main.py가 실행이 안됩니다.

[hola-ai]

아래의 명령으로 실행했습니다.
python main.py --stock_code 005930 005380 015760 --rl_method a3c --net lstm --num_steps 5 --learning --num_epoches 1000 --lr 0.001 --start_epsilon 1 --discount_factor 0.9 --output_name train --start_date 20170101 --end_date 20181231

에러 메세지는 아래와 같습니다.
From /home/justin/tt/rltrader/networks.py:25: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

2021-03-11 17:05:17.985730: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2021-03-11 17:05:18.005756: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3600000000 Hz
2021-03-11 17:05:18.006034: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5634039255c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-03-11 17:05:18.006052: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
From /home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/initializers.py:143: calling RandomNormal.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
From /home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.init (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
Traceback (most recent call last):
File "main.py", line 163, in
'policy_network_path': policy_network_path})
File "/home/justin/tt/rltrader/learners.py", line 533, in init
input_dim=self.num_features)
File "/home/justin/tt/rltrader/networks.py", line 82, in get_shared_network
Input((num_steps, input_dim)))
File "/home/justin/tt/rltrader/networks.py", line 164, in get_network_head
kernel_initializer='random_normal')(inp)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 623, in call
return super(RNN, self).call(inputs, **kwargs)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 854, in call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 2549, in call
inputs, mask=mask, training=training, initial_state=initial_state)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 682, in call
inputs, initial_state, constants)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 798, in _process_inputs
initial_state = self.get_initial_state(inputs)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 606, in get_initial_state
inputs=None, batch_size=batch_size, dtype=dtype)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 2314, in get_initial_state
self, inputs, batch_size, dtype))
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 2752, in _generate_zero_filled_state_for_cell
return _generate_zero_filled_state(batch_size, cell.state_size, dtype)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 2768, in _generate_zero_filled_state
return nest.map_structure(create_zeros, state_size)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/util/nest.py", line 536, in map_structure
structure[0], [func(*x) for x in entries],
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/util/nest.py", line 536, in
structure[0], [func(*x) for x in entries],
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/recurrent.py", line 2765, in create_zeros
return array_ops.zeros(init_state_size, dtype=dtype)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line 2338, in zeros
output = _constant_if_small(zero, shape, dtype, name)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line 2295, in _constant_if_small
if np.prod(shape) < 1000:
File "<array_function internals>", line 6, in prod
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 3031, in prod
keepdims=keepdims, initial=initial, where=where)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 87, in _wrapreduction
return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
File "/home/justin/anaconda3/envs/rlt/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 736, in array
" array.".format(self.name))
NotImplementedError: Cannot convert a symbolic Tensor (lstm/strided_slice:0) to a numpy array.

[quantylab]

@udp-justin-lee

python 3.6 + cuda 10.0 + cudnn 7.3.1 로 시도해 보시길 권해드립니다.
GPU 사용가능하시면 다음과 같이 환경 만드시면 됩니다.

conda create -n rltrader python=3.6
conda activate rltrader
pip install tensorflow-gpu==1.15
conda install cudatoolkit=10.0
conda install cudnn=7.3.1
pip install numpy
pip install pandas