Run error, "ZeroDivisionError"

[Cody2333]

博主好，我在跑你的demo的时候遇到了这个问题，不知道该如何解决 root@fa817dfe202e:~/temp/py-captcha-breaking# python demo.py | tee ./demo.log Using Theano backend. Start demo.... Networks initialization.... Initial network1.... Traceback (most recent call last): File "demo.py", line 427, in main() File "demo.py", line 257, in main phase1_model = initial_num_char_phase1() File "demo.py", line 88, in initial_num_char_phase1 model.add(Dense(input_dim=1646, output_dim=256, init='glorot_uniform')) File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/models.py", line 312, in add output_tensor = layer(self.outputs[0]) File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/engine/topology.py", line 487, in call self.build(input_shapes[0]) File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/layers/core.py", line 695, in build name='{}_W'.format(self.name)) File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/initializations.py", line 58, in glorot_uniform s = np.sqrt(6. / (fan_in + fan_out)) ZeroDivisionError: float division by zero

[iamGavinZhou]

I think problem is here "model.add(Dense(input_dim=1646, output_dim=256, init='glorot_uniform'))", input dim doesn't match

[hits-nlp]

I have the same problem (see issue #2527). Any solutions so far?