I got error at tf1.2:
mldl@mldlUB1604:~/ub16_prj/tf-differentiable-neural-computer$ python3 python/main.py copy data --summary-dir summary
== COPY ==
[*] Loading from cached data...
== DNC ==
2017-08-02 03:47:45.524244: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-02 03:47:45.524267: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-02 03:47:45.524285: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-08-02 03:47:45.524288: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-02 03:47:45.524311: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-08-02 03:47:45.614177: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:893] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2017-08-02 03:47:45.614533: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties:
name: GeForce GTX 950M
major: 5 minor: 0 memoryClockRate (GHz) 1.124
pciBusID 0000:01:00.0
Total memory: 3.95GiB
Free memory: 3.66GiB
2017-08-02 03:47:45.614566: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0
2017-08-02 03:47:45.614571: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: Y
2017-08-02 03:47:45.614601: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 950M, pci bus id: 0000:01:00.0)
Compiling timestep 2/3 (66.67 %)Traceback (most recent call last):
File "python/main.py", line 35, in
optimizer="RMSProp")
File "/home/mldl/ub16_prj/tf-differentiable-neural-computer/python/dnc.py", line 57, in init
self.compile()
File "/home/mldl/ub16_prj/tf-differentiable-neural-computer/python/dnc.py", line 132, in compile
output, state = lstm_cell(input_, state)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 180, in call
return super(RNNCell, self).call(inputs, state)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/base.py", line 441, in call
outputs = self.call(inputs, *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 383, in call
concat = _linear([inputs, h], 4 * self._num_units, True)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1017, in _linear
initializer=kernel_initializer)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 1065, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 962, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 360, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 183, in _rnn_get_variable
variable = getter(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 352, in _true_getter
use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 669, in _get_single_variable
found_var.get_shape()))
ValueError: Trying to share variable timestep_0/basic_lstm_cell/kernel, but specified shape (628, 2048) and found shape (568, 2048).
mldl@mldlUB1604:~/ub16_prj/tf-differentiable-neural-computer$