Mostafa-Samir / DNC-tensorflow

A TensorFlow implementation of DeepMind's Differential Neural Computers (DNC)
MIT License
581 stars 164 forks source link

TypeError: 'numpy.float64' object cannot be interpreted as an index #16

Open SeekPoint opened 7 years ago

SeekPoint commented 7 years ago

python tasks/copy/train.py --iterations=50000 Building Computational Graph ... Traceback (most recent call last): File "tasks/copy/train.py", line 82, in batch_size File "/Users/yike.ke/yike_prj/DNC-tensorflow/tasks/copy/dnc/dnc.py", line 46, in init self.controller = controller_class(self.input_size, self.output_size, self.read_heads, self.word_size, self.batch_size) File "/Users/yike.ke/yike_prj/DNC-tensorflow/tasks/copy/dnc/controller.py", line 45, in init self.network_vars() File "/Users/yike.ke/yike_prj/DNC-tensorflow/tasks/copy/feedforward_controller.py", line 16, in network_vars self.W1 = tf.Variable(tf.truncatednormal([input, 128], stddev=initialstd(input)), name='layer1_W') File "/Users/yike.ke/yike_prj/DNC-tensorflow/tasks/copy/feedforward_controller.py", line 13, in initial_std = lambda in_nodes: np.min(1e-2, np.sqrt(2.0 / in_nodes)) File "/Users/yike.ke/yike_prj/ve_tf0.11_py2/venv/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 2372, in amin out=out, **kwargs) File "/Users/yike.ke/yike_prj/ve_tf0.11_py2/venv/lib/python2.7/site-packages/numpy/core/_methods.py", line 29, in _amin return umr_minimum(a, axis, None, out, keepdims) TypeError: 'numpy.float64' object cannot be interpreted as an index