.py", line 72, in generate 13 self.yolo_model = load_model(model_path, compile=False) 14 File "/Users/takehsi.ono/field_1/.venv/lib/python3.6/site-packages/keras/engine/saving.py", line 492, in load_wrapper 15 return load_function(*args, **kwargs) 16 File "/Users/takehsi.ono/field_1/.venv/lib/python3.6/site-packages/keras/engine/saving.py", line 584, in load_model 17 model = _deserialize_model(h5dict, custom_objects, compile) 18 File "/Users/takehsi.ono/field_1/.venv/lib/python3.6/site-packages/keras/engine/saving.py", line 273, in _deserialize_model 19 model_config = json.loads(model_config.decode('utf-8')) 20AttributeError: 'str' object has no attribute 'decode'
回答1件
あなたの回答
tips
プレビュー
バッドをするには、ログインかつ
こちらの条件を満たす必要があります。
退会済みユーザー
2020/11/12 00:50