Error when run yolo.py

[Sakuralala]

Hi, when I run the code as the README.MD suggested,at the step of "python yolo.py",I got an error:TypeError: float() argument must be a string or a number, not 'dict'?Is there a way I can solve it?Thanks.

[qqwweee]

It is wired. Check the traceback to see where the error occurs. By the way, this repo is on Python3. If you are on Python2, error occurs somewhere.

[Sakuralala]

I use python3,and here is my running environment: python 3 + keras-gpu 2.15 +tensorflow-gpu 1.7 As for the traceback: Traceback (most recent call last): File "yolo.py", line 194, in detect_img(YOLO()) File "yolo.py", line 33, in init self.boxes, self.scores, self.classes = self.generate() File "yolo.py", line 54, in generate self.yolo_model = load_model(model_path, compile=False) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/models.py", line 243, in load_model model = model_from_config(model_config, custom_objects=custom_objects) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/models.py", line 317, in model_from_config return layer_module.deserialize(config, custom_objects=custom_objects) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/layers/init.py", line 55, in deserialize printable_module_name='layer') File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 144, in deserialize_keras_object list(custom_objects.items()))) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/engine/topology.py", line 2514, in from_config process_layer(layer_data) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/engine/topology.py", line 2500, in process_layer custom_objects=custom_objects) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/layers/init.py", line 55, in deserialize printable_module_name='layer') File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 146, in deserialize_keras_object return cls.from_config(config['config']) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/engine/topology.py", line 1271, in from_config return cls(**config) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/layers/advanced_activations.py", line 43, in init self.alpha = K.cast_to_floatx(alpha) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/keras/backend/common.py", line 110, in cast_to_floatx return np.asarray(x, dtype=_FLOATX) File "/root/anaconda2/envs/3dpy3/lib/python3.6/site-packages/numpy/core/numeric.py", line 531, in asarray return array(a, dtype, copy=False, order=order) TypeError: float() argument must be a string or a number, not 'dict' Because I'm new in using keras,so I'm not sure what error happened yet...Can you help me ?Thanks!

[qqwweee]

Perhaps something wrong with your environment, even if the version seems OK.

[zhlw2017]

hello！when i run the yolo.py as the README.MD suggested,I got the Error ：AttributeError：module ‘tensorflow.python.ops.nn’ has no attribute 'leaky_relu'. I don't know how to solve it，the environment is

Python 3.6
Keras 2.1.6
tensorflow 1.2.1

[zhlw2017]

额，问题已经解决了。 the error is killed，and the code is very good。

[gittigxuy]

@zhlw2017 ,怎么解决的呢？我的系统是ubuntu14.04，因此不能使用tf>=1.5，我的环境是

Python 3.6 Keras 2.1.5 tensorflow 1.3.0 请问一下如何解决的？可否加我QQ:1262485779交流一下,谢谢了