yichen914/myalphagozeroonconnect4

My Simple Implementation of AlphaGo Zero on Connect4

myalphagozeroonconnect4's Issues

Question about the network used

Hello

Can you tell me what about the model your using.
How many conv-layers, residual layers etc.

Trying to run monte_carlo_tree.py results in an error.

Thanks for publishing your experiments, tried to run the monte_carlo_tree program but the name is missing in the current master:

> python monte_carlo_tree.py
Using TensorFlow backend.
Traceback (most recent call last):
  File "monte_carlo_tree.py", line 174, in <module>
    root_path=None)
TypeError: __init__() missing 1 required positional argument: 'name'

Question about MCTS

First, great implementation, this really helped me understand how AlphaGo Zero works, and I’ve used it for other games as well.
There’s is still one thing I couldn’t understand though. Why do you return -v instead of v when you do the Monte Carlo tree search?

Error running training_multithreads.py

Same error is given regardless of the response Y or N

>python training_multithreads.py
Using TensorFlow backend.
Would you like to train the network before test it (answer Y or N): N
2018-12-05 09:24:45.572326: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2018-12-05 09:24:45.816212: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\common_runtime\gpu\gpu_device.cc:1105] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:01:00.0
totalMemory: 11.00GiB freeMemory: 9.09GiB
2018-12-05 09:24:45.825529: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\common_runtime\gpu\gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
Traceback (most recent call last):
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 686, in _call_cpp_shape_fn_impl
    input_tensors_as_shapes, status)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be rank 1 but is rank 0 for 'batch_normalization_1/cond/Reshape_4' (op: 'Reshape') with input shapes: [1,7,1,1], [].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "training_multithreads.py", line 328, in <module>
    best_network = Network('Best')
  File "C:\Users\Agustin\Documents\MyAlphaGoZeroOnConnect4\src\Connect4\network.py", line 31, in __init__
    self.model = self._build_model()
  File "C:\Users\Agustin\Documents\MyAlphaGoZeroOnConnect4\src\Connect4\network.py", line 87, in _build_model
    kernel_size=self.layers_metadata[0]['kernel_size'])
  File "C:\Users\Agustin\Documents\MyAlphaGoZeroOnConnect4\src\Connect4\network.py", line 43, in _add_conv_block
    block = BatchNormalization(axis=1)(block)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\keras\engine\base_layer.py", line 457, in __call__
    output = self.call(inputs, **kwargs)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\keras\layers\normalization.py", line 206, in call
    training=training)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py", line 3123, in in_train_phase
    x = switch(training, x, alt)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py", line 3058, in switch
    else_expression_fn)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\util\deprecation.py", line 316, in new_func
    return func(*args, **kwargs)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 1903, in cond
    orig_res_f, res_f = context_f.BuildCondBranch(false_fn)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 1752, in BuildCondBranch
    original_result = fn()
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\keras\layers\normalization.py", line 167, in normalize_inference
    epsilon=self.epsilon)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py", line 1908, in batch_normalization
    mean = tf.reshape(mean, (-1))
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 5184, in reshape
    "Reshape", tensor=tensor, shape=shape, name=name)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 3162, in create_op
    compute_device=compute_device)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 3208, in _create_op_helper
    set_shapes_for_outputs(op)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 2427, in set_shapes_for_outputs
    return _set_shapes_for_outputs(op)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 2400, in _set_shapes_for_outputs
    shapes = shape_func(op)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 2330, in call_with_requiring
    return call_cpp_shape_fn(op, require_shape_fn=True)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 627, in call_cpp_shape_fn
    require_shape_fn)
  File "C:\Users\Agustin\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 691, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Shape must be rank 1 but is rank 0 for 'batch_normalization_1/cond/Reshape_4' (op: 'Reshape') with input shapes: [1,7,1,1], [].